TY  - CONF
AU  - Jocić, Darko
AU  - Ćirović, Velimir
AU  - Aleksendrić, Dragan
PY  - 2019
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3094
AB  - Object detection using deep learning over the years became one of the most popular methods for implementation in autonomous systems. Autonomous vehicle requires very reliable and accurate identification and recognition of surrounding objects in real traffic environments to achieve decent detection results. In this paper, special type of Artificial Neural Network (ANN) named Convolutional Neural Network (CNN) was used for identification and recognition of surrounding objects in real traffic. The new model based on CNN was trained and developed to be able to identify and recognize 4 different classes of objects: cars, traffic lights, persons and bicycles. The developed model has shown 94.6% accuracy of object identification and recognizing on the test set.
PB  - Springer International Publishing Ag, Cham
C3  - Experimental and Numerical Investigations in Materials Science and Engineering
T1  - Identification and Recognition of Vehicle Environment Using Artificial Neural Networks
EP  - 219
SP  - 208
VL  - 54
DO  - 10.1007/978-3-319-99620-2_16
ER  - 

@conference{
author = "Jocić, Darko and Ćirović, Velimir and Aleksendrić, Dragan",
year = "2019",
abstract = "Object detection using deep learning over the years became one of the most popular methods for implementation in autonomous systems. Autonomous vehicle requires very reliable and accurate identification and recognition of surrounding objects in real traffic environments to achieve decent detection results. In this paper, special type of Artificial Neural Network (ANN) named Convolutional Neural Network (CNN) was used for identification and recognition of surrounding objects in real traffic. The new model based on CNN was trained and developed to be able to identify and recognize 4 different classes of objects: cars, traffic lights, persons and bicycles. The developed model has shown 94.6% accuracy of object identification and recognizing on the test set.",
publisher = "Springer International Publishing Ag, Cham",
journal = "Experimental and Numerical Investigations in Materials Science and Engineering",
title = "Identification and Recognition of Vehicle Environment Using Artificial Neural Networks",
pages = "219-208",
volume = "54",
doi = "10.1007/978-3-319-99620-2_16"
}

Jocić, D., Ćirović, V.,& Aleksendrić, D.. (2019). Identification and Recognition of Vehicle Environment Using Artificial Neural Networks. in Experimental and Numerical Investigations in Materials Science and Engineering
Springer International Publishing Ag, Cham., 54, 208-219.
https://doi.org/10.1007/978-3-319-99620-2_16

Jocić D, Ćirović V, Aleksendrić D. Identification and Recognition of Vehicle Environment Using Artificial Neural Networks. in Experimental and Numerical Investigations in Materials Science and Engineering. 2019;54:208-219.
doi:10.1007/978-3-319-99620-2_16 .

Jocić, Darko, Ćirović, Velimir, Aleksendrić, Dragan, "Identification and Recognition of Vehicle Environment Using Artificial Neural Networks" in Experimental and Numerical Investigations in Materials Science and Engineering, 54 (2019):208-219,
https://doi.org/10.1007/978-3-319-99620-2_16 . .

TY  - JOUR
AU  - Aleksendrić, Dragan
AU  - Bellini, Costanzo
AU  - Carlone, Pierpaolo
AU  - Ćirović, Velimir
AU  - Rubino, Felice
AU  - Sorrentino, Luca
PY  - 2019
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3032
AB  - This article addresses the optimization of curing process for thick composite laminates. The proposed methodology aims at the evaluation of the thermal cycle promoting a desired evolution of the degree of cure inside the material. At the same time, temperature overshooting as well as excessive temperature and cure degree gradient through the thickness of the material are prevented. The developed approach is based on the integrated application of artificial neural networks and a fuzzy logic controller. The neural networks promptly predict the behavior of composite material during curing process, while the fuzzy logic controller continuously and opportunely adjusts the proper variations on the imposed thermal cycle. The results highlighted the efficiency of the method in comparison with the cure profiles dictated by the material suppliers. For thick laminates, a reduction of 35% of cure time and improvements of approximately 10% of temperature overshooting was obtained compared to conventional curing cycles. The method was validated by experimental tests.
PB  - Taylor & Francis Inc, Philadelphia
T2  - Materials and Manufacturing Processes
T1  - Neural-fuzzy optimization of thick composites curing process
EP  - 273
IS  - 3
SP  - 262
VL  - 34
DO  - 10.1080/10426914.2018.1512116
ER  - 

@article{
author = "Aleksendrić, Dragan and Bellini, Costanzo and Carlone, Pierpaolo and Ćirović, Velimir and Rubino, Felice and Sorrentino, Luca",
year = "2019",
abstract = "This article addresses the optimization of curing process for thick composite laminates. The proposed methodology aims at the evaluation of the thermal cycle promoting a desired evolution of the degree of cure inside the material. At the same time, temperature overshooting as well as excessive temperature and cure degree gradient through the thickness of the material are prevented. The developed approach is based on the integrated application of artificial neural networks and a fuzzy logic controller. The neural networks promptly predict the behavior of composite material during curing process, while the fuzzy logic controller continuously and opportunely adjusts the proper variations on the imposed thermal cycle. The results highlighted the efficiency of the method in comparison with the cure profiles dictated by the material suppliers. For thick laminates, a reduction of 35% of cure time and improvements of approximately 10% of temperature overshooting was obtained compared to conventional curing cycles. The method was validated by experimental tests.",
publisher = "Taylor & Francis Inc, Philadelphia",
journal = "Materials and Manufacturing Processes",
title = "Neural-fuzzy optimization of thick composites curing process",
pages = "273-262",
number = "3",
volume = "34",
doi = "10.1080/10426914.2018.1512116"
}

Aleksendrić, D., Bellini, C., Carlone, P., Ćirović, V., Rubino, F.,& Sorrentino, L.. (2019). Neural-fuzzy optimization of thick composites curing process. in Materials and Manufacturing Processes
Taylor & Francis Inc, Philadelphia., 34(3), 262-273.
https://doi.org/10.1080/10426914.2018.1512116

Aleksendrić D, Bellini C, Carlone P, Ćirović V, Rubino F, Sorrentino L. Neural-fuzzy optimization of thick composites curing process. in Materials and Manufacturing Processes. 2019;34(3):262-273.
doi:10.1080/10426914.2018.1512116 .

Aleksendrić, Dragan, Bellini, Costanzo, Carlone, Pierpaolo, Ćirović, Velimir, Rubino, Felice, Sorrentino, Luca, "Neural-fuzzy optimization of thick composites curing process" in Materials and Manufacturing Processes, 34, no. 3 (2019):262-273,
https://doi.org/10.1080/10426914.2018.1512116 . .

TY  - CHAP
AU  - Carlone, Pierpaolo
AU  - Aleksendrić, Dragan
AU  - Rubino, Felice
AU  - Ćirović, Velimir
PY  - 2018
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/2992
AB  - Autoclave curing is a common practice to manufacture high temperature thermoset matrix composites. The cycle design and optimization of the temperature-time curve is a key issue for a competitive production. In this paper artificial neural networks (ANN), as a technique of artificial intelligence, were used for prediction of the composite temperature profile during the autoclave curing process. Different neural network models have been investigated regarding their capabilities for prediction of the composite temperature profile. The new neural network model has been developed able to predict the composite temperature profile in the wide range of manufacturing conditions changing.
PB  - Pleiades journals
T2  - Lecture Notes in Mechanical Engineering
T1  - Artificial neural networks in advanced thermoset matrix composite manufacturing
EP  - 88
IS  - 9783319895628
SP  - 78
VL  - 0
DO  - 10.1007/978-3-319-89563-5_5
ER  - 

@inbook{
author = "Carlone, Pierpaolo and Aleksendrić, Dragan and Rubino, Felice and Ćirović, Velimir",
year = "2018",
abstract = "Autoclave curing is a common practice to manufacture high temperature thermoset matrix composites. The cycle design and optimization of the temperature-time curve is a key issue for a competitive production. In this paper artificial neural networks (ANN), as a technique of artificial intelligence, were used for prediction of the composite temperature profile during the autoclave curing process. Different neural network models have been investigated regarding their capabilities for prediction of the composite temperature profile. The new neural network model has been developed able to predict the composite temperature profile in the wide range of manufacturing conditions changing.",
publisher = "Pleiades journals",
journal = "Lecture Notes in Mechanical Engineering",
booktitle = "Artificial neural networks in advanced thermoset matrix composite manufacturing",
pages = "88-78",
number = "9783319895628",
volume = "0",
doi = "10.1007/978-3-319-89563-5_5"
}

Carlone, P., Aleksendrić, D., Rubino, F.,& Ćirović, V.. (2018). Artificial neural networks in advanced thermoset matrix composite manufacturing. in Lecture Notes in Mechanical Engineering
Pleiades journals., 0(9783319895628), 78-88.
https://doi.org/10.1007/978-3-319-89563-5_5

Carlone P, Aleksendrić D, Rubino F, Ćirović V. Artificial neural networks in advanced thermoset matrix composite manufacturing. in Lecture Notes in Mechanical Engineering. 2018;0(9783319895628):78-88.
doi:10.1007/978-3-319-89563-5_5 .

Carlone, Pierpaolo, Aleksendrić, Dragan, Rubino, Felice, Ćirović, Velimir, "Artificial neural networks in advanced thermoset matrix composite manufacturing" in Lecture Notes in Mechanical Engineering, 0, no. 9783319895628 (2018):78-88,
https://doi.org/10.1007/978-3-319-89563-5_5 . .

TY  - CONF
AU  - Rubino, Felice
AU  - Carlone, Pierpaolo
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
AU  - Sorrentino, Luca
AU  - Bellini, Costanzo
PY  - 2016
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/2418
AB  - The curing process of thermosetting resins plays a key role on the final quality of the composite material components. Soft computing techniques proved to be an efficient method to control and optimize the curing process, replacing the conventional experimental and numerical approaches. In this paper artificial neural network (ANN) and fuzzy logic control (FLC) were implemented together to predict and control the temperature and degree of cure profile during the autoclave curing process. The obtained outcomes proved the capability of ANNs and FLC with respect to the hard computing methods.
PB  - Amer Inst Physics, Melville
C3  - Proceedings of The 19th International Esaform Conference on Material Forming (Esaform 2016)
T1  - Hard and Soft Computing Models of Composite Curing Process Looking Toward Monitoring and Control
VL  - 1769
DO  - 10.1063/1.4963438
ER  - 

@conference{
author = "Rubino, Felice and Carlone, Pierpaolo and Aleksendrić, Dragan and Ćirović, Velimir and Sorrentino, Luca and Bellini, Costanzo",
year = "2016",
abstract = "The curing process of thermosetting resins plays a key role on the final quality of the composite material components. Soft computing techniques proved to be an efficient method to control and optimize the curing process, replacing the conventional experimental and numerical approaches. In this paper artificial neural network (ANN) and fuzzy logic control (FLC) were implemented together to predict and control the temperature and degree of cure profile during the autoclave curing process. The obtained outcomes proved the capability of ANNs and FLC with respect to the hard computing methods.",
publisher = "Amer Inst Physics, Melville",
journal = "Proceedings of The 19th International Esaform Conference on Material Forming (Esaform 2016)",
title = "Hard and Soft Computing Models of Composite Curing Process Looking Toward Monitoring and Control",
volume = "1769",
doi = "10.1063/1.4963438"
}

Rubino, F., Carlone, P., Aleksendrić, D., Ćirović, V., Sorrentino, L.,& Bellini, C.. (2016). Hard and Soft Computing Models of Composite Curing Process Looking Toward Monitoring and Control. in Proceedings of The 19th International Esaform Conference on Material Forming (Esaform 2016)
Amer Inst Physics, Melville., 1769.
https://doi.org/10.1063/1.4963438

Rubino F, Carlone P, Aleksendrić D, Ćirović V, Sorrentino L, Bellini C. Hard and Soft Computing Models of Composite Curing Process Looking Toward Monitoring and Control. in Proceedings of The 19th International Esaform Conference on Material Forming (Esaform 2016). 2016;1769.
doi:10.1063/1.4963438 .

Rubino, Felice, Carlone, Pierpaolo, Aleksendrić, Dragan, Ćirović, Velimir, Sorrentino, Luca, Bellini, Costanzo, "Hard and Soft Computing Models of Composite Curing Process Looking Toward Monitoring and Control" in Proceedings of The 19th International Esaform Conference on Material Forming (Esaform 2016), 1769 (2016),
https://doi.org/10.1063/1.4963438 . .

TY  - GEN
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
AU  - Smiljanić, Dušan
AU  - Matić, Veljko
PY  - 2016
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5771
PB  - Универзитета у Београду Машински факултет
T1  - Метода управљања притиском активирања кочница на основу процене услова приањања точка у подужном правцу
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5771
ER  - 

@misc{
author = "Aleksendrić, Dragan and Ćirović, Velimir and Smiljanić, Dušan and Matić, Veljko",
year = "2016",
publisher = "Универзитета у Београду Машински факултет",
title = "Метода управљања притиском активирања кочница на основу процене услова приањања точка у подужном правцу",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5771"
}

Aleksendrić, D., Ćirović, V., Smiljanić, D.,& Matić, V.. (2016). Метода управљања притиском активирања кочница на основу процене услова приањања точка у подужном правцу. 
Универзитета у Београду Машински факултет..
https://hdl.handle.net/21.15107/rcub_machinery_5771

Aleksendrić D, Ćirović V, Smiljanić D, Matić V. Метода управљања притиском активирања кочница на основу процене услова приањања точка у подужном правцу. 2016;.
https://hdl.handle.net/21.15107/rcub_machinery_5771 .

Aleksendrić, Dragan, Ćirović, Velimir, Smiljanić, Dušan, Matić, Veljko, "Метода управљања притиском активирања кочница на основу процене услова приањања точка у подужном правцу" (2016),
https://hdl.handle.net/21.15107/rcub_machinery_5771 .

TY  - JOUR
AU  - Aleksendrić, Dragan
AU  - Carlone, Pierpaolo
AU  - Ćirović, Velimir
PY  - 2016
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/2484
AB  - An intelligent optimization model aiming at off-line or pre-series optimization of the thermal curing cycle of polymer matrix composites is proposed and discussed. The computational procedure is based on the coupling of a finite element thermochemical process model, dynamic artificial neural networks and genetic algorithms. Objective of the optimization routine is the maximization of the composite degree of cure by the definition of the autoclave temperature. Obtained outcomes evidenced the capability of the method as well as its efficiency with respect to hard computing or experimental procedures.
PB  - Springer, Dordrecht
T2  - Applied Composite Materials
T1  - Optimization of the Temperature-Time Curve for the Curing Process of Thermoset Matrix Composites
EP  - 1063
IS  - 5
SP  - 1047
VL  - 23
DO  - 10.1007/s10443-016-9499-y
ER  - 

@article{
author = "Aleksendrić, Dragan and Carlone, Pierpaolo and Ćirović, Velimir",
year = "2016",
abstract = "An intelligent optimization model aiming at off-line or pre-series optimization of the thermal curing cycle of polymer matrix composites is proposed and discussed. The computational procedure is based on the coupling of a finite element thermochemical process model, dynamic artificial neural networks and genetic algorithms. Objective of the optimization routine is the maximization of the composite degree of cure by the definition of the autoclave temperature. Obtained outcomes evidenced the capability of the method as well as its efficiency with respect to hard computing or experimental procedures.",
publisher = "Springer, Dordrecht",
journal = "Applied Composite Materials",
title = "Optimization of the Temperature-Time Curve for the Curing Process of Thermoset Matrix Composites",
pages = "1063-1047",
number = "5",
volume = "23",
doi = "10.1007/s10443-016-9499-y"
}

Aleksendrić, D., Carlone, P.,& Ćirović, V.. (2016). Optimization of the Temperature-Time Curve for the Curing Process of Thermoset Matrix Composites. in Applied Composite Materials
Springer, Dordrecht., 23(5), 1047-1063.
https://doi.org/10.1007/s10443-016-9499-y

Aleksendrić D, Carlone P, Ćirović V. Optimization of the Temperature-Time Curve for the Curing Process of Thermoset Matrix Composites. in Applied Composite Materials. 2016;23(5):1047-1063.
doi:10.1007/s10443-016-9499-y .

Aleksendrić, Dragan, Carlone, Pierpaolo, Ćirović, Velimir, "Optimization of the Temperature-Time Curve for the Curing Process of Thermoset Matrix Composites" in Applied Composite Materials, 23, no. 5 (2016):1047-1063,
https://doi.org/10.1007/s10443-016-9499-y . .

TY  - GEN
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
PY  - 2015
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5770
PB  - Универзитета у Београду Машински факултет
T1  - Метода за оцену услова приањања коченог точка помоћу фази логике
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5770
ER  - 

@misc{
author = "Aleksendrić, Dragan and Ćirović, Velimir",
year = "2015",
publisher = "Универзитета у Београду Машински факултет",
title = "Метода за оцену услова приањања коченог точка помоћу фази логике",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5770"
}

Aleksendrić, D.,& Ćirović, V.. (2015). Метода за оцену услова приањања коченог точка помоћу фази логике. 
Универзитета у Београду Машински факултет..
https://hdl.handle.net/21.15107/rcub_machinery_5770

Aleksendrić D, Ćirović V. Метода за оцену услова приањања коченог точка помоћу фази логике. 2015;.
https://hdl.handle.net/21.15107/rcub_machinery_5770 .

Aleksendrić, Dragan, Ćirović, Velimir, "Метода за оцену услова приањања коченог точка помоћу фази логике" (2015),
https://hdl.handle.net/21.15107/rcub_machinery_5770 .

TY  - CONF
AU  - Carlone, Pierpaolo
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
AU  - Palazzo, Gaetano S.
PY  - 2014
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1877
AB  - Autoclave curing is a common practice to manufacture high temperature thermoset matrix composites in order to improve the mechanical properties of the final product. The cycle design i.e. the definition and optimization of the temperature-time curve is a key issue for a competitive production. In this paper a very fast and effective procedure, based on the coupling of a finite element thermochemical model of the process and an artificial neural network, is proposed to predict the evolution of temperature in predefined control points inside the processing material. The model has been tested against the imposed thermal cycle used as an input. The procedure is tested simulating the curing process of a three-dimensional double-curved shape. Obtained outcomes highlighted the remarkable capabilities of the implemented procedure in terms of reliability of temperature predictions and of drastic reduction of the computational time with respect to classic computational models.
PB  - Trans Tech Publications Ltd, Durnten-Zurich
C3  - Material Forming Esaform 2014
T1  - Modelling of thermoset matrix composite curing process
EP  - 1674
SP  - 1667
VL  - 611-612
DO  - 10.4028/www.scientific.net/KEM.611-612.1667
ER  - 

@conference{
author = "Carlone, Pierpaolo and Aleksendrić, Dragan and Ćirović, Velimir and Palazzo, Gaetano S.",
year = "2014",
abstract = "Autoclave curing is a common practice to manufacture high temperature thermoset matrix composites in order to improve the mechanical properties of the final product. The cycle design i.e. the definition and optimization of the temperature-time curve is a key issue for a competitive production. In this paper a very fast and effective procedure, based on the coupling of a finite element thermochemical model of the process and an artificial neural network, is proposed to predict the evolution of temperature in predefined control points inside the processing material. The model has been tested against the imposed thermal cycle used as an input. The procedure is tested simulating the curing process of a three-dimensional double-curved shape. Obtained outcomes highlighted the remarkable capabilities of the implemented procedure in terms of reliability of temperature predictions and of drastic reduction of the computational time with respect to classic computational models.",
publisher = "Trans Tech Publications Ltd, Durnten-Zurich",
journal = "Material Forming Esaform 2014",
title = "Modelling of thermoset matrix composite curing process",
pages = "1674-1667",
volume = "611-612",
doi = "10.4028/www.scientific.net/KEM.611-612.1667"
}

Carlone, P., Aleksendrić, D., Ćirović, V.,& Palazzo, G. S.. (2014). Modelling of thermoset matrix composite curing process. in Material Forming Esaform 2014
Trans Tech Publications Ltd, Durnten-Zurich., 611-612, 1667-1674.
https://doi.org/10.4028/www.scientific.net/KEM.611-612.1667

Carlone P, Aleksendrić D, Ćirović V, Palazzo GS. Modelling of thermoset matrix composite curing process. in Material Forming Esaform 2014. 2014;611-612:1667-1674.
doi:10.4028/www.scientific.net/KEM.611-612.1667 .

Carlone, Pierpaolo, Aleksendrić, Dragan, Ćirović, Velimir, Palazzo, Gaetano S., "Modelling of thermoset matrix composite curing process" in Material Forming Esaform 2014, 611-612 (2014):1667-1674,
https://doi.org/10.4028/www.scientific.net/KEM.611-612.1667 . .

TY  - GEN
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
AU  - Carlone, Pierpaolo
PY  - 2014
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5769
PB  - Универзитета у Београду Машински факултет
T1  - Метода предвиђања утицаја температуре на процес полимеризације композитног материјала
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5769
ER  - 

@misc{
author = "Aleksendrić, Dragan and Ćirović, Velimir and Carlone, Pierpaolo",
year = "2014",
publisher = "Универзитета у Београду Машински факултет",
title = "Метода предвиђања утицаја температуре на процес полимеризације композитног материјала",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5769"
}

Aleksendrić, D., Ćirović, V.,& Carlone, P.. (2014). Метода предвиђања утицаја температуре на процес полимеризације композитног материјала. 
Универзитета у Београду Машински факултет..
https://hdl.handle.net/21.15107/rcub_machinery_5769

Aleksendrić D, Ćirović V, Carlone P. Метода предвиђања утицаја температуре на процес полимеризације композитног материјала. 2014;.
https://hdl.handle.net/21.15107/rcub_machinery_5769 .

Aleksendrić, Dragan, Ćirović, Velimir, Carlone, Pierpaolo, "Метода предвиђања утицаја температуре на процес полимеризације композитног материјала" (2014),
https://hdl.handle.net/21.15107/rcub_machinery_5769 .

TY  - JOUR
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
PY  - 2014
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1996
AB  - Since the driver obtains important feedback of a vehicle's dynamics and its braking capabilities depending on the change of brake performance, it represents an important aspect of a vehicle's performance and its quality of use. Sensitivity of braking torque vs. the friction couple interaction, under different braking conditions, is one of the most important properties of the disc brake. In this paper, we investigated possibilities for an intelligent dynamic optimisation of automotive braking system performance. The hybrid neuro-genetic optimisation model was developed in order to perform dynamic control and optimisation of the disc brake performance during a braking cycle. This model provided stabilisation of the brake performance and their maximisation vs. the brake pedal travel, selected by the driver, and the influence of the initial speed during a braking cycle. The model provided the disc brake actuation pressure which is adjusted upto the level that provides stable and, for current braking regimes, maximum braking torque values.
PB  - Inderscience Enterprises Ltd, Geneva
T2  - International Journal of Vehicle Design
T1  - Neuro-genetic optimisation of disc brake speed sensitivity
EP  - 271
IS  - 3
SP  - 258
VL  - 66
DO  - 10.1504/IJVD.2014.065716
ER  - 

@article{
author = "Aleksendrić, Dragan and Ćirović, Velimir",
year = "2014",
abstract = "Since the driver obtains important feedback of a vehicle's dynamics and its braking capabilities depending on the change of brake performance, it represents an important aspect of a vehicle's performance and its quality of use. Sensitivity of braking torque vs. the friction couple interaction, under different braking conditions, is one of the most important properties of the disc brake. In this paper, we investigated possibilities for an intelligent dynamic optimisation of automotive braking system performance. The hybrid neuro-genetic optimisation model was developed in order to perform dynamic control and optimisation of the disc brake performance during a braking cycle. This model provided stabilisation of the brake performance and their maximisation vs. the brake pedal travel, selected by the driver, and the influence of the initial speed during a braking cycle. The model provided the disc brake actuation pressure which is adjusted upto the level that provides stable and, for current braking regimes, maximum braking torque values.",
publisher = "Inderscience Enterprises Ltd, Geneva",
journal = "International Journal of Vehicle Design",
title = "Neuro-genetic optimisation of disc brake speed sensitivity",
pages = "271-258",
number = "3",
volume = "66",
doi = "10.1504/IJVD.2014.065716"
}

Aleksendrić, D.,& Ćirović, V.. (2014). Neuro-genetic optimisation of disc brake speed sensitivity. in International Journal of Vehicle Design
Inderscience Enterprises Ltd, Geneva., 66(3), 258-271.
https://doi.org/10.1504/IJVD.2014.065716

Aleksendrić D, Ćirović V. Neuro-genetic optimisation of disc brake speed sensitivity. in International Journal of Vehicle Design. 2014;66(3):258-271.
doi:10.1504/IJVD.2014.065716 .

Aleksendrić, Dragan, Ćirović, Velimir, "Neuro-genetic optimisation of disc brake speed sensitivity" in International Journal of Vehicle Design, 66, no. 3 (2014):258-271,
https://doi.org/10.1504/IJVD.2014.065716 . .

TY  - JOUR
AU  - Carlone, Pierpaolo
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
AU  - Palazzo, Gaetano S.
PY  - 2014
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1915
AB  - Thermal curing is a common practice to manufacture high temperature thermosetting matrix composites, in order to improve the mechanical properties of the final product. The cycle design i.e. the definition and optimization of the temperature time curve is a key issue for a competitive production. In this framework, a suitable model describing the composite temperature and degree of cure variations versus the imposed thermal cycle is highly desirable. An effective procedure, based on the coupling of a finite element thermochemical model of the process and an artificial neural network, is herein proposed and tested. Obtained outcomes highlight the remarkable capabilities of the implemented procedure in terms of reliability of temperature and degree of cure predictions.
PB  - Elsevier Sci Ltd, Oxford
T2  - Composites Part B-Engineering
T1  - Meta-modeling of the curing process of thermoset matrix composites by means of a FEM-ANN approach
EP  - 448
SP  - 441
VL  - 67
DO  - 10.1016/j.compositesb.2014.08.022
ER  - 

@article{
author = "Carlone, Pierpaolo and Aleksendrić, Dragan and Ćirović, Velimir and Palazzo, Gaetano S.",
year = "2014",
abstract = "Thermal curing is a common practice to manufacture high temperature thermosetting matrix composites, in order to improve the mechanical properties of the final product. The cycle design i.e. the definition and optimization of the temperature time curve is a key issue for a competitive production. In this framework, a suitable model describing the composite temperature and degree of cure variations versus the imposed thermal cycle is highly desirable. An effective procedure, based on the coupling of a finite element thermochemical model of the process and an artificial neural network, is herein proposed and tested. Obtained outcomes highlight the remarkable capabilities of the implemented procedure in terms of reliability of temperature and degree of cure predictions.",
publisher = "Elsevier Sci Ltd, Oxford",
journal = "Composites Part B-Engineering",
title = "Meta-modeling of the curing process of thermoset matrix composites by means of a FEM-ANN approach",
pages = "448-441",
volume = "67",
doi = "10.1016/j.compositesb.2014.08.022"
}

Carlone, P., Aleksendrić, D., Ćirović, V.,& Palazzo, G. S.. (2014). Meta-modeling of the curing process of thermoset matrix composites by means of a FEM-ANN approach. in Composites Part B-Engineering
Elsevier Sci Ltd, Oxford., 67, 441-448.
https://doi.org/10.1016/j.compositesb.2014.08.022

Carlone P, Aleksendrić D, Ćirović V, Palazzo GS. Meta-modeling of the curing process of thermoset matrix composites by means of a FEM-ANN approach. in Composites Part B-Engineering. 2014;67:441-448.
doi:10.1016/j.compositesb.2014.08.022 .

Carlone, Pierpaolo, Aleksendrić, Dragan, Ćirović, Velimir, Palazzo, Gaetano S., "Meta-modeling of the curing process of thermoset matrix composites by means of a FEM-ANN approach" in Composites Part B-Engineering, 67 (2014):441-448,
https://doi.org/10.1016/j.compositesb.2014.08.022 . .

TY  - JOUR
AU  - Ćirović, Velimir
AU  - Smiljanić, Dušan
AU  - Aleksendrić, Dragan
AU  - Simović, V.
PY  - 2014
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/2053
AB  - Osnovni problem u radu kočnica motornih vozila je pad njihovih performansi na povišenim temperaturama u kontaktu frikcionog para kočnice (kočnog diska i disk pločice). Povećanje temperature u kontaktu frikcionog para kočnice često dovodi do pada vrednosti momenta kočenja u toku ciklusa kočenja, a samim tim i do smanjenja izlaznih performansi kočnice. Da bi se obezbedila stabilnost momenta kočenja u toku ciklusa kočenja, razvijen je optimizacioni model na bazi dinamičkih veštačkih neuronskih mreža. Razvijeni model je iskorišćen za modeliranje složenih sinergijskih uticaja koji dovode do pojave triboloških fenomena koji utiču na izlazne performanse disk kočnice. Dinamički optimizacioni neuronski model performansi disk kočnice je razvijen na bazi rekurentnih neuronskih mreža. Model predviđa dinamičku promenu momenta kočenja u zavisnosti od trenutnih vrednosti pritiska aktiviranja kočnice, brzine i temperature u kontaktu frikcionog para u toku ciklusa kočenja. Genetski algoritmi su integrisani sa neuronskim dinamičkim modelom u cilju optimizacije pritiska aktiviranja kočnice koji u toku ciklusa kočenja treba da obezbedi željenu vrednost momenta kočenja. Ovakav hibridni, neuro-genetski, model je pokazao mogućnost uspešne optimizacije vrednosti hidrauličkog pritiska aktiviranja kočnice, potreban da bi se postigle stabilne i maksimizirane izlazne performanse kočnice u toku ciklusa kočenja.
AB  - The basic problem of automotive brakes operation is the decreasing of their performance at elevated temperatures in the contact of friction pair (brake disc and brake pad). Increasing of the brake interface temperature often causes decreasing of braking torque during a braking cycle. In order to provide the stable level of braking torque during a braking cycle, the neural network based optimization model of the disc brake performance has been developed. The dynamic neural networks have been employed for modelling of complex synergy of tribological phenomena that affects the final disc brake performance at elevated temperatures. The dynamic optimization neural network model of disc brake performance at elevated temperatures has been developed using recurrent neural networks. It predicts the braking torque versus the dynamic change of the brake actuation pressure, sliding speed and the brake interface temperature in a braking cycle. Genetic algorithms were integrated with the neural network model for optimization of the brake actuation pressure in order to obtain the desired level of braking torque. This hybrid, neuro-genetic model was successfully used in optimization of the brake hydraulic pressure level needed to achieve the maximum and stable brake performance during a braking cycle.
PB  - Univerzitet u Beogradu - Mašinski fakultet, Beograd
T2  - FME Transactions
T1  - Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama
T1  - Neuro-genetic optimization of disc brake performance at elevated temperatures
EP  - 149
IS  - 2
SP  - 142
VL  - 42
DO  - 10.5937/fmet1402142C
ER  - 

@article{
author = "Ćirović, Velimir and Smiljanić, Dušan and Aleksendrić, Dragan and Simović, V.",
year = "2014",
abstract = "Osnovni problem u radu kočnica motornih vozila je pad njihovih performansi na povišenim temperaturama u kontaktu frikcionog para kočnice (kočnog diska i disk pločice). Povećanje temperature u kontaktu frikcionog para kočnice često dovodi do pada vrednosti momenta kočenja u toku ciklusa kočenja, a samim tim i do smanjenja izlaznih performansi kočnice. Da bi se obezbedila stabilnost momenta kočenja u toku ciklusa kočenja, razvijen je optimizacioni model na bazi dinamičkih veštačkih neuronskih mreža. Razvijeni model je iskorišćen za modeliranje složenih sinergijskih uticaja koji dovode do pojave triboloških fenomena koji utiču na izlazne performanse disk kočnice. Dinamički optimizacioni neuronski model performansi disk kočnice je razvijen na bazi rekurentnih neuronskih mreža. Model predviđa dinamičku promenu momenta kočenja u zavisnosti od trenutnih vrednosti pritiska aktiviranja kočnice, brzine i temperature u kontaktu frikcionog para u toku ciklusa kočenja. Genetski algoritmi su integrisani sa neuronskim dinamičkim modelom u cilju optimizacije pritiska aktiviranja kočnice koji u toku ciklusa kočenja treba da obezbedi željenu vrednost momenta kočenja. Ovakav hibridni, neuro-genetski, model je pokazao mogućnost uspešne optimizacije vrednosti hidrauličkog pritiska aktiviranja kočnice, potreban da bi se postigle stabilne i maksimizirane izlazne performanse kočnice u toku ciklusa kočenja., The basic problem of automotive brakes operation is the decreasing of their performance at elevated temperatures in the contact of friction pair (brake disc and brake pad). Increasing of the brake interface temperature often causes decreasing of braking torque during a braking cycle. In order to provide the stable level of braking torque during a braking cycle, the neural network based optimization model of the disc brake performance has been developed. The dynamic neural networks have been employed for modelling of complex synergy of tribological phenomena that affects the final disc brake performance at elevated temperatures. The dynamic optimization neural network model of disc brake performance at elevated temperatures has been developed using recurrent neural networks. It predicts the braking torque versus the dynamic change of the brake actuation pressure, sliding speed and the brake interface temperature in a braking cycle. Genetic algorithms were integrated with the neural network model for optimization of the brake actuation pressure in order to obtain the desired level of braking torque. This hybrid, neuro-genetic model was successfully used in optimization of the brake hydraulic pressure level needed to achieve the maximum and stable brake performance during a braking cycle.",
publisher = "Univerzitet u Beogradu - Mašinski fakultet, Beograd",
journal = "FME Transactions",
title = "Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama, Neuro-genetic optimization of disc brake performance at elevated temperatures",
pages = "149-142",
number = "2",
volume = "42",
doi = "10.5937/fmet1402142C"
}

Ćirović, V., Smiljanić, D., Aleksendrić, D.,& Simović, V.. (2014). Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama. in FME Transactions
Univerzitet u Beogradu - Mašinski fakultet, Beograd., 42(2), 142-149.
https://doi.org/10.5937/fmet1402142C

Ćirović V, Smiljanić D, Aleksendrić D, Simović V. Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama. in FME Transactions. 2014;42(2):142-149.
doi:10.5937/fmet1402142C .

Ćirović, Velimir, Smiljanić, Dušan, Aleksendrić, Dragan, Simović, V., "Neuro-genetska optimizacija performansi disk kočnice na povišenim temperaturama" in FME Transactions, 42, no. 2 (2014):142-149,
https://doi.org/10.5937/fmet1402142C . .

TY  - CONF
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
AU  - Jakovljević, Živana
PY  - 2013
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1751
AB  - Monitoring, modeling, prediction, and control of the braking process is a difficult task due to a complex interaction between the brake contact surfaces (disc pads and brake disc). It is caused by different influences of braking regimes and brake operation conditions on its performance. Faster and better control of the braking process is extremely important in order to provide harmonization of the generated braking torque with the tire-road adhesion conditions. It has significant influence on the stopping distance. The control of the braking process should be based on monitoring of the previous and current values of parameters that have influence on the brake performance. Primarily, it is related to the disc brake actuation pressure, the vehicle speed, and the brake interface temperature. The functional relationship between braking regimes and braking torque has to be established and continuously adapted according to the change of mentioned influencing factors. In this paper dynamic neural networks have been used for the purpose of modeling and control of the disc brake actuation pressure. Parameters of the developed dynamic neural model were used to build a program for implementation in a microcontroller. Recurrent neural networks have been implemented in 8-bit CMOS microcontroller for control of the disc brake actuation pressure. Two different models have been developed and integrated into the microcontroller. The first model was used for modeling and prediction of the braking torque. Based on that, the second inverse neural model, has been developed able to predict the brake actuation pressure needed for achieving previously selected (desired) braking torque value.
PB  - SAE International
C3  - SAE Technical Papers
T1  - Microcontroller based control of disc brake actuation pressure
VL  - 8
DO  - 10.4271/2013-01-2055
ER  - 

@conference{
author = "Aleksendrić, Dragan and Ćirović, Velimir and Jakovljević, Živana",
year = "2013",
abstract = "Monitoring, modeling, prediction, and control of the braking process is a difficult task due to a complex interaction between the brake contact surfaces (disc pads and brake disc). It is caused by different influences of braking regimes and brake operation conditions on its performance. Faster and better control of the braking process is extremely important in order to provide harmonization of the generated braking torque with the tire-road adhesion conditions. It has significant influence on the stopping distance. The control of the braking process should be based on monitoring of the previous and current values of parameters that have influence on the brake performance. Primarily, it is related to the disc brake actuation pressure, the vehicle speed, and the brake interface temperature. The functional relationship between braking regimes and braking torque has to be established and continuously adapted according to the change of mentioned influencing factors. In this paper dynamic neural networks have been used for the purpose of modeling and control of the disc brake actuation pressure. Parameters of the developed dynamic neural model were used to build a program for implementation in a microcontroller. Recurrent neural networks have been implemented in 8-bit CMOS microcontroller for control of the disc brake actuation pressure. Two different models have been developed and integrated into the microcontroller. The first model was used for modeling and prediction of the braking torque. Based on that, the second inverse neural model, has been developed able to predict the brake actuation pressure needed for achieving previously selected (desired) braking torque value.",
publisher = "SAE International",
journal = "SAE Technical Papers",
title = "Microcontroller based control of disc brake actuation pressure",
volume = "8",
doi = "10.4271/2013-01-2055"
}

Aleksendrić, D., Ćirović, V.,& Jakovljević, Ž.. (2013). Microcontroller based control of disc brake actuation pressure. in SAE Technical Papers
SAE International., 8.
https://doi.org/10.4271/2013-01-2055

Aleksendrić D, Ćirović V, Jakovljević Ž. Microcontroller based control of disc brake actuation pressure. in SAE Technical Papers. 2013;8.
doi:10.4271/2013-01-2055 .

Aleksendrić, Dragan, Ćirović, Velimir, Jakovljević, Živana, "Microcontroller based control of disc brake actuation pressure" in SAE Technical Papers, 8 (2013),
https://doi.org/10.4271/2013-01-2055 . .

TY  - GEN
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
PY  - 2013
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5768
PB  - Универзитета у Београду Машински факултет
T1  - Метода адаптивног неуро-фази управљања клизањем коченог точка
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5768
ER  - 

@misc{
author = "Aleksendrić, Dragan and Ćirović, Velimir",
year = "2013",
publisher = "Универзитета у Београду Машински факултет",
title = "Метода адаптивног неуро-фази управљања клизањем коченог точка",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5768"
}

Aleksendrić, D.,& Ćirović, V.. (2013). Метода адаптивног неуро-фази управљања клизањем коченог точка. 
Универзитета у Београду Машински факултет..
https://hdl.handle.net/21.15107/rcub_machinery_5768

Aleksendrić D, Ćirović V. Метода адаптивног неуро-фази управљања клизањем коченог точка. 2013;.
https://hdl.handle.net/21.15107/rcub_machinery_5768 .

Aleksendrić, Dragan, Ćirović, Velimir, "Метода адаптивног неуро-фази управљања клизањем коченог точка" (2013),
https://hdl.handle.net/21.15107/rcub_machinery_5768 .

TY  - JOUR
AU  - Ćirović, Velimir
AU  - Aleksendrić, Dragan
PY  - 2013
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1697
AB  - Due to complex and nonlinear dynamics of a braking process and complexity in the tire-road interaction, the control of automotive braking systems performance simultaneously with the wheel slip represents a challenging problem. The non-optimal wheel slip level during braking, causing inability to achieve the desired tire-road friction force strongly influences the braking distance. In addition, steerability and maneuverability of the vehicle could be disturbed. In this paper, an active neuro-fuzzy approach has been developed for improving the wheel slip control in the longitudinal direction of the commercial vehicle. The dynamic neural network has been used for prediction and an adaptive control of the brake actuation pressure, during each braking cycle, according to the identified maximum adhesion coefficient between the wheel and road surface. The brake actuation pressure was dynamically adjusted on the level that provides the optimal level of the longitudinal wheel slip vs. the brake pressure selected by driver, the current vehicle speed, the brake interface temperature, vehicle load conditions, and the current value of longitudinal wheel slip. Thus the dynamic neural network model operates (learn, generalize and predict) on-line during each braking cycle, fuzzy logic has been integrated with the neural model as a support to the neural controller control actions in the case when prediction error of the dynamic neural model reached the predefined value. The hybrid control approach presented here provided intelligent dynamic model - based control of the brake actuation pressure in order to keep the longitudinal wheel slip on the optimum level during a braking cycle.
PB  - Pergamon-Elsevier Science Ltd, Oxford
T2  - Expert Systems With Applications
T1  - Adaptive neuro-fuzzy wheel slip control
EP  - 5209
IS  - 13
SP  - 5197
VL  - 40
DO  - 10.1016/j.eswa.2013.03.012
ER  - 

@article{
author = "Ćirović, Velimir and Aleksendrić, Dragan",
year = "2013",
abstract = "Due to complex and nonlinear dynamics of a braking process and complexity in the tire-road interaction, the control of automotive braking systems performance simultaneously with the wheel slip represents a challenging problem. The non-optimal wheel slip level during braking, causing inability to achieve the desired tire-road friction force strongly influences the braking distance. In addition, steerability and maneuverability of the vehicle could be disturbed. In this paper, an active neuro-fuzzy approach has been developed for improving the wheel slip control in the longitudinal direction of the commercial vehicle. The dynamic neural network has been used for prediction and an adaptive control of the brake actuation pressure, during each braking cycle, according to the identified maximum adhesion coefficient between the wheel and road surface. The brake actuation pressure was dynamically adjusted on the level that provides the optimal level of the longitudinal wheel slip vs. the brake pressure selected by driver, the current vehicle speed, the brake interface temperature, vehicle load conditions, and the current value of longitudinal wheel slip. Thus the dynamic neural network model operates (learn, generalize and predict) on-line during each braking cycle, fuzzy logic has been integrated with the neural model as a support to the neural controller control actions in the case when prediction error of the dynamic neural model reached the predefined value. The hybrid control approach presented here provided intelligent dynamic model - based control of the brake actuation pressure in order to keep the longitudinal wheel slip on the optimum level during a braking cycle.",
publisher = "Pergamon-Elsevier Science Ltd, Oxford",
journal = "Expert Systems With Applications",
title = "Adaptive neuro-fuzzy wheel slip control",
pages = "5209-5197",
number = "13",
volume = "40",
doi = "10.1016/j.eswa.2013.03.012"
}

Ćirović, V.,& Aleksendrić, D.. (2013). Adaptive neuro-fuzzy wheel slip control. in Expert Systems With Applications
Pergamon-Elsevier Science Ltd, Oxford., 40(13), 5197-5209.
https://doi.org/10.1016/j.eswa.2013.03.012

Ćirović V, Aleksendrić D. Adaptive neuro-fuzzy wheel slip control. in Expert Systems With Applications. 2013;40(13):5197-5209.
doi:10.1016/j.eswa.2013.03.012 .

Ćirović, Velimir, Aleksendrić, Dragan, "Adaptive neuro-fuzzy wheel slip control" in Expert Systems With Applications, 40, no. 13 (2013):5197-5209,
https://doi.org/10.1016/j.eswa.2013.03.012 . .

TY  - JOUR
AU  - Ćirović, Velimir
AU  - Aleksendrić, Dragan
AU  - Smiljanić, Dušan
PY  - 2013
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1655
AB  - The control of automotive braking systems performance and a wheel slip is a challenging problem due to nonlinear dynamics of a braking process and a tire-road interaction. When the wheel slip is not between the optimal limits during braking, the desired tire-road friction force cannot be achieved, which influences braking distance, the loss in steerability and maneuverability of the vehicle. In this paper, the new approach, based on dynamic neural networks, has been employed for improving of the longitudinal wheel slip control. This approach is based on dynamic adaptation of the brake actuation pressure, during a braking cycle, according to the identified maximum adhesion coefficient between the wheel and road. The brake actuated pressure was adjusted on the level which provides the optimal longitudinal wheel slip versus the brake actuated pressure selected by a driver, the current vehicle speed, load conditions, the brake interface temperature and the current value of the wheel slip. The dynamic neural network has been used for modeling of a nonlinear functional relationship between the brake actuation pressure and the longitudinal wheel slip during a braking cycle. It provided preconditions for control of the brake actuation pressure based on the wheel slip change.
PB  - Pergamon-Elsevier Science Ltd, Oxford
T2  - Mechatronics
T1  - Longitudinal wheel slip control using dynamic neural networks
EP  - 146
IS  - 1
SP  - 135
VL  - 23
DO  - 10.1016/j.mechatronics.2012.11.007
ER  - 

@article{
author = "Ćirović, Velimir and Aleksendrić, Dragan and Smiljanić, Dušan",
year = "2013",
abstract = "The control of automotive braking systems performance and a wheel slip is a challenging problem due to nonlinear dynamics of a braking process and a tire-road interaction. When the wheel slip is not between the optimal limits during braking, the desired tire-road friction force cannot be achieved, which influences braking distance, the loss in steerability and maneuverability of the vehicle. In this paper, the new approach, based on dynamic neural networks, has been employed for improving of the longitudinal wheel slip control. This approach is based on dynamic adaptation of the brake actuation pressure, during a braking cycle, according to the identified maximum adhesion coefficient between the wheel and road. The brake actuated pressure was adjusted on the level which provides the optimal longitudinal wheel slip versus the brake actuated pressure selected by a driver, the current vehicle speed, load conditions, the brake interface temperature and the current value of the wheel slip. The dynamic neural network has been used for modeling of a nonlinear functional relationship between the brake actuation pressure and the longitudinal wheel slip during a braking cycle. It provided preconditions for control of the brake actuation pressure based on the wheel slip change.",
publisher = "Pergamon-Elsevier Science Ltd, Oxford",
journal = "Mechatronics",
title = "Longitudinal wheel slip control using dynamic neural networks",
pages = "146-135",
number = "1",
volume = "23",
doi = "10.1016/j.mechatronics.2012.11.007"
}

Ćirović, V., Aleksendrić, D.,& Smiljanić, D.. (2013). Longitudinal wheel slip control using dynamic neural networks. in Mechatronics
Pergamon-Elsevier Science Ltd, Oxford., 23(1), 135-146.
https://doi.org/10.1016/j.mechatronics.2012.11.007

Ćirović V, Aleksendrić D, Smiljanić D. Longitudinal wheel slip control using dynamic neural networks. in Mechatronics. 2013;23(1):135-146.
doi:10.1016/j.mechatronics.2012.11.007 .

Ćirović, Velimir, Aleksendrić, Dragan, Smiljanić, Dušan, "Longitudinal wheel slip control using dynamic neural networks" in Mechatronics, 23, no. 1 (2013):135-146,
https://doi.org/10.1016/j.mechatronics.2012.11.007 . .

TY  - JOUR
AU  - Ćirović, Velimir
AU  - Aleksendrić, Dragan
AU  - Mladenović, Dušan
PY  - 2012
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1351
AB  - The basic problem in the operation of automotive brakes is the unpredictable nature of the tribological processes that occur at the contact of the friction pair. The stochastic nature of the tribological contact of the disc brake is affected differently by the complex interaction between the brake disc and the friction material under different conditions because of the influences of the applied pressure, the speed and the brake interface temperature. Owing to the highly dynamic non-linear change in the braking torque induced by the complex situation at the contact of the disc brake, the braking torque could not be modelled, predicted and controlled using classical mathematical methods. This is related, in particular, to the dynamic change in the braking torque in a braking cycle. Dynamic modelling and prediction of the braking torque is very important for further improvement in the performance of the brakes of motor vehicles through more precise control of their performance with respect to the driver demands and the change in the adhesion between the tyre and the road. Recurrent dynamic neural networks were employed in this paper for modelling, prediction and control of the dynamic change in the braking torque during a braking cycle. The dynamic functional relationship between the changes in the applied pressure, the sliding speed, the brake interface temperature and the braking torque of the disc brake was established. The dynamic model developed was used to predict and control the braking torque during a braking cycle under different disc brake operation conditions.
PB  - Sage Publications Ltd, London
T2  - Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering
T1  - Braking torque control using recurrent neural networks
EP  - 766
IS  - D6
SP  - 754
VL  - 226
DO  - 10.1177/0954407011428720
ER  - 

@article{
author = "Ćirović, Velimir and Aleksendrić, Dragan and Mladenović, Dušan",
year = "2012",
abstract = "The basic problem in the operation of automotive brakes is the unpredictable nature of the tribological processes that occur at the contact of the friction pair. The stochastic nature of the tribological contact of the disc brake is affected differently by the complex interaction between the brake disc and the friction material under different conditions because of the influences of the applied pressure, the speed and the brake interface temperature. Owing to the highly dynamic non-linear change in the braking torque induced by the complex situation at the contact of the disc brake, the braking torque could not be modelled, predicted and controlled using classical mathematical methods. This is related, in particular, to the dynamic change in the braking torque in a braking cycle. Dynamic modelling and prediction of the braking torque is very important for further improvement in the performance of the brakes of motor vehicles through more precise control of their performance with respect to the driver demands and the change in the adhesion between the tyre and the road. Recurrent dynamic neural networks were employed in this paper for modelling, prediction and control of the dynamic change in the braking torque during a braking cycle. The dynamic functional relationship between the changes in the applied pressure, the sliding speed, the brake interface temperature and the braking torque of the disc brake was established. The dynamic model developed was used to predict and control the braking torque during a braking cycle under different disc brake operation conditions.",
publisher = "Sage Publications Ltd, London",
journal = "Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering",
title = "Braking torque control using recurrent neural networks",
pages = "766-754",
number = "D6",
volume = "226",
doi = "10.1177/0954407011428720"
}

Ćirović, V., Aleksendrić, D.,& Mladenović, D.. (2012). Braking torque control using recurrent neural networks. in Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering
Sage Publications Ltd, London., 226(D6), 754-766.
https://doi.org/10.1177/0954407011428720

Ćirović V, Aleksendrić D, Mladenović D. Braking torque control using recurrent neural networks. in Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering. 2012;226(D6):754-766.
doi:10.1177/0954407011428720 .

Ćirović, Velimir, Aleksendrić, Dragan, Mladenović, Dušan, "Braking torque control using recurrent neural networks" in Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering, 226, no. D6 (2012):754-766,
https://doi.org/10.1177/0954407011428720 . .

TY  - GEN
AU  - Ćirović, Velimir
AU  - Aleksendrić, Dragan
PY  - 2012
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5777
PB  - Универзитета у Београду Машински факултет
T1  - Метода предвиђања притиска активирања диск кочнице привредног возила у зависности од услова приањања у контакту пнеуматика и тла током кочења
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5777
ER  - 

@misc{
author = "Ćirović, Velimir and Aleksendrić, Dragan",
year = "2012",
publisher = "Универзитета у Београду Машински факултет",
title = "Метода предвиђања притиска активирања диск кочнице привредног возила у зависности од услова приањања у контакту пнеуматика и тла током кочења",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5777"
}

Ćirović, V.,& Aleksendrić, D.. (2012). Метода предвиђања притиска активирања диск кочнице привредног возила у зависности од услова приањања у контакту пнеуматика и тла током кочења. 
Универзитета у Београду Машински факултет..
https://hdl.handle.net/21.15107/rcub_machinery_5777

Ćirović V, Aleksendrić D. Метода предвиђања притиска активирања диск кочнице привредног возила у зависности од услова приањања у контакту пнеуматика и тла током кочења. 2012;.
https://hdl.handle.net/21.15107/rcub_machinery_5777 .

Ćirović, Velimir, Aleksendrić, Dragan, "Метода предвиђања притиска активирања диск кочнице привредног возила у зависности од услова приањања у контакту пнеуматика и тла током кочења" (2012),
https://hdl.handle.net/21.15107/rcub_machinery_5777 .

TY  - GEN
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
PY  - 2012
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5775
PB  - Универзитета у Београду Машински факултет
T1  - Метода управљања подужним клизањем коченог точка коришћењем динамичких вештачких неуронских мрежа
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5775
ER  - 

@misc{
author = "Aleksendrić, Dragan and Ćirović, Velimir",
year = "2012",
publisher = "Универзитета у Београду Машински факултет",
title = "Метода управљања подужним клизањем коченог точка коришћењем динамичких вештачких неуронских мрежа",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5775"
}

Aleksendrić, D.,& Ćirović, V.. (2012). Метода управљања подужним клизањем коченог точка коришћењем динамичких вештачких неуронских мрежа. 
Универзитета у Београду Машински факултет..
https://hdl.handle.net/21.15107/rcub_machinery_5775

Aleksendrić D, Ćirović V. Метода управљања подужним клизањем коченог точка коришћењем динамичких вештачких неуронских мрежа. 2012;.
https://hdl.handle.net/21.15107/rcub_machinery_5775 .

Aleksendrić, Dragan, Ćirović, Velimir, "Метода управљања подужним клизањем коченог точка коришћењем динамичких вештачких неуронских мрежа" (2012),
https://hdl.handle.net/21.15107/rcub_machinery_5775 .

TY  - GEN
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
PY  - 2012
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5772
PB  - Универзитета у Београду Машински факултет
T1  - Метода динамичког управљања перформансама кочница моторних возила
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5772
ER  - 

@misc{
author = "Aleksendrić, Dragan and Ćirović, Velimir",
year = "2012",
publisher = "Универзитета у Београду Машински факултет",
title = "Метода динамичког управљања перформансама кочница моторних возила",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5772"
}

Aleksendrić, D.,& Ćirović, V.. (2012). Метода динамичког управљања перформансама кочница моторних возила. 
Универзитета у Београду Машински факултет..
https://hdl.handle.net/21.15107/rcub_machinery_5772

Aleksendrić D, Ćirović V. Метода динамичког управљања перформансама кочница моторних возила. 2012;.
https://hdl.handle.net/21.15107/rcub_machinery_5772 .

Aleksendrić, Dragan, Ćirović, Velimir, "Метода динамичког управљања перформансама кочница моторних возила" (2012),
https://hdl.handle.net/21.15107/rcub_machinery_5772 .

TY  - CONF
AU  - Ćirović, Velimir
AU  - Aleksendrić, Dragan
AU  - Jakovljević, Živana
PY  - 2012
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5186
AB  - Computer simulations take an important place in the engineering development of innovative control strategies of vehicle braking systems. The simulations are often used to study and analyze the design and operation of various conceptual solutions of braking systems for determination of a near optimal configurations and performance. In addition, complex and continuously increasing technological demands related to vehicles’ safety and stability issues indicate that design and operation of their braking systems should be constantly improved by developing new and intelligent solutions. Adequate simulation platforms for developing of braking systems with intelligent abilities could be very helpful in analysis of such designed conceptual solutions and verification of the selected control strategies. That is why, a simulation model of intelligent braking system has been proposed in this paper using Matlab/Simulink. It is done in order to simulate the different braking situations and predict the braking system performance versus driver’s demands, vehicle load conditions and actual braking regimes.
C3  - Innovative Automotive Technology – IAT 2012, Proceedings
T1  - Simulation Platform for Intelligent Braking System Development
EP  - 42
SP  - 35
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5186
ER  - 

@conference{
author = "Ćirović, Velimir and Aleksendrić, Dragan and Jakovljević, Živana",
year = "2012",
abstract = "Computer simulations take an important place in the engineering development of innovative control strategies of vehicle braking systems. The simulations are often used to study and analyze the design and operation of various conceptual solutions of braking systems for determination of a near optimal configurations and performance. In addition, complex and continuously increasing technological demands related to vehicles’ safety and stability issues indicate that design and operation of their braking systems should be constantly improved by developing new and intelligent solutions. Adequate simulation platforms for developing of braking systems with intelligent abilities could be very helpful in analysis of such designed conceptual solutions and verification of the selected control strategies. That is why, a simulation model of intelligent braking system has been proposed in this paper using Matlab/Simulink. It is done in order to simulate the different braking situations and predict the braking system performance versus driver’s demands, vehicle load conditions and actual braking regimes.",
journal = "Innovative Automotive Technology – IAT 2012, Proceedings",
title = "Simulation Platform for Intelligent Braking System Development",
pages = "42-35",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5186"
}

Ćirović, V., Aleksendrić, D.,& Jakovljević, Ž.. (2012). Simulation Platform for Intelligent Braking System Development. in Innovative Automotive Technology – IAT 2012, Proceedings, 35-42.
https://hdl.handle.net/21.15107/rcub_machinery_5186

Ćirović V, Aleksendrić D, Jakovljević Ž. Simulation Platform for Intelligent Braking System Development. in Innovative Automotive Technology – IAT 2012, Proceedings. 2012;:35-42.
https://hdl.handle.net/21.15107/rcub_machinery_5186 .

Ćirović, Velimir, Aleksendrić, Dragan, Jakovljević, Živana, "Simulation Platform for Intelligent Braking System Development" in Innovative Automotive Technology – IAT 2012, Proceedings (2012):35-42,
https://hdl.handle.net/21.15107/rcub_machinery_5186 .

TY  - JOUR
AU  - Aleksendrić, Dragan
AU  - Ćirović, Velimir
AU  - Sovrović, V.
PY  - 2012
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1538
AB  - Since the driver obtains an important feedback of vehicle dynamics and its braking capabilities depending on a brake performance change, it represents an important aspect of vehicle performance and its quality of use. Regarding modern automotive brakes, the extreme demands have been imposed on the friction couple and its tribological performance. Different sensitivity of braking torque, i.e. a disc brake performance versus the influence of the friction couple interaction, under different braking conditions (applied pressure, speed and brake interface temperature), is one of the most important the disc brake properties. That is why, control of braking performance in the sense of providing stable braking performance during a braking cycle and their dynamic adaptation to the driver demands and/or demands imposed by ABS/ESC, are very important. Investigation presented in this paper contributes to the efforts in the direction of intelligent dynamic control of automotive braking systems performance. The dynamic model has been developed in the paper in order to provide dynamic prediction and control of the disc brake performance during a braking cycle. This model provided stabilization of the brake performance and their maximization versus the brake pedal travel, selected by a driver, and influence of the current values of initial speed, the brake activation pressure, and the brake interface temperature.
PB  - SAE International
T2  - SAE International Journal of Passenger Cars - Mechanical Systems
T1  - Dynamic Control of Disc Brake Performance
EP  - 1272
IS  - 4
SP  - 1266
VL  - 5
DO  - 10.4271/2012-01-1837
ER  - 

@article{
author = "Aleksendrić, Dragan and Ćirović, Velimir and Sovrović, V.",
year = "2012",
abstract = "Since the driver obtains an important feedback of vehicle dynamics and its braking capabilities depending on a brake performance change, it represents an important aspect of vehicle performance and its quality of use. Regarding modern automotive brakes, the extreme demands have been imposed on the friction couple and its tribological performance. Different sensitivity of braking torque, i.e. a disc brake performance versus the influence of the friction couple interaction, under different braking conditions (applied pressure, speed and brake interface temperature), is one of the most important the disc brake properties. That is why, control of braking performance in the sense of providing stable braking performance during a braking cycle and their dynamic adaptation to the driver demands and/or demands imposed by ABS/ESC, are very important. Investigation presented in this paper contributes to the efforts in the direction of intelligent dynamic control of automotive braking systems performance. The dynamic model has been developed in the paper in order to provide dynamic prediction and control of the disc brake performance during a braking cycle. This model provided stabilization of the brake performance and their maximization versus the brake pedal travel, selected by a driver, and influence of the current values of initial speed, the brake activation pressure, and the brake interface temperature.",
publisher = "SAE International",
journal = "SAE International Journal of Passenger Cars - Mechanical Systems",
title = "Dynamic Control of Disc Brake Performance",
pages = "1272-1266",
number = "4",
volume = "5",
doi = "10.4271/2012-01-1837"
}

Aleksendrić, D., Ćirović, V.,& Sovrović, V.. (2012). Dynamic Control of Disc Brake Performance. in SAE International Journal of Passenger Cars - Mechanical Systems
SAE International., 5(4), 1266-1272.
https://doi.org/10.4271/2012-01-1837

Aleksendrić D, Ćirović V, Sovrović V. Dynamic Control of Disc Brake Performance. in SAE International Journal of Passenger Cars - Mechanical Systems. 2012;5(4):1266-1272.
doi:10.4271/2012-01-1837 .

Aleksendrić, Dragan, Ćirović, Velimir, Sovrović, V., "Dynamic Control of Disc Brake Performance" in SAE International Journal of Passenger Cars - Mechanical Systems, 5, no. 4 (2012):1266-1272,
https://doi.org/10.4271/2012-01-1837 . .

TY  - JOUR
AU  - Aleksendrić, Dragan
AU  - Jakovljević, Živana
AU  - Ćirović, Velimir
PY  - 2012
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1495
AB  - Intelligent modeling, prediction and control of the braking process are not an easy task if using classical modeling techniques, regarding its complexity. In this paper, the new approach has been proposed for easy and effective monitoring, modeling, prediction, and control of the braking process i.e. the brake performance during a braking cycle. The context based control of the disc brake actuation pressure was used for improving the dynamic control of braking process versus influence of the previous and current values of the disc brake actuation pressure, the vehicle speed, and the brake interface temperature. For these purposes, two different dynamic neural models have been developed and integrated into the microcontroller. Microcontrollers are resource intensive and cost effective platforms that offer possibilities to associate with commonly used artificial intelligence techniques. The neural models, based on recurrent dynamic neural networks, are implemented in 8-bit CMOS microcontroller for control of the disc brake actuation pressure during a braking cycle. The first neural model was used for modeling and prediction of the braking process output (braking torque). Based on such acquired knowledge about the real brake operation, the inverse neural model has been developed which was able to predict the brake actuation pressure needed for achieving previously selected (desired) braking torque value in accordance with the previous and current influence of the pressure, speed, and the brake interface temperature. Both neural models have had inherent abilities for on-line learning and prediction during each braking cycle and an intelligent adaptation to the change of influences of pressure, speed, and temperature on the braking process.
PB  - Pergamon-Elsevier Science Ltd, Oxford
T2  - Expert Systems With Applications
T1  - Intelligent control of braking process
EP  - 11765
IS  - 14
SP  - 11758
VL  - 39
DO  - 10.1016/j.eswa.2012.04.076
ER  - 

@article{
author = "Aleksendrić, Dragan and Jakovljević, Živana and Ćirović, Velimir",
year = "2012",
abstract = "Intelligent modeling, prediction and control of the braking process are not an easy task if using classical modeling techniques, regarding its complexity. In this paper, the new approach has been proposed for easy and effective monitoring, modeling, prediction, and control of the braking process i.e. the brake performance during a braking cycle. The context based control of the disc brake actuation pressure was used for improving the dynamic control of braking process versus influence of the previous and current values of the disc brake actuation pressure, the vehicle speed, and the brake interface temperature. For these purposes, two different dynamic neural models have been developed and integrated into the microcontroller. Microcontrollers are resource intensive and cost effective platforms that offer possibilities to associate with commonly used artificial intelligence techniques. The neural models, based on recurrent dynamic neural networks, are implemented in 8-bit CMOS microcontroller for control of the disc brake actuation pressure during a braking cycle. The first neural model was used for modeling and prediction of the braking process output (braking torque). Based on such acquired knowledge about the real brake operation, the inverse neural model has been developed which was able to predict the brake actuation pressure needed for achieving previously selected (desired) braking torque value in accordance with the previous and current influence of the pressure, speed, and the brake interface temperature. Both neural models have had inherent abilities for on-line learning and prediction during each braking cycle and an intelligent adaptation to the change of influences of pressure, speed, and temperature on the braking process.",
publisher = "Pergamon-Elsevier Science Ltd, Oxford",
journal = "Expert Systems With Applications",
title = "Intelligent control of braking process",
pages = "11765-11758",
number = "14",
volume = "39",
doi = "10.1016/j.eswa.2012.04.076"
}

Aleksendrić, D., Jakovljević, Ž.,& Ćirović, V.. (2012). Intelligent control of braking process. in Expert Systems With Applications
Pergamon-Elsevier Science Ltd, Oxford., 39(14), 11758-11765.
https://doi.org/10.1016/j.eswa.2012.04.076

Aleksendrić D, Jakovljević Ž, Ćirović V. Intelligent control of braking process. in Expert Systems With Applications. 2012;39(14):11758-11765.
doi:10.1016/j.eswa.2012.04.076 .

Aleksendrić, Dragan, Jakovljević, Živana, Ćirović, Velimir, "Intelligent control of braking process" in Expert Systems With Applications, 39, no. 14 (2012):11758-11765,
https://doi.org/10.1016/j.eswa.2012.04.076 . .

TY  - JOUR
AU  - Ćirović, Velimir
AU  - Aleksendrić, Dragan
PY  - 2011
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1297
AB  - Interakcija između diska kočnice i frikcionog materijala disk kočnice motornih vozila se odlikuje velikim brojem kontaktnih fenomena. Nastanak ovih fenomena je vezan za radne uslove kočnice (pritisak aktiviranja, brzina, temperatura u kontaktu) kao i za karakteristike materijala frikcionog para. Dinamičke i izraženo nelinearne promene, koje se dešavaju u kontaktu frikcionog para, izazivaju teško predvidivu promenu momenta kočenja, kao najvažnije izlazne performanse kočnice. Složena situacija u kontaktu frikcionog para se ne može lako modelirati i predvideti korišćenjem klasičnih matematičkih metoda. Zbog toga su istraživane mogućnosti razvoja metode za predviđanje uticaja radnih režima disk kočnice na pojavu tzv. 'stickslip' fenomena tokom ciklusa kočenja. Korišćenjem dinamičkih neuronskih mreža, razvijen je dinamički model uticaja radnih uslova disk kočnice na pojavu kontaktnih fenomena i način promene momenta kočenja.
AB  - An interaction between a brake disc and friction material of automotive brake is characterized by a number of braking phenomena. These phenomena are influenced by brake operation conditions (applied pressure, speed, and brake interface temperature) and material characteristics of a friction couple. The dynamic and highly non-linear changes occurred in the contact of the friction pair, provokes hard-to-predict change of braking torque as the most important brake's output performance. Complex disc brake contact situation is causing sudden change of braking torque and could not be easily modeled and predicted using classical mathematical methods. That is why, the possibilities for development of the method for prediction of influence of braking regimes on generation of the stick-slip phenomena during a braking cycle has been investigated in this paper. Dynamic neural networks have been employed for development of the model of influences of the disc brake operation conditions on contact phenomena generation and 'nature' of braking torque change.
PB  - Univerzitet u Beogradu - Mašinski fakultet, Beograd
T2  - FME Transactions
T1  - Dinamičko modeliranje kontaktnih fenomena disk kočnice
T1  - Dynamic modeling of disc brake contact phenomena
EP  - 183
IS  - 4
SP  - 177
VL  - 39
UR  - https://hdl.handle.net/21.15107/rcub_machinery_1297
ER  - 

@article{
author = "Ćirović, Velimir and Aleksendrić, Dragan",
year = "2011",
abstract = "Interakcija između diska kočnice i frikcionog materijala disk kočnice motornih vozila se odlikuje velikim brojem kontaktnih fenomena. Nastanak ovih fenomena je vezan za radne uslove kočnice (pritisak aktiviranja, brzina, temperatura u kontaktu) kao i za karakteristike materijala frikcionog para. Dinamičke i izraženo nelinearne promene, koje se dešavaju u kontaktu frikcionog para, izazivaju teško predvidivu promenu momenta kočenja, kao najvažnije izlazne performanse kočnice. Složena situacija u kontaktu frikcionog para se ne može lako modelirati i predvideti korišćenjem klasičnih matematičkih metoda. Zbog toga su istraživane mogućnosti razvoja metode za predviđanje uticaja radnih režima disk kočnice na pojavu tzv. 'stickslip' fenomena tokom ciklusa kočenja. Korišćenjem dinamičkih neuronskih mreža, razvijen je dinamički model uticaja radnih uslova disk kočnice na pojavu kontaktnih fenomena i način promene momenta kočenja., An interaction between a brake disc and friction material of automotive brake is characterized by a number of braking phenomena. These phenomena are influenced by brake operation conditions (applied pressure, speed, and brake interface temperature) and material characteristics of a friction couple. The dynamic and highly non-linear changes occurred in the contact of the friction pair, provokes hard-to-predict change of braking torque as the most important brake's output performance. Complex disc brake contact situation is causing sudden change of braking torque and could not be easily modeled and predicted using classical mathematical methods. That is why, the possibilities for development of the method for prediction of influence of braking regimes on generation of the stick-slip phenomena during a braking cycle has been investigated in this paper. Dynamic neural networks have been employed for development of the model of influences of the disc brake operation conditions on contact phenomena generation and 'nature' of braking torque change.",
publisher = "Univerzitet u Beogradu - Mašinski fakultet, Beograd",
journal = "FME Transactions",
title = "Dinamičko modeliranje kontaktnih fenomena disk kočnice, Dynamic modeling of disc brake contact phenomena",
pages = "183-177",
number = "4",
volume = "39",
url = "https://hdl.handle.net/21.15107/rcub_machinery_1297"
}

Ćirović, V.,& Aleksendrić, D.. (2011). Dinamičko modeliranje kontaktnih fenomena disk kočnice. in FME Transactions
Univerzitet u Beogradu - Mašinski fakultet, Beograd., 39(4), 177-183.
https://hdl.handle.net/21.15107/rcub_machinery_1297

Ćirović V, Aleksendrić D. Dinamičko modeliranje kontaktnih fenomena disk kočnice. in FME Transactions. 2011;39(4):177-183.
https://hdl.handle.net/21.15107/rcub_machinery_1297 .

Ćirović, Velimir, Aleksendrić, Dragan, "Dinamičko modeliranje kontaktnih fenomena disk kočnice" in FME Transactions, 39, no. 4 (2011):177-183,
https://hdl.handle.net/21.15107/rcub_machinery_1297 .

TY  - JOUR
AU  - Ćirović, Velimir
AU  - Aleksendrić, Dragan
PY  - 2010
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/1025
AB  - Kvalitet veštačkih neuronskih modela pretežno zavisi od pravilnog izbora arhitekture veštačke neuronske mreže, odnosno algoritma učenja, funkcije prenosa, opsega i raspodele podataka korišćenih za obuku, validaciju i testiranje. Osnovni cilj ovog rada se odnosi na istraživanje kako arhitekture veštačkih neuronskih mreža utiču na uspešnost predviđanja tj. sposobnost generalizacije mreža za isti set podataka za obuku i testiranje. Kompleksni postupak razvoja veštačkog neuronskog modela je demonstriran na primeru disk kočnice. Modeliran je uticaj radnih uslova disk kočnice (pritisak aktiviranja, početna brzina i temperatura) na njene maksimalne performanse kao i performanse opadanja i obnavljanja efikasnosti. Veštački neuronski model je razvijan kroz istraživanje na koji način sinergija različitih parametara mreže, poput algoritma učenja, funkcije prenosa i broja neurona u skrivenim slojevima, utiče na sposobnosti neuronskog modela da predvidi performanse disk kočnice. U ovom radu je pokazano da kompleksne nelinearne zavisnosti između posmatranih ulaznih i izlaznih parametara mogu biti modelirane odgovarajućom analizom i podešavanjem parametara veštačke neuronske mreže.
AB  - The quality of artificial neural network models mostly depends on a proper setting of neural network architecture i.e. learning algorithm, transfer functions, range and distribution of data used for training, validation, and testing, etc. The goal of this paper is related to the investigation on how artificial neural network architectures influence the network's generalization performance based on the same input/output parameters. The complex procedure of an artificial neural network model development has been demonstrated related to the disc brake performance. The influence of disc brake operation conditions (application pressure, initial speed, and temperature) has been modeled related to the disc brake cold, fade, and recovery performance. The artificial neural network model has been developed through investigation of how the synergy of different network's parameters, such as learning algorithm, transfer functions, the number of neurons in the hidden layers, affect the neural model abilities to predict the disc brake performance. It was shown in this paper that complex non-linear interrelations between the disc brake input/output variables can be modeled by proper analysis and setting of artificial neural network parameters. .
PB  - Univerzitet u Beogradu - Mašinski fakultet, Beograd
T2  - FME Transactions
T1  - Razvoj neuronskog modela rada disk kočnice
T1  - Development of neural network model of disc brake operation
EP  - 38
IS  - 1
SP  - 29
VL  - 38
UR  - https://hdl.handle.net/21.15107/rcub_machinery_1025
ER  - 

@article{
author = "Ćirović, Velimir and Aleksendrić, Dragan",
year = "2010",
abstract = "Kvalitet veštačkih neuronskih modela pretežno zavisi od pravilnog izbora arhitekture veštačke neuronske mreže, odnosno algoritma učenja, funkcije prenosa, opsega i raspodele podataka korišćenih za obuku, validaciju i testiranje. Osnovni cilj ovog rada se odnosi na istraživanje kako arhitekture veštačkih neuronskih mreža utiču na uspešnost predviđanja tj. sposobnost generalizacije mreža za isti set podataka za obuku i testiranje. Kompleksni postupak razvoja veštačkog neuronskog modela je demonstriran na primeru disk kočnice. Modeliran je uticaj radnih uslova disk kočnice (pritisak aktiviranja, početna brzina i temperatura) na njene maksimalne performanse kao i performanse opadanja i obnavljanja efikasnosti. Veštački neuronski model je razvijan kroz istraživanje na koji način sinergija različitih parametara mreže, poput algoritma učenja, funkcije prenosa i broja neurona u skrivenim slojevima, utiče na sposobnosti neuronskog modela da predvidi performanse disk kočnice. U ovom radu je pokazano da kompleksne nelinearne zavisnosti između posmatranih ulaznih i izlaznih parametara mogu biti modelirane odgovarajućom analizom i podešavanjem parametara veštačke neuronske mreže., The quality of artificial neural network models mostly depends on a proper setting of neural network architecture i.e. learning algorithm, transfer functions, range and distribution of data used for training, validation, and testing, etc. The goal of this paper is related to the investigation on how artificial neural network architectures influence the network's generalization performance based on the same input/output parameters. The complex procedure of an artificial neural network model development has been demonstrated related to the disc brake performance. The influence of disc brake operation conditions (application pressure, initial speed, and temperature) has been modeled related to the disc brake cold, fade, and recovery performance. The artificial neural network model has been developed through investigation of how the synergy of different network's parameters, such as learning algorithm, transfer functions, the number of neurons in the hidden layers, affect the neural model abilities to predict the disc brake performance. It was shown in this paper that complex non-linear interrelations between the disc brake input/output variables can be modeled by proper analysis and setting of artificial neural network parameters. .",
publisher = "Univerzitet u Beogradu - Mašinski fakultet, Beograd",
journal = "FME Transactions",
title = "Razvoj neuronskog modela rada disk kočnice, Development of neural network model of disc brake operation",
pages = "38-29",
number = "1",
volume = "38",
url = "https://hdl.handle.net/21.15107/rcub_machinery_1025"
}

Ćirović, V.,& Aleksendrić, D.. (2010). Razvoj neuronskog modela rada disk kočnice. in FME Transactions
Univerzitet u Beogradu - Mašinski fakultet, Beograd., 38(1), 29-38.
https://hdl.handle.net/21.15107/rcub_machinery_1025

Ćirović V, Aleksendrić D. Razvoj neuronskog modela rada disk kočnice. in FME Transactions. 2010;38(1):29-38.
https://hdl.handle.net/21.15107/rcub_machinery_1025 .

Ćirović, Velimir, Aleksendrić, Dragan, "Razvoj neuronskog modela rada disk kočnice" in FME Transactions, 38, no. 1 (2010):29-38,
https://hdl.handle.net/21.15107/rcub_machinery_1025 .