TY - GEN
T1 - AI-Driven Reconstruction and Optimization of Teaching Model for Fault Detection and Diagnosis in Industrial Safety Production
AU - Zhang, Ming Qing
AU - Xu, Yuan
AU - He, Yan Lin
AU - Zhang, Yang
AU - Song, Xiao Lu
N1 - Publisher Copyright:
© 2025 Copyright held by the owner/author(s).
PY - 2025/11/30
Y1 - 2025/11/30
N2 - In industrial process, fault detection and diagnosis (FDD) are critical to ensure system safety and reliability. However, the increasing complexity of operating environments and the growth in demand bring some challenges to FDD education. In this study, we analyze FDD methods based on multivariate statistical learning, deep learning, and the limitations on skill training. To bridge this gap, we propose a framework for AI-driven FDD education. The framework consists of a progressive three-tier teaching system built around theoretical learning, virtual simulation, and practical applications. On this foundation, a spiral competency development path, which includes FDD methods, digital twin verification, and physical system commissioning, is designed to enhance students' practical skills. The study showed that the above teaching model not only improved the understanding of industrial fault analysis, but also demonstrated efficiency in developing engineering practice and independent learning skills.
AB - In industrial process, fault detection and diagnosis (FDD) are critical to ensure system safety and reliability. However, the increasing complexity of operating environments and the growth in demand bring some challenges to FDD education. In this study, we analyze FDD methods based on multivariate statistical learning, deep learning, and the limitations on skill training. To bridge this gap, we propose a framework for AI-driven FDD education. The framework consists of a progressive three-tier teaching system built around theoretical learning, virtual simulation, and practical applications. On this foundation, a spiral competency development path, which includes FDD methods, digital twin verification, and physical system commissioning, is designed to enhance students' practical skills. The study showed that the above teaching model not only improved the understanding of industrial fault analysis, but also demonstrated efficiency in developing engineering practice and independent learning skills.
KW - Teaching model optimization
KW - artificial intelligence
KW - digital twin
KW - fault diagnosis
KW - industrial system safety
UR - https://www.scopus.com/pages/publications/105025521450
U2 - 10.1145/3764206.3764241
DO - 10.1145/3764206.3764241
M3 - Conference contribution
AN - SCOPUS:105025521450
T3 - Proceedings of The 2nd International Conference on Intelligent Education and Computer Technology, IECT 2025
SP - 234
EP - 239
BT - Proceedings of The 2nd International Conference on Intelligent Education and Computer Technology, IECT 2025
PB - Association for Computing Machinery, Inc
T2 - 2nd International Conference on Intelligent Education and Computer Technology, IECT 2025
Y2 - 27 June 2025 through 29 June 2025
ER -