Prediction of the Filter Life Cycle Based on Artificial Neural Networks
Нема приказа
Конференцијски прилог (Објављена верзија)
,
Prof. Vidosav Majstorović
Метаподаци
Приказ свих података о документуАпстракт
This paper aims to show the realization of the system based on artificial neural networks application in the process of monitoring of water filtration procedure, early prediction of filter damage and initial activation of self-cleaning, which is necessary to carry out so that the system would function properly. The control system proposed involves two artificial neural networks which completely define parameters of the process state. Capability of filter self-cleaning gives a possibility of significant autonomous work. The most important characteristic of the filter is the change of differential pressure in the function of water flow, and as this is a nonlinear function, the choice of such supervising system and control process is justified. The learning algorithm used in this nonlinear mapping was back-propagation within the BPnet software. Considering the fact that the system permanently does the acquisition of information about the system state, it is possible, by using data about "...rainy days", to define correlation between the characteristic of filter operation and outward atmosphere factor.
Кључне речи:
Artificial neural networks / Monitoring of water filtration procedure / Prediction method / Filter damage / Filter self-cleaning / Industrial control systems / Differential pressure / Water flow / Supervising learning system / The acquisition of the industrial system state / Life cycle engineering / Autonomous plant / BPnet softwareИзвор:
Proceedings of the 11th International CIRP Life Cycle Engineering Seminar, 2004, 131-137Издавач:
- Association SCG for Quality and Standards, Belgrade
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Lazarević, Ivan AU - Miljković, Zoran PY - 2004 UR - https://machinery.mas.bg.ac.rs/handle/123456789/6509 AB - This paper aims to show the realization of the system based on artificial neural networks application in the process of monitoring of water filtration procedure, early prediction of filter damage and initial activation of self-cleaning, which is necessary to carry out so that the system would function properly. The control system proposed involves two artificial neural networks which completely define parameters of the process state. Capability of filter self-cleaning gives a possibility of significant autonomous work. The most important characteristic of the filter is the change of differential pressure in the function of water flow, and as this is a nonlinear function, the choice of such supervising system and control process is justified. The learning algorithm used in this nonlinear mapping was back-propagation within the BPnet software. Considering the fact that the system permanently does the acquisition of information about the system state, it is possible, by using data about "rainy days", to define correlation between the characteristic of filter operation and outward atmosphere factor. PB - Association SCG for Quality and Standards, Belgrade C3 - Proceedings of the 11th International CIRP Life Cycle Engineering Seminar T1 - Prediction of the Filter Life Cycle Based on Artificial Neural Networks EP - 137 SP - 131 UR - https://hdl.handle.net/21.15107/rcub_machinery_6509 ER -
@conference{ author = "Lazarević, Ivan and Miljković, Zoran", year = "2004", abstract = "This paper aims to show the realization of the system based on artificial neural networks application in the process of monitoring of water filtration procedure, early prediction of filter damage and initial activation of self-cleaning, which is necessary to carry out so that the system would function properly. The control system proposed involves two artificial neural networks which completely define parameters of the process state. Capability of filter self-cleaning gives a possibility of significant autonomous work. The most important characteristic of the filter is the change of differential pressure in the function of water flow, and as this is a nonlinear function, the choice of such supervising system and control process is justified. The learning algorithm used in this nonlinear mapping was back-propagation within the BPnet software. Considering the fact that the system permanently does the acquisition of information about the system state, it is possible, by using data about "rainy days", to define correlation between the characteristic of filter operation and outward atmosphere factor.", publisher = "Association SCG for Quality and Standards, Belgrade", journal = "Proceedings of the 11th International CIRP Life Cycle Engineering Seminar", title = "Prediction of the Filter Life Cycle Based on Artificial Neural Networks", pages = "137-131", url = "https://hdl.handle.net/21.15107/rcub_machinery_6509" }
Lazarević, I.,& Miljković, Z.. (2004). Prediction of the Filter Life Cycle Based on Artificial Neural Networks. in Proceedings of the 11th International CIRP Life Cycle Engineering Seminar Association SCG for Quality and Standards, Belgrade., 131-137. https://hdl.handle.net/21.15107/rcub_machinery_6509
Lazarević I, Miljković Z. Prediction of the Filter Life Cycle Based on Artificial Neural Networks. in Proceedings of the 11th International CIRP Life Cycle Engineering Seminar. 2004;:131-137. https://hdl.handle.net/21.15107/rcub_machinery_6509 .
Lazarević, Ivan, Miljković, Zoran, "Prediction of the Filter Life Cycle Based on Artificial Neural Networks" in Proceedings of the 11th International CIRP Life Cycle Engineering Seminar (2004):131-137, https://hdl.handle.net/21.15107/rcub_machinery_6509 .