Monitoring and fault diagnosis of the steam generator system of a nuclear power plant using data-driven modeling and residual space analysis

Abstract

An advanced fault detection and isolation (FDI) technique was developed for the steam generator system of a typical pressurized water reactor (PWR) plant. The system characterization module used the group method of data handling method for modeling the interrelationship among the various process variables associated with a U-tube steam generator (UTSG). A principal component analysis algorithm was utilized for the generation of representative fault signatures. The accuracy of fault identification was quantified using normalized vector projections on to fault spaces. Other classical pattern classification methods were executed in parallel to increase the robustness of FDI results. Six typical static faults and one transient fault were successfully detected and isolated using a full-scope simulation of a four-loop PWR. The results demonstrate the implementation of the FDI algorithm for both instrument and actuator monitoring.