Implementation of fault isolation for molten salt reactor using PCA and contribution analysis

In order to implement the real-time monitoring of the system and equipment, principal component analysis (PCA) and contribution analysis are combined for fault isolation in this paper. The molten salt reactor (MSR) is taken as the research object. PCA and contribution analysis are applicable even in the case of lack of expert knowledge or small amount of data, with advantages in processing a large number of variables of complex systems. PCA is used for detecting faults. After an anomaly is detected, contribution analysis is used to diagnose the signal that causes the anomaly. The undetectable intervals of PCA models are performed quantitatively for obtaining better detection effect. Since the traditional contribution analysis method is prone to misjudgment due to smearing effect, the reconstruction-based contribution (RBC) is modified to improve the diagnostic accuracy. The three contribution analysis methods are compared and analyzed. Methods mentioned are evaluated through simulation tests and fault conditions in actual operation. Results demonstrate that the method proposed in this paper is accurate, effective and highly applicable. (C) 2022 Elsevier Ltd. All rights reserved.

Automated summary

This paper combines principal component analysis (PCA) and contribution analysis to achieve real-time monitoring and fault isolation of the system and equipment. Through the application on molten salt reactor (MSR), the advantages and applicability of these two analysis methods are demonstrated. With quantitative analysis and the modified contribution analysis method, the signal causing the anomaly can be diagnosed more accurately.