Application of Prediction Monitoring and Diagnostic System to Plant Performance Evaluation
高瀬 健太郎 Kentaro TAKASE 林 司 Tsukasa HAYASHI 藤岡 隆 Takashi FUJIOKA 山本 敬之 Takayuki YAMAMOTO
Big Data AnalysisMaintenance PlanningMaintenance RecordMultivariate AnalysisSystem Performance Indicator
We have developed the prediction monitoring and diagnostic system for the purpose of the early detection of the abnormal behavior of the complicated system like a nuclear power plant. Furthermore, the techniques for the modeling of the relationships between sensors are applied to evaluate the system performance. The developed method is applied to the primary loop recirculation (PLR) pumps and the system performance indicator is calculated. The results are compared with the maintenance record of the PLR pumps and the good agreement is achieved. The method is further developed to utilize the big data more efficiently. For the prediction of the main target parameter, the combination of three parameters are used. All combinations from the given parameters are tested and the best combination is selected. The results are much more improved. These results shows the developed method is helpful for the maintenance planning.