Principal Components Based Support Vector Regression Model for On-line Instrument Calibration Monitoring in Npps

For the past two decades, the nuclear industry has attempted to move toward a condition-based maintenance philosophy using new technologies developed to monitor the condition of plant equipment during operation. Specifically, techniques have been developed to monitor the condition of sensors and their associated instrument loops while a plant is operating. Traditionally, instruments must be recalibrated at each refueling outage in accordance with nuclear regulations. One concern with periodic calibrations is that only the sensor’s operating status is checked at every fuel outage, meaning that faulty sensors may remain undetected for periods of up to 24 months. Also, the traditional periodic maintenance method can lead to equipment damage, incorrect calibrations due to adjustments made under nonservice conditions, increased radiation exposure of maintenance personnel, and possibly, increased downtime. In fact, recent studies have shown that less than 5% of the process instruments are in a degraded condition that requires maintenance [13]. Therefore, plant operators are interested in finding ways to monitor sensor performance during operation and to manually calibrate only sensors that require correction. Hence, in this study we developed an OLM model for tracking instrument performance. Considerable research efforts have been devoted to the development of OLM algorithms. The application of artificial intelligence techniques to NPPs was investigated for instrument condition monitoring [1]. The Multivariate State Estimation Technique (MSET) was developed in the late 1980s [2], and Plant Evaluation and Analysis by Neural Operators (PEANO) was developed by researchers at the Halden Reactor Project in Norway [4]. The underlying In nuclear power plants (NPPs), periodic sensor calibrations are required to assure that sensors are operating correctly. By checking the sensor’s operating status at every fuel outage, faulty sensors may remain undetected for periods of up to 24 months. Moreover, typically, only a few faulty sensors are found to be calibrated. For the safe operation of NPP and the reduction of unnecessary calibration, on-line instrument calibration monitoring is needed. In this study, principal componentbased auto-associative support vector regression (PCSVR) using response surface methodology (RSM) is proposed for the sensor signal validation of NPPs. This paper describes the design of a PCSVR-based sensor validation system for a power generation system. RSM is employed to determine the optimal values of SVR hyperparameters and is compared to the genetic algorithm (GA). The proposed PCSVR model is confirmed with the actual plant data of Kori Nuclear Power Plant Unit 3 and is compared with the Auto-Associative support vector regression (AASVR) and the auto-associative neural network (AANN) model. The auto-sensitivity of AASVR is improved by around six times by using a PCA, resulting in good detection of sensor drift. Compared to AANN, accuracy and cross-sensitivity are better while the auto-sensitivity is almost the same. Meanwhile, the proposed RSM for the optimization of the PCSVR algorithm performs even better in terms of accuracy, auto-sensitivity, and averaged maximum error, except in averaged RMS error, and this method is much more time efficient compared to the conventional GA method.