Physics and Data Collaborative Root Cause Analysis Integrating Pretrained Large Language Models and Data-Driven AI for Trustworthy Asset Health Management
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Data-driven tools for asset health management face significant challenges, including a lack of understanding of physical principles, difficulty incorporating domain experts’ experiences, and consequently low detection accuracy, leading to trustworthiness issues. Automatically integrating data-driven analysis with human knowledge and experience, as found in literature and maintenance logs, is critically needed. Recent progress in large language models (LLMs) offers opportunities to achieve this goal. However, there is still a lack of work that effectively combines pretrained LLMs with data-driven models for asset health management using industrial time series data as input. This paper presents a framework that integrates our recently proposed data-driven AI with pretrained LLMs to address root cause detection in industrial failure analysis. The framework employs LLMs to analyze outputs from our data-driven root cause analysis models, filtering out less relevant results and prioritizing those that align closely with physical principles and domain expertise. Our innovative approach leverages advanced data-driven analytics and a multi-LLM debate for collaborative decision-making, seamlessly merging data-driven insights with domain knowledge. Specifically, through our proposed self-exclusionary debates among multiple LLMs, biases inherent in single-LLM systems are effectively mitigated, enhancing reliability and stability. Crucially, the framework bridges the gap between data-driven models and physics-informed LLMs, accelerating the interaction between data and knowledge for more informed and realistic decision-making processes.
How to Cite
##plugins.themes.bootstrap3.article.details##
root cause analysis, LLM
2. Arunthavanathan, R., Khan, F., Ahmed, S., & Imtiaz, S. (2022). Autonomous fault diagnosis and root cause analysis for the processing system using one-class svm and nn permutation algorithm. Industrial & Engineering Chemistry Research, 61(3).
3. Bai, Y., & Zhao, J. (2023). A novel transformer-based multivariable multi-step prediction method for chemical process fault prognosis. Process Safety and Environmental Protection, 169, 937–947.
4. Chan, C.-M., Chen, W., Su, Y., Yu, J., Xue, W., Zhang, S., . . . Liu, Z. (2023). Chateval: Towards better llm-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201.
5. Cheng, W., Zhang, K., Chen, H., Jiang, G., Chen, Z., & Wang, W. (2016). Ranking causal anomalies via temporal and dynamical analysis on vanishing correlations. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 805–814).
6. Du, Y., Li, S., Torralba, A., Tenenbaum, J. B., & Mordatch, I. (2023). Improving factuality and reasoning in language models through multiagent debate. arXiv preprint arXiv:2305.14325.
7. Ellefsen, A. L., .s.y, V., Ushakov, S.,&Zhang, H. (2019). A comprehensive survey of prognostics and health management based on deep learning for autonomous ships. IEEE Transactions on Reliability, 68(2), 720–740.
8. Filonov, P., Kitashov, F., & Lavrentyev, A. (n.d.). Rnn-based early cyber-attack detection for the tennessee eastman process. arXiv preprint arXiv:1709.02232.
9. Huang, H., Shah, T., Karigiannis, J., & Evans, S. (2024). Deep root cause analysis: unveiling anomalies and enhancing fault detection in industrial time series. In 2024 international joint conference on neural networks (ijcnn).
10. Ji, C., Ma, F., Wang, J., Wang, J., & Sun, W. (2021). Realtime industrial process fault diagnosis based on time delayed mutual information analysis. Processes, 9(6), 1027.
11. Kim, C., Lee, H., & Lee, W. B. (2019). Process fault diagnosis via the integrated use of graphical lasso and markov random fields learning & inference. Computers & Chemical Engineering, 125, 460–475.
12. Kozitsin, V., Katser, I., & Lakontsev, D. (2021). Online forecasting and anomaly detection based on the arima model. Applied Sciences, 11(7), 3194.
13. Kumar, V., Gleyzer, L., Kahana, A., Shukla, K., & Karniadakis, G. E. (2023). Mycrunchgpt: A llm assisted framework for scientific machine learning. Journal of Machine Learning for Modeling and Computing, 4(4).
14. Li, P., Wang, X., Zhang, Z., Meng, Y., Shen, F., Li, Y., . . . Zhu, W. (2024). Llm-enhanced causal discovery in temporal domain from interventional data. arXiv preprint arXiv:2404.14786.
15. Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., . . . Shi, S. (2023). Encouraging divergent thinking in large language models through multi-agent debate. arXiv preprint arXiv:2305.19118.
16. Liao, L., & Ahn, H.-i. (2016). Combining deep learning and survival analysis for asset health management. International Journal of PHM, 7(4).
17. Lomov, I., Lyubimov, M., Makarov, I., & Zhukov, L. E. (2021). Fault detection in tennessee eastman process with temporal deep learning models. Journal of Industrial Information Integration, 23, 100216.
18. Nascimento, N., Alencar, P., & Cowan, D. (2023). Self adaptive large language model (llm)-based multiagent systems. In 2023 ieee international conference on autonomic computing and self-organizing systems companion (acsosc) (pp. 104–109).
19. Niebur, E. (2007). Saliency map. Scholarpedia, 2(8). Pang, G., & Aggarwal, C. (2021). Toward explainable deep anomaly detection. In Proceedings of the 27th acm sigkdd conference on knowledge discovery & data mining (pp. 4056–4057).
20. Park, P., Marco, P. D., Shin, H., & Bang, J. (2019). Fault detection and diagnosis using combined autoencoder and long short-term memory network. Sensors, 19(21), 4612.
21. Qiu, H., Liu, Y., Subrahmanya, N. A., & Li, W. (2012). Granger causality for time-series anomaly detection. In 2012 ieee 12th international conference on data mining (pp. 1074–1079).
22. Ragab, A., El-Koujok, M., Poulin, B., Amazouz, M., & Yacout, S. (2018). Fault diagnosis in industrial chemical processes using interpretable patterns based on logical analysis of data. Expert Systems with Applications, 95, 368– 383.
23. Rane, N. L., Tawde, A., Choudhary, S. P., & Rane, J. (2023). Contribution and performance of chatgpt and other large language models (llm) for scientific and research advancements: a double-edged sword. International Research Journal of Modernization in Engineering Technology and Science, 5(10), 875–899.
24. Tian, Y., Du,W., & Qian, F. (2013). Fault detection and diagnosis for non-gaussian processes with periodic disturbance based on amra-ica. Industrial & Engineering Chemistry Research, 52(34), 12082–12107.
25. Wu, Q., Bansal, G., Zhang, J., Wu, Y., Zhang, S., Zhu, E., . . . Wang, C. (2023). Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155.
26. Xiao, Z., Kordon, A., & Sen, S. (2023). Fault detection and diagnosis in tennessee eastman process with deep autoencoder. In Annual conference of the phm society (Vol. 15).
27. Xu, H., Pang, G., Wang, Y., & Wang, Y. (2023). Deep isolation forest for anomaly detection. IEEE Transactions on Knowledge and Data Engineering.
28. Xue, F., Huang, H., Fu, Y., Feng, B., Yan, W., & Wang, T. (2021). Deep analysis net with causal embedding for coal-fired power plant fault detection and diagnosis (dance4cfdd) (Tech. Rep.). GE Global Research, Niskayuna, New York (United States).
29. Yang, F., Zhao, P., Wang, Z., Wang, L., Zhang, J., Garg, M., . . . Zhang, D. (2023). Empower large language model to perform better on industrial domain-specific question answering. arXiv preprint arXiv:2305.11541.
30. Yin, S., Ding, S. X., Haghani, A., Hao, H., & Zhang, P. (2012). A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark tennessee eastman process. Journal of process control, 22.
31. Zhang, C., Song, D., Chen, Y., Feng, X., Lumezanu, C., Cheng, W., . . . Chawla, N. V. (2019). A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data. In Proceedings of the aaai conference on artificial intelligence (Vol. 33, pp. 1409– 1416).
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.