The best way to conference proceedings by Francis Academic Press

Web of Proceedings - Francis Academic Press
Web of Proceedings - Francis Academic Press

Research on Fault Diagnosis Method of Coolant System in Nuclear Power Plant

Download as PDF

DOI: 10.25236/AISCT.2019.090

Author(s)

Qiu Pinda, Ye Liqiang

Corresponding Author

Qiu Pinda

Abstract

Coolant system is one of the most important systems in nuclear power plant. The safety and stability of the system is the basis of the stable operation of the whole nuclear power unit. Firstly, the typical fault characteristics of the system are introduced. In order to improve the accuracy of fault diagnosis, an expert diagnosis method based on sparse coding is proposed by fusing the sparse coding fault diagnosis results with the expert system. The results show that the method can extract fault feature information effectively. The accuracy of expert system for fault diagnosis of coolant system is 87.5%. After sparse coding fusion, the accuracy of fault diagnosis is increased to 94.4%. The validity and reliability of the system are verified, which can provide reference for safe operation and decision-making of nuclear power plant.

Keywords

Coolant system; Fault diagnosis; Expert system; Sparse coding