Real-Time Equipment Health State Prediction with LSTM Networks and Bayesian Inference
- 210 Downloads
Due to the emergence of sensing technology, a large number of sensors is used to monitor the health state of manufacturing equipment, thus enhancing the capabilities of predicting abnormal behaviours in (near) real-time. However, existing algorithms in predictive maintenance suffer from several limitations related to their scalability, efficiency, and reliability preventing their wide application to various industries. This paper proposes an approach for real-time prediction of the equipment health state using time-domain features extraction, Long Short-Term Memory (LSTM) Neural Networks, and Bayesian Online Changepoint Detection (BOCD). The proposed approach is applied to a real-life case in the steel industry and extensive experiments are performed. The paper also discusses the results and the conclusions drawn from the proposed approach.
KeywordsPredictive analytics Deep learning Changepoint detection Prognosis Machine learning Predictive maintenance Industry 4.0
This work was partly funded by the European Union's Horizon 2020 projects: UPTIME “Unified Predictive Maintenance System” (Grant agreement No. 768634) and COALA “Cognitive Assisted agile manufacturing for a Labor force supported by trustworthy Artificial Intelligence” (Grant agreement No. 957296). The work presented here reflects only the authors’ view and the European Commission is not responsible for any use that may be made of the information it contains.
- 5.Angelopoulos, A., et al.: Tackling faults in the industry 4.0 era—a survey of machine-learning solutions and key aspects. Sensors 20(1), 109 (2020)Google Scholar
- 7.Shi, Z., Chehade, A.: A dual-LSTM framework combining change point detection and remaining useful life prediction. Reliab. Eng. Sys. Saf. 205(1), 107257 (2021)Google Scholar
- 14.Yang, T., Zheng, Z., Qi, L.: A method for degradation prediction based on Hidden Semi-Markov models with mixture of Kernels. Comput. Ind. 122, 103295 (2020)Google Scholar
- 17.Zheng, S., Ristovski, K., Farahat, A., Gupta, C.: Long short-term memory network for remaining useful life estimation. In: 2017 IEEE International Conference on Prognostics and Health Management (ICPHM), pp. 88–95. IEEE (2017)Google Scholar
- 22.Namoano, B., Starr, A., Emmanouilidis, C., Cristobal, R.C.: Online change detection techniques in time series: An overview. In: 2019 IEEE International Conference on Prognostics and Health Management (ICPHM), pp. 1–10. IEEE (2019)Google Scholar
- 23.Caesarendra, W., Kosasih, B., Tieu, K., Moodie, C.A.: An application of nonlinear feature extraction-a case study for low speed slewing bearing condition monitoring and prognosis. In: 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, pp. 1713–1718. IEEE (2013)Google Scholar
- 25.Namoano, B., Emmanouilidis, C., Ruiz-Carcel, C., Starr, A. G.: Change detection in streaming data analytics: a comparison of Bayesian online and martingale approaches. IFAC-PapersOnLine, 53(3), 336–341 (2020)Google Scholar
- 26.Adams, R.P., MacKay, D.J.: Bayesian online changepoint detection. arXiv preprint arXiv:0710.3742 (2017)
- 27.Kingma, D. P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
- 28.Bousdekis, A., Apostolou, D., Mentzas, G.: A human cyber physical system framework for operator 4.0–artificial intelligence symbiosis. Manuf. Lett. 25(1), 10–15 (2020)Google Scholar