Interpretable Recurrent Variational State-Space Model for Fault Detection of Complex Systems Based on Multisensory Signals
Source abstract
Abstract
It is necessary to develop a health monitoring system (HMS) for complex systems to improve safety and reliability and prevent potential failures. Time-series signals are collected from multiple sensors installed on the equipment that can reflect the health condition of them. In this study, a novel interpretable recurrent variational state-space model (IRVSSM) is proposed for time-series modeling and anomaly detection. To be specific, the deterministic hidden state of a recursive neural network is used to capture the latent structure of sensor data, while the stochastic latent variables of a nonlinear deep state-space model capture the diversity of sensor data. Temporal dependencies are modeled through a nonlinear transition matrix; an automatic relevance determination network is introduced to selectively emphasize important sensor data. Experimental results demonstrate that the proposed algorithm effectively captures vital information within the sensor data and provides accurate and reliable fault diagnosis during the steady-state phase of liquid rocket engine operation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Anomaly Detection Techniques and Applications · Neural Networks and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China
Funding
National Natural Science Foundation of China · Basic Research Program of China · Basic Research Fund of Xi’an Jiaotong University · High level innovation and entrepreneurship talent program
References (28)
Show source-provided references
1. Hu, N., Qin, G., Hu, L., Xie, G., and Hu, H. (2007, January 11–13). Real-time fault detection system for turbopump of liquid rocket engine based on vibration measurement signals. Proceedings of the 6th International Workshop on Structural Health Monitoring, Stanford, CA, USA.
2. Norman, J.A., and Nemeth, E. (1990, January 16–18). Development of a health monitoring algorithm. Proceedings of the 26th Joint Propulsion Conference, Orlando, FL, USA.10.2514/6.1990-1991 ↗
3. Deep neural network approach for fault detection and diagnosis during startup transient of liquid-propellant rocket engine10.1016/j.actaastro.2020.08.019 ↗
4. Steady-state process fault detection for liquid rocket engines based on convolutional auto-encoder and one-class support vector machine10.1109/ACCESS.2019.2961742 ↗
5. Memory-augmented skip-connected autoencoder for unsupervised anomaly detection of rocket engines with multi-source fusion10.1016/j.isatra.2022.07.014 ↗
6. Make the rocket intelligent at IoT edge: Stepwise GAN for anomaly detection of LRE with multisource fusion10.1109/JIOT.2021.3097437 ↗
7. Model-Based Leakage Estimation and Remaining Useful Life Prediction of Control Gas Cylinder10.1155/2023/3606822 ↗
8. Omata, N., Tsutsumi, S., Abe, M., Satoh, D., Hashimoto, T., Sato, M., Kimura, T., and IEEE (2022, January 5–12). Model-based fault detection with uncertainties in a reusable rocket engine. Proceedings of the 2022 IEEE Aerospace Conference (AERO), Big Sky, MT, USA.10.1109/AERO53065.2022.9843212 ↗
9. Deep state space model for predicting cryptocurrency price10.1016/j.ins.2022.10.129 ↗
10. Learning robust deep state space for unsupervised anomaly detection in contaminated time-series
11. Sequential Estimation of Gaussian Process-based Deep State-Space Models10.1109/TSP.2023.3303648 ↗
12. Kalman Filtering for Spacecraft Attitude Estimation10.2514/3.56190 ↗
13. Kingma, D.P., and Welling, M. (2014). Auto-Encoding Variational Bayes. arXiv.
14. Rangapuram, S.S., Seeger, M., Gasthaus, J., Stella, L., Wang, Y., and Januschowski, T. (2018, January 3–8). Deep state space models for time series forecasting. Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
15. Fraccaro, M. (2018). Deep Latent Variable Models for Sequential Data, DTU Compute.
16. A Flow-Based Deep Latent Variable Model for Speech Spectrogram Modeling and Enhancement
17. Shen, X. (2022). Deep Latent-Variable Models for Text Generation. arXiv.
18. BioVAE: A pre-trained latent variable language model for biomedical text mining
19. Chira, D., Haralampiev, I., Winther, O., Dittadi, A., and Liévin, V. (2022, January 23–27). Image Super-Resolution with Deep Variational Autoencoders. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-25063-7_24 ↗
20. Krishnan, R.G., Shalit, U., Sontag, D. (2017, January 4–9). Structured Inference Networks for Nonlinear State Space Models. Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10779 ↗
21. Gedon, D., Wahlstrm, N., Schn, T.B., and Ljung, L. (2021). Deep State Space Models for Nonlinear System Identification, Elsevier.10.1016/j.ifacol.2021.08.406 ↗
22. Burda, Y., Grosse, R., and Salakhutdinov, R. (2015). Importance Weighted Autoencoders. arXiv.
23. Learning Representations by Back-Propagating Errors10.1038/323533a0 ↗
24. Rezende, D.J., Mohamed, S., and Wierstra, D. (2014, January 22–24). Stochastic Backpropagation and Approximate Inference in Deep Generative Models. Proceedings of the International Conference on Machine Learning, Beijing, China.
25. Kingma, D.P., Rezende, D.J., Mohamed, S., and Welling, M. (2014, January 8–13). Semi-supervised Learning with Deep Generative Models. Proceedings of the 28th Conference on Neural Information Processing Systems (NIPS), Montreal, QC, Canada.
26. A New View of Automatic Relevance Determination
27. Sparse methods for automatic relevance determination10.1016/j.physd.2021.132843 ↗
28. Li, L.Y., Yan, J.C., Yang, X.K., and Jin, Y.H. (2019, January 10–16). Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting. Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China.10.24963/ijcai.2019/402 ↗