Uncertainty Aware Deep Learning for Fault Prediction Using Multivariate Time Series Signals

Conference · Tue Aug 01 04:00:00 EDT 2023 · 2023 International Joint Conference on Neural Networks (IJCNN)

DOI:https://doi.org/10.1109/ijcnn54540.2023.10191827· OSTI ID:2283148

Rahman, Md Monibor ^[1]; Vidyaratne, L. ^[2]; Carpenter, A. ^[2]; Tennant, C. ^[2]; Iftekharuddin, K. ^[1]

---

1. Old Dominion University,Vision Lab,Department of Electrical and Computer Engineering,Norfolk,VA,USA
2. Jefferson Laboratory,Newport News,VA,USA

The superconducting radio-frequency cavities are a crucial component of the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. When a cavity faults, beam delivery to experimental end users is disrupted. Prediction of cavity faults prior to onset is essential to reduce operation and maintenance costs. In this work, a parallel long short-term memory (LSTM)-convolution neural network (CNN)-based deep learning (DL) model is proposed to predict impending faults using pre-fault signals. Further, we introduce an uncertainty quantification approach using Monte Carlo dropout with the LSTM-CNN model to ascertain confidence in the prediction. The model was tested using multivariate time series signals from stable cavity operations and before faults. Initial results show that on the test dataset, the model can identify impending faults before their onset with an average 10-fold cross validation accuracy of 97.39% and a standard deviation of 0.12% using a 100-ms time window. It is also observed that the model performs better as the prediction time moves closer to the fault onset. For additional context, we compare the performance of the model with three machine-learning-based (ML) fault prediction models. Our proposed parallel LSTM-CNN-based DL method shows better performance than the ML-based methods.

• Research Organization: Thomas Jefferson National Accelerator Facility, Newport News, VA (United States)
• Sponsoring Organization: U.S. Department of Energy
• DOE Contract Number: AC05-06OR23177
• OSTI ID: 2283148
• Report Number(s): JLAB-ACC-23-3992; DOE/OR/23177-7390
• Conference Information: Journal Name: 2023 International Joint Conference on Neural Networks (IJCNN)
• Country of Publication: United States
• Language: English