Signal validation based on PCSVR and EULM

In a nuclear power plant (NPP), periodic sensor calibrations are required to assure sensors are operating correctly. However, only a few faulty sensors are found to be calibrated. For the safe operation of an NPP and the reduction of unnecessary calibration, on-line calibration monitoring is needed. In the previous study, principal component-based auto-associative support vector regression (PCSVR) was proposed for the sensor signal validation of the NPP. In this paper the error uncertainty limit monitoring (EULM) is integrated with PCSVR for the failure detection. This paper describes the design of an AASVR-based sensor validation system for a power generation system. Response surface methodology (RSM) is employed to efficiently determine the optimal values of SVR hyperparameters. The residuals between the estimated signals and the measured signals are inputted to the EULM to detect whether the sensors are failed or not. The proposed sensor monitoring algorithm was verified through applications to the turbine 1^st chamber pressure in pressurized water reactor (PWR).