Neural modelling of friction material cold performance
Само за регистроване кориснике
2008
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
The complex and highly non-linear phenomena involved during braking are primarily caused by friction materials' characteristics. The final friction materials' characteristics are determined by their compositions, manufacturing, and the brake's operating conditions. Analytical models of friction materials' behaviour are difficult, even impossible, to obtain for the case of different brakes' operating conditions. That is why, in this paper, all relevant influences on the friction materials' cold performance have been integrated by means of artificial neural networks. The influences of 26 input parameters, defined by the friction materials' composition (18 ingredients), manufacturing (five parameters), and brake's operating conditions (three parameters), have been modelled versus changes of the brake factor C. Based on training and testing of 18 different architectures of neural networks with five learning algorithms, a total of 90 neural models have been investigated. The neural model (1...3112684 1) trained by the two-layered neural network, with a Bayesian regulation algorithm, was found to reach the best prediction results. This neural model was able to generalize the friction materials' cold performance, for temperatures in the contact of the friction pair T lt = 100 C in the range of application pressure changes between 20 and 100 bar, and for initial speed changes between 20 and 100 km/h.
Кључне речи:
neural modelling / friction material / cold performanceИзвор:
Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering, 2008, 222, D7, 1201-1209Издавач:
- Professional Engineering Publishing Ltd, Westminister
DOI: 10.1243/09544070JAUTO583
ISSN: 0954-4070
WoS: 000258637300006
Scopus: 2-s2.0-47949121254
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Aleksendrić, Dragan AU - Duboka, Čedomir AU - Mariotti, G. V. PY - 2008 UR - https://machinery.mas.bg.ac.rs/handle/123456789/818 AB - The complex and highly non-linear phenomena involved during braking are primarily caused by friction materials' characteristics. The final friction materials' characteristics are determined by their compositions, manufacturing, and the brake's operating conditions. Analytical models of friction materials' behaviour are difficult, even impossible, to obtain for the case of different brakes' operating conditions. That is why, in this paper, all relevant influences on the friction materials' cold performance have been integrated by means of artificial neural networks. The influences of 26 input parameters, defined by the friction materials' composition (18 ingredients), manufacturing (five parameters), and brake's operating conditions (three parameters), have been modelled versus changes of the brake factor C. Based on training and testing of 18 different architectures of neural networks with five learning algorithms, a total of 90 neural models have been investigated. The neural model (13112684 1) trained by the two-layered neural network, with a Bayesian regulation algorithm, was found to reach the best prediction results. This neural model was able to generalize the friction materials' cold performance, for temperatures in the contact of the friction pair T lt = 100 C in the range of application pressure changes between 20 and 100 bar, and for initial speed changes between 20 and 100 km/h. PB - Professional Engineering Publishing Ltd, Westminister T2 - Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering T1 - Neural modelling of friction material cold performance EP - 1209 IS - D7 SP - 1201 VL - 222 DO - 10.1243/09544070JAUTO583 ER -
@article{ author = "Aleksendrić, Dragan and Duboka, Čedomir and Mariotti, G. V.", year = "2008", abstract = "The complex and highly non-linear phenomena involved during braking are primarily caused by friction materials' characteristics. The final friction materials' characteristics are determined by their compositions, manufacturing, and the brake's operating conditions. Analytical models of friction materials' behaviour are difficult, even impossible, to obtain for the case of different brakes' operating conditions. That is why, in this paper, all relevant influences on the friction materials' cold performance have been integrated by means of artificial neural networks. The influences of 26 input parameters, defined by the friction materials' composition (18 ingredients), manufacturing (five parameters), and brake's operating conditions (three parameters), have been modelled versus changes of the brake factor C. Based on training and testing of 18 different architectures of neural networks with five learning algorithms, a total of 90 neural models have been investigated. The neural model (13112684 1) trained by the two-layered neural network, with a Bayesian regulation algorithm, was found to reach the best prediction results. This neural model was able to generalize the friction materials' cold performance, for temperatures in the contact of the friction pair T lt = 100 C in the range of application pressure changes between 20 and 100 bar, and for initial speed changes between 20 and 100 km/h.", publisher = "Professional Engineering Publishing Ltd, Westminister", journal = "Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering", title = "Neural modelling of friction material cold performance", pages = "1209-1201", number = "D7", volume = "222", doi = "10.1243/09544070JAUTO583" }
Aleksendrić, D., Duboka, Č.,& Mariotti, G. V.. (2008). Neural modelling of friction material cold performance. in Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering Professional Engineering Publishing Ltd, Westminister., 222(D7), 1201-1209. https://doi.org/10.1243/09544070JAUTO583
Aleksendrić D, Duboka Č, Mariotti GV. Neural modelling of friction material cold performance. in Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering. 2008;222(D7):1201-1209. doi:10.1243/09544070JAUTO583 .
Aleksendrić, Dragan, Duboka, Čedomir, Mariotti, G. V., "Neural modelling of friction material cold performance" in Proceedings of The Institution of Mechanical Engineers Part D-Journal of Automobile Engineering, 222, no. D7 (2008):1201-1209, https://doi.org/10.1243/09544070JAUTO583 . .