Научный журнал Моделирование, оптимизация и информационные технологииThe scientific journal Modeling, Optimization and Information Technology
cетевое издание
issn 2310-6018

DEEP NEURAL NETWORKS FOR PREDICTIVE MAINTENANCE

Sai V.С.  

UDC 004.02
DOI: 10.26102/2310-6018/2019.27.4.011

  • Abstract
  • List of references
  • About authors

At present, deep neural networks are becoming one of the most popular approaches in solving various practical problems from a wide variety of fields, such as image and speech recognition, natural language processing, computer vision, medical informatics, etc. The article considers the possibility of using deep neural networks in the implementation of proactive maintenance strategy – predictive maintenance (PdM). Various methods of constructing predictive models for PdM are considered. Currently, the data-driven approaches using deep neural networks for constructing predictive models for PdM are most promising methods. One of the reasons for the successful application of deep neural networks is that the networks automatically selects important features from the data needed to solve the problem. The most commonly used neural networks for PdM are considered: Long short-term memory (LSTM), convolutional neural networks (CNN) and autoencoders. An overview of powerful frameworks for the design and training of neural networks is given.

1. Sai Van Cuong, Shсherbakov M. V. A data-driven method for remaining useful life prediction of multiple-component systems. Сaspian journal: management and high technologies. 2019;(1):33-44.

2. Azhmuhamedov I.M., Gostjunin Ju.A. Vybor strategija tehnicheskogo obsluzhivanija i remonta oborudovanija setej svjazi na predprijatijah neftegazovogo kompleksa. Jelektronnyj nauchnyj zhurnal: Inzhenernyj vestnik Dona. 2017;(2):74-84.

3. Liu J., Wan W., Golnaraghi F. A multi-step predictor with a variable input pattern for system state forecasting // Mech. Syst. Signal Process. 2009:1586-1599.

4. Huang Z., Xu Z., Wang W., Sun Y. Remaining useful life prediction for a nonlinear heterogeneous Wiener process model with an adaptive drift. IEEE Trans. Rel. 2015;(2):687- 700.

5. Dui H., Si S., Zuo M., Sun S. Semi-Markov process-based integrated importance measure for multi-state systems. IEEE Transactions on Reliability. 2015;64(2):54-765.

6. Cartella F., Lemeire J., Dimiccoli L., Sahli H. Hidden semi-Markov models for predictive maintenance. Mathematical Problems in Engineering. 2015.

7. Liu J., Saxena A., Goebel K., Saha B., Wang W. An adaptive recurrent neural network for remaining useful life prediction of lithiumion batteries. Annual Conference of the Prognostics and Health Management Society. 2010:1-9.

8. Lei Y., Li N., Gontarz S., Lin J., Radkowski S., Dybala S. A Model-Based Method for Remaining Useful Life Prediction of Machinery . IEEE Transactions on Reliability. 2017.

9. Khoury E., Deloux E., Grall A., Berenguer C. On the Use of Time-Limited Information for Maintenance Decision Support: A Predictive Approach under Maintenance Constraints // Mathematical Problems in Engineering, 2013:1-11.

10. De Benedetti M., Leonardi F., Messina F., Santoro C., Vasilakos A. Anomaly detection and predictive maintenance for photovoltaic systems. Neurocomputing. 2018:59-68.

11. Zhao R., Wang J., Yan R., Mao K. Machine health monitoring with LSTM networks. 10th International Conference on the Sensing Technology. 2016.

12. Li X., Ding Q., Sun J. Q. Remaining useful life estimation in prognostics using deep convolution neural networks. Reliability Engineering & System Safety/ 2018;(172):1-11.

13. Sun W., Shao S., Zhao R., Yan R., Zhang X., Chen X. A sparse auto- encoder-based deep neural network approach for induction motor faults classification. Measurement. 2016;(89):171-178.

14. Lu C., Wang Z., Qin W., Ma, J. Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state. 2017.

15. Guo L., Gao H., Huang H., He X., Li S. Multi-features fusion and nonlinear dimension reduction for intelligent bearing condition monitoring. Shock and Vibration. 2016.

16. TenforFlow. Available at: https://www.tensorflow.org/ (accessed 22.09.2019).

17. Theano. Available at: http://deeplearning.net/software/theano/, (accessed 25.09.2019).

18. CNTK. Available at: https://cntk.ai, (accessed 25.09.2019).

19. Keras. Available at: https://keras.io, (accessed 26.09.2019).

20. PyTorch. Available at: https://pytorch.org, (accessed 27.10.2019).

Sai Van Сuong

Email: svcuonghvktqs@gmail.com

Volgograd State Technical University

Volgograd, Russian Federation

Keywords: predictive maintenance, data-driven methods, deep neural networks, lstm, cnn, autoencoders

For citation: Sai V.С. DEEP NEURAL NETWORKS FOR PREDICTIVE MAINTENANCE. Modeling, Optimization and Information Technology. 2019;7(4). Available from: https://moit.vivt.ru/wp-content/uploads/2019/11/SaiVanCuong_4_19_1.pdf DOI: 10.26102/2310-6018/2019.27.4.011 (In Russ).

136

Full text in PDF