The genetic fuzzy based proactive maintenance of a technical object

• Autorzy: Smoczek J. , Szpytko J.
• Języki publikacji: EN

Abstrakty

EN

The proactive maintenance is an effective approach to enhance the system availability through real time monitoring the current state of a system. The key part of this method is forecasting the nonoperational states for advanced warning of the failure possibility that can bring the attention of machines operators and maintenance personnel to impending danger facilitate planning preventive and corrective operations, and resources managing as well. The paper presents the HMI/SCADA-type application used to support decision-making process. The proposed approach to proactive maintenance is based on forecasting the remaining useful life of device equipment and delivering the user-defined maintenance strategy developed during system operation. The HMI/SCADA application is used to collect data in form of failures history, changes of operational conditions and performances of a monitored process between failures, as well as heuristic knowledge about process created by experienced user. The data history is used to design the predictive fuzzy models of time between failures of system equipment. The fuzzy predictive models are designed using the genetic algorithm applied to optimize the fuzzy partitions covering the training data examples, as well as to identify fuzzy predictive patterns represented by a set of rules in the knowledge base. The evolutionary learning strategy, which has been proposed in this paper, provides the effective reproduction techniques for searching the solution space with respect to optimization of knowledge base and membership functions according to the fitness function expressed as a ratio of compatibility of fuzzy partitions with data examples to root mean squares error. The proposed application was created and tested on the laboratory stand for monitoring the availability of the overhead travelling crane.

Słowa kluczowe

EN

proactive maintenance; failure prediction; fuzzy logic; genetic algorithm

• Wydawca: Łukasiewicz Research Network - Institute of Aviation ; European Science Society of Powertrain and Transport KONES Poland ; Wydawnictwo Instytutu Technicznego Wojsk Lotniczych
• Czasopismo: Journal of KONES
• Rocznik: 2012
• Tom: Vol. 19, No. 3
• Strony: 399--405
• Opis fizyczny: Bibliogr. 11 poz., rys.

Twórcy

autor

Smoczek J.

autor

Szpytko J.

• AGH University of Science and Technology Faculty of Mechanical Engineering and Robotics Mickiewicza Av. 30, 30-059 Krakow, Poland tel.: [phone], fax: [phone],

Bibliografia

• [1] Chen, Y., Chang, F. J., Evolutionary artificial neural networks for hydrological systems forecasting, Journal of Hydrology, 367, pp. 125-137, 2004.
• [2] Damousis, I. G., Alexiadis, M. C., Theocharis, J. B., Dokopoulos, P. S., A fuzzy model for wind speed prediction and power generation in wind park using spatial correlation, IEEE Transactions on Energy Conversion, Vol. 19, No. 2,pp. 352-361, 2004.
• [3] Kim, D., Kim, C., Forecasting time series with genetic fuzzy predictor ensemble, IEEE Transactions on Fuzzy Systems, Vol. 5, No. 4, pp. 523-535, 1997.
• [4] Kisi, O., Shiri, J., Precipitation forecasting using wavelet-genetic programming and waveletneuro- fuzzy conjunction Models, Water Resource Manage, 25, pp. 3135-3152, 2011.
• [5] Ning, M. H., Yong, Q., Di, H., Ying, C., Zhong, Z. J., Software aging prediction model based on fuzzy wavelet network with adaptive genetic algorithm, In 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI’06), IEEE Computer Society, pp. 659–666, Los Alamitos, CA, USA 2006.
• [6] Pawar, P. M., Ganguli, R., Genetic fuzzy system for online structural health monitoring of composite helicopter rotor blades, Mechanical Systems and Signal processing, 21: 2212- 2236, 2007.
• [7] Prochazka, A., Sys, V., Time series prediction using genetically trained wavelet networks, Proceedings of IEEE Workshop on Neural Networks for Signal Processing, pp. 195-203, 1994.
• [8] Smoczek, J., Szpytko, J., Intelligent supervisory system for availability estimation of automated material handling system, In Proceedings of the European Safety and Reliability Conferemce, ESREL, Troyes, France, pp. 2797-2804, 2011.
• [9] Smoczek, J., Szpytko, J., Self-learning fuzzy predictor of exploitation system operating time, Journal of KONES Powertrain and Transport, Vol. 18, No. 4, pp. 463-469, 2011.
• [10] Smoczek, J., Szpytko, J., A genetic fuzzy approach to estimate operating time of transport device, Journal of KONES Powertrain and Transport, Vol. 18, No. 4, pp. 601-608, 2011.
• [11] Weiss, G., Timeweaver: A genetic algorithm for identifying predictive patterns in sequences of events, In Proceedings of the Genetic and Evolutionary Computation Conference, pp. 718-725, Morgan Kaufmann, San Francisco, CA, 1999.