View source for Representation Learning for Fault Detection and Prognosis

{{StudentProjectTemplate
|Summary=Characterise the observed system using representation learning techniques, for fault detection and remaining useful life prediction
|References=Bengio, Yoshua, Aaron Courville, and Pascal Vincent. "Representation learning: A review and new perspectives." IEEE transactions on pattern analysis and machine intelligence 35.8 (2013): 1798-1828.

Jaiswal, Ashish, et al. "A survey on contrastive self-supervised learning." Technologies 9.1 (2020): 2.

Liu, Xiao, et al. "Self-supervised learning: Generative or contrastive." IEEE Transactions on Knowledge and Data Engineering (2021).

Wan, Chuan, et al. "Representation Learning for Fault Diagnosis with Contrastive Predictive Coding." 2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes (SAFEPROCESS). IEEE, 2021.

Jiang, Guoqian, et al. "Stacked multilevel-denoising autoencoders: A new representation learning approach for wind turbine gearbox fault diagnosis." IEEE Transactions on Instrumentation and Measurement 66.9 (2017): 2391-2402.

Xiao, Dengyu, et al. "Unsupervised deep representation learning for motor fault diagnosis by mutual information maximization." Journal of Intelligent Manufacturing 32.2 (2021): 377-391.

Li, Guoqiang, et al. "Self-supervised learning for intelligent fault diagnosis of rotating machinery with limited labeled data." Applied Acoustics 191 (2022): 108663.

Wang, Tian, et al. "Data-driven prognostic method based on self-supervised learning approaches for fault detection." Journal of Intelligent Manufacturing 31.7 (2020): 1611-1619.

Quevedo, Joseba, et al. "Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network." Engineering Applications of Artificial Intelligence 30 (2014): 18-29.

Fan, Yuantao, et al. "Predicting Air Compressor Failures with Echo State Networks." Third European Conference of the Prognostics and Health Management Society 2016, Bilbao, Spain, 5-8 July, 2016. PHM Society, 2016.
|Supervisor=Yuantao Fan, 
|Status=Draft
}}
Fault detection and prognosis are essential components for many industrial operations and equipment maintenance. Time series data are streamed and analyzed to evaluate the health condition of the industrial equipment, and for maintenance scheduling. The objective of this project is to explore and develop representation learning methods that can capture various characteristics (e.g. temporal information) of the observed system and evaluate its usefulness in the context of fault detection and prognosis. One promising approach is via self-supervised (contrastive) learning, as industrial data are of massive amounts with very few labels.