A new approach for fault diagnosis with full-scope simulator based on state information imaging in nuclear power plant

In this paper, a new approach aimed at the Fault Diagnosis with Full-scope Simulator based on the State Information Imaging (FDFSSII) in NPP is proposed. The FDFSSII approach first constructs a series of gray-image which presents the operating transient (included normal and fault condition) according to the real time monitoring data. Furthermore, the Machine Learning (ML) technology is employed to achieve image feature extraction and classification by analyzing and learning from massive amounts of historical and synthetic gray-image data – the image feature is extracted by the Kernel Principal Component Analysis (KPCA) and classified by the designed classifiers in different learning methods. Finally, diagnosis effect is evaluated by the F1 score. The simulation result shows that the FDFSSII approach has achieved good effect for the fault diagnosis in NPP. Meanwhile, it simplifies the process of nuclear reactor with the large monitoring data and provides useful support information to the operators.