Data-Driven Machine Learning for Fault Detection and Diagnosis in Nuclear Power Plants: A Review

Data-driven machine learning (DDML) methods for the fault diagnosis and detection (FDD) in nuclear power plant (NPP) are of emerging interest recent years. However, there still lacks research on comprehensive reviewing state-of-the-art progress DDML FDD NPP. In this review, classifications, principles, characteristics firstly introduced, which include supervised type, unsupervised so on. Then, latest applications FDD, consist reactor system, component, condition monitoring illustrated, can better predict NPP behaviors. Lastly, future development is concluded.