Stanley Fong

PhD Candidate with the SDIC group

Department of Civil & Environmental Engineering

University of Waterloo, Waterloo, Canada

stan.fong@uwaterloo.ca

Research Interests

My overall focus is centered on the development of application-agnostic machine learning and signal processing methods for condition monitoring in unsupervised, real-world settings. Specific topics include:

  • Unsupervised early degradation detection, degradation thresholding and fault prediction using machine learning and hierarchical Bayesian methods

  • Unsupervised and semi-supervised methods for leak detection and localization for water distribution networks with emphasis on IoT conducive methods

  • Blind analysis of non-stationary vibration signals with time-frequency-based clustering techniques and statistical tools

  • Unsupervised frameworks for data-driven condition monitoring of rotating machinery with emphasis on scalability and ease of implementation in IoT applications in "real world" settings

Keywords: unsupervised learning, machine learning, signal processing, non-stationary signals, condition-based maintenance, condition monitoring, leak detection



Fig 1: Early degradation detection in industrial bearing run-to-failure data using Bayesian OC-SVM (B-OCSVM) [2]

Fig 2: Prior-indepedent Bayesian fault prediction with novel t-3 prognostic and B-OCSVM-based fault threshold [2]

Publications

  1. S. Fong and S. Narasimhan, “An unsupervised Bayesian oc-svm approach for early degradation detection, thresholding and fault prediction in machinery monitoring,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-11, 2022, Art no. 3500811, doi: 10.1109/TIM.2021.3137858.

  2. M. Kafle, S. Fong, and S. Narasimhan, "Active acoustic leak detection and localization in a plastic pipe using time delay estimation", Applied Acoustics, vol. 187, 2022. doi: 10.1016/j.apacoust.2021.108482.

  3. S. Fong, J. Harmouche, S. Narasimhan, and J. Antoni, “Mean shift clustering-based analysis of non-stationary vibration signals for machinery diagnostics,” IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 7, pp. 4056–4066, 2020. doi:10.1109/TIM.2019.2944503.

  4. S. Fong, S. Narasimhan, and M. Riseborough, “A blind condition-based maintenance framework for real-time fault detection and degradation modeling of the link apm gearbox,” in Automated People Movers and Automated Transit Systems 2020, pp. 43–54. doi: 10.1061/9780784483077.005.

  5. S. Fong, A. Ashasi-Sorkhabi, G. Prakash, S. Naraimshan, and M. Riseborough, “Automated condition-based monitoring of automated people movers,” in Proceedings of the 16th International Conference on Automated People Movers and Automated Transit Systems, Tampa, FL: ASCE, 2018. doi: 10.1061/9780784481318.

  6. A. Ashasi-Sorkhabi, S. Fong, G. Prakash, and S. Naraimshan, “A condition based maintenance implementation for an automated people mover gearbox,” International Journal of Prognostics and Health Management, vol. 8, no. 020, p. 13, 2017. doi: 10.36001/ ijphm.2017.v8i3.2648.

  7. S. Fong, S. Walbridge, and S. Narasimhan "Studies on vibration serviceability assessment of aluminum pedestrian bridges," in Proceedings of: 2016 Annual Conference of the Canadian Society for Civil Engineering, London, ON: CSCE, June 1-4.