Bayesian network approach to fault diagnosis of a hydroelectric generation system. Issue 5 (21st June 2019)

• Record Type: Journal Article
• Authors: Xu, Beibei; Li, Huanhuan; Pang, Wentai; Chen, Diyi; Tian, Yu; Lei, Xiaohui; Gao, Xiang; Wu, Changzhi; Patelli, Edoardo
• Is Part Of: Energy science & engineering. Volume 7:Issue 5(2019)
• Page Start: 1669
• Page End: 1677
• Publication Date: 2019-06-21
• Subjects: Bayesian network -- expert system -- fault diagnosis -- hydroelectric generation system -- state evaluation; Energy industries -- Periodicals; Energy development -- Periodicals; Power resources -- Periodicals; 621.042
• DOI: 10.1002/ese3.383
• Languages: English
• ISSNs: 2050-0505

Abstract

Abstract: This study focuses on the fault diagnosis of a hydroelectric generation system with hydraulic‐mechanical‐electric structures. To achieve this analysis, a methodology combining Bayesian network approach and fault diagnosis expert system is presented, which enables the time‐based maintenance to transform to the condition‐based maintenance. First, fault types and the associated fault characteristics of the generation system are extensively analyzed to establish a precise Bayesian network. Then, the Noisy‐Or modeling approach is used to implement the fault diagnosis expert system, which not only reduces node computations without severe information loss but also eliminates the data dependency. Some typical applications are proposed to fully show the methodology capability of the fault diagnosis of the hydroelectric generation system. Abstract : Fault diagnosis of a hydroelectric generation system is a critical science and engineering problem to improve the safety of hydropower stations. To enable the risk quantification in the process of fault diagnosis, fault types and associated fault characteristics of a hydroelectric generation system are extensively analyzed to model a precise Bayesian Network. Noisy‐Or modeling approach is used for the implementation of fault diagnosis expert system, which not only reduces the computation of nodes probability without severe information loss but also eliminates the data dependency. A typical application is proposed to fully show the capability of the presented methodology of the HGS's fault diagnosis.