A review on methods and applications of artificial intelligence on Fault Detection and Diagnosis in nuclear power plants

Abstract

Nuclear power plants are critical facilities, which can generate a lot of energy through nuclear power and reduce environmental pollution. At the same time, should an accident occur at nuclear power plants, such as a nuclear leak, the consequences can be more severe than those associated with traditional power generation facilities. Therefore, Fault Detection and Diagnosis (FDD) has been an important technology in nuclear power plants. Traditional FDD methods mostly rely on the precise mathematical system model, which can be sometimes difficult to obtain in reality, and the detection accuracy of existing methods is thus limited. With the development of artificial intelligence (AI) technologies, FDD methods based on AI have been widely used. In this work, we make a systematic review of AI-based FDD methods, in conjunction with the introduction of the traditional FDD methods, and present the corresponding application scenarios of them. We hope that this work will help researchers incorporate more advanced AI models in nuclear power plants FDD and enlighten those interested in this field.