Survey on Foundation Models for Prognostics and Health Management in Industrial Cyber-Physical Systems
- 10 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Cyber-Physical Systems
- Vol. 2, 264-280
Abstract
Industrial Cyber-Physical Systems (ICPS) integrating disciplines such as computer science, communication technology, and engineering, have become a crucial component of modern manufacturing and industry. However, ICPS faces numerous challenges during long-term operation, including equipment faults, performance degradation, and security threats, etc. To achieve efficient maintenance and management, prognostics and health management (PHM) has been widely applied in the critical tasks of ICPS such as fault prediction, health monitoring, and maintenance decision-making. The emergence of large-scale foundation models (LFMs) like BERT and GPT marks a significant advancement in artificial intelligence (AI) technology, demonstrating substantial application potential in multiple fields. The accumulation of AI technology, rapid development of LFMs, and the abundance of industrial data and industrial process knowledge provide the foundational conditions for the construction and advancement of industrial LFMs. However, there is currently a lack of consensus on applying LFMs of PHM in ICPS, necessitating a systematic review and roadmap to clarify future development directions. To bridge this gap, this survey provides a comprehensive survey and understanding of the recent advances in LFMs of PHM in ICPS. It provides valuable references for decision makers and researchers in the industry, and helps to further improve the reliability, availability and safety of ICPS.Keywords
All Related Versions
Funding Information
- National Science and Technology Major Project (2022ZD0119900)
- National Natural Science Foundation of China (62206199, U2141234)
- Shanghai Science and Technology Program (22015810300)
- Hainan Province Science and Technology Special Fund (ZDYF2024GXJS003)
- Young Elite Scientist Sponsorship Program (YESS20220409)
- Alexander von Humboldt-Stiftung (1226831)
This publication has 99 references indexed in Scilit:
- Integrating active learning and semi-supervised learning for improved data-driven HVAC fault diagnosis performanceApplied Energy, 2023
- A new convolutional dual-channel Transformer network with time window concatenation for remaining useful life prediction of rolling bearingsAdvanced Engineering Informatics, 2023
- Vibration and current dataset of three-phase permanent magnet synchronous motors with stator faultsData in Brief, 2023
- You can get smaller: A lightweight self-activation convolution unit modified by transformer for fault diagnosisAdvanced Engineering Informatics, 2023
- A review on fault detection and diagnosis techniques: basics and beyondArtificial Intelligence Review, 2020
- Potential, challenges and future directions for deep learning in prognostics and health management applicationsEngineering Applications of Artificial Intelligence, 2020
- A novel study for the estimation of crack propagation in concrete using machine learning algorithmsConstruction and Building Materials, 2019
- Bearing vibration data collected under time-varying rotational speed conditionsData in Brief, 2018
- Fault tree analysis: A survey of the state-of-the-art in modeling, analysis and toolsComputer Science Review, 2015
- Semantic Web based innovative design knowledge modeling for collaborative designExpert Systems with Applications, 2012