Recurrent Neural Networks for Predictive Maintenance of Mill Fan Systems

• Autorzy: Koprinkova-Hristova P. D. , Hadjiski M. B. , Doukovska L. A. , Beloreshki S. V.
• Języki publikacji: EN

Abstrakty

EN

In the present paper we focus on online monitoring system for predictive maintenance based on sensor automated inputs. Our subject was a device from Maritsa East 2 power plant - a mill fan. The main sensor information we have access to is based on the vibration of the nearest to the mill rotor bearing block. Our aim was to create a (nonlinear) model able to predict on time possible changes in vibrations tendencies that can be early signal for system work deterioration. For that purpose, we compared two types of recurrent neural networks: historical Elman architecture and a recently developed kind of RNN named Echo stet networks (ESN). The preliminary investigations showed better approximation and faster training abilities of ESN in comparison to the Elman network. Direction of future work will be increasing of predications time horizon and inclusion of our predictor at lower level of a complex predictive maintenance system.

Słowa kluczowe

EN

technical diagnosis; thermal power plant; TPP; recurrent neural network; RNN; distributed control system; DCS; predictive maintenance

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2011
• Tom: Vol. 57, No. 3
• Strony: 401--406
• Opis fizyczny: Bibliogr. 14 poz., il., wykr.

Twórcy

autor

Koprinkova-Hristova P. D.

autor

Hadjiski M. B.

autor

Doukovska L. A.

autor

Beloreshki S. V.

• Institute of System Engineering and Robotics, Bulgarian Academy of Sciences,

Bibliografia

• [1] S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. Prentice Hall International, Inc., 1999.
• [2] F. E. Ciarapica and G. Giacchetta, „Managing the Condition-Based Mintenance of a Combined-Cycle Power Plant: An Approach Using Soft Computing Techniques”, Journal of Loss Prevention in the Process Industries, vol. 19, pp. 316 - 325, 2006.
• [3] J. L. Elman, „Finding Structure in Time”, Cognitive Science, vol. 14, pp. 179 - 211, 1990.
• [4] H. Jaeger, „Tutorial on Training Recurrent Nural Networks, Covering BPPT, RTRL, EKF and the „Echo State Network”Approach”, German National Research Center for Information Technology, GMD Report 159, 2002.
• [5] H. Jaeger, „Adaptive Nonlinear System Identification with Echo State Networks”, in Advances in Neural Information Processing Systems 15. Cambridge, MA: MIT Press, 2003, pp. 593 - 600.
• [6] M. Lukosevicius and H. Jaeger, „Reservoir Computing Approaches to Recurrent Neural Network Training”, Computer Science Review, vol. 3, pp. 127 - 149, 2009.
• [7] B. Schrauwen, M. Wandermann, D. Verstraeten, and J. J. Steil, „Improving Reservoirs Using Intrinsic Plasticity”, Neurocomputing, vol. 71, pp. 1159 - 1171, 2008.
• [8] P. Koprinkova-Hristova and G. Palm, „Adaptive Critic Design with ESN Critic for Bioprocess Optimization”, Lecture Notes in Computer Science, vol. 6353, pp. 438 - 447, 2010.
• [9] P. Koprinkova-Hristova, M. Oubbati, and G. Palm, „Adaptive Critic Design with Echo State Network”, in 2010 IEEE Intenrational Conference on Systems, Man and Cybernetics SMC '2010, Istanbul, Turkey, October 10-13 2010, pp. 1010 - 1015.
• [10] T. Balabanov, P. Koprinkova-Hritstova, L. Doukovska, M. Hadjiski, and S. Beloreshki, „Neural Network Model of Mill-Fan System Elements Vibration for Predictive Maintenance”, in 2011 Intenrational Symposium on Innovations in Intelligent SysTems and Applications (INISTA), Istanbul, Turkey, June 15-18 2011, pp. 410 - 414.
• [11] Http://www.mathworks.com/matlabcentral/fileexchange/18289.
• [12] D. Prokhorov, „Echo State Networks: Appeal and Challenges”, in Proceedings of International Joint Conference on Neural Networks (IJCNN), Montreal, Canada, 2005, pp. 1463 - 1466.
• [13] Http://www.reservoir-computing.org/software: Simple and very simple Matlab toolbox for Echo State Networks by H. Jaeger and group members.
• [14] D. L. Donoho, „De-Noising by Soft-Thresholding”, IEEE Transactions on Information Theory, vol. 41, no. 3, pp. 613 - 627, 1995.