基于移动窗核主成分分析的核电厂主泵故障检测  

Fault Detection for Reactor Coolant Pump Based on Moving Window Kernel Principal Component Analysis

作　　者：张秀春[1,2,3,4] 夏虹 刘永康[5] 朱少民 刘洁 张汲宇 Zhang Xiuchun;Xia Hong;Liu Yongkang;Zhu Shaomin;Liu Jie;Zhang Jiyu(Key Laboratory of Nuclear Safety and Advanced Nuclear Energy Technology,Ministry of Industry and Information Technology,Harbin Engineering University,Harbin,150001,China;Fundamental Science on Nuclear Safety and Simulation Technology Laboratory,Harbin Engineering University,Harbin,150001,China;Suzhou Nuclear Power Research Institute Co.,Ltd.,Suzhou,Jiangsu,215000,China;National Engineering Research Center for Nuclear Power Plant Safety&Reliability,Suzhou,Jiangsu,215000,China;China Nuclear Power Technology Research Institute Co.,Ltd.,Shenzhen,Guangdong,518000,China)

机构地区：[1]哈尔滨工程大学核安全与先进核能技术工信部重点实验室,哈尔滨150001 [2]哈尔滨工程大学核安全与仿真技术国防重点学科实验室,哈尔滨150001 [3]苏州热工研究院有限公司,江苏苏州215000 [4]国家核电厂安全及可靠性工程技术研究中心,江苏苏州215000 [5]中广核研究院有限公司,广东深圳518000

出　　处：《核动力工程》2024年第3期234-240,共7页Nuclear Power Engineering

基　　金：国家自然科学基金项目(U21B2083)。

摘　　要：由于部件性能衰退、工况变化等因素影响,核动力装置在运行过程中会表现出明显的时变性,进而造成故障检测模型失效。为了改善传统故障检测方法在时变工业过程中的性能和在役适应性,基于核主成分分析(KPCA)和移动窗技术,提出了一种用于核动力装置的长时故障检测方法。该方法通过移动窗技术可实现KPCA故障检测模型的自动更新,从而解决检测过程中信号的时变性问题。将移动窗KPCA方法应用于某核电厂主泵的长时监测中,结果表明,主泵在正常和异常状态下,移动窗KPCA方法在故障检测率(FDR)、误报率(FAR)等指标方面均表现出了良好的性能。Due to the influence of component performance decline and operation condition change,nuclear power plants(NPPs)show obvious time variability during operation,which leads to the failure of fault detection model.In order to improve the performance and in-service adaptability of traditional fault detection methods in time-varying industrial processes,this paper proposes a longterm fault detection strategy for NPPs based on kernel principal component analysis(KPCA)and moving window.In this method,the KPCA fault detection model is automatically updated by moving window technology,which solves the time-varying problem of signals in the detection process.The moving window KPCA method is applied to the long-term monitoring of the reactor coolant pump in a nuclear power plant.The results show that the moving window KPCA method has good performance in fault detection rate and false alarm rate under normal and abnormal conditions.

关 键 词：核动力装置 核主成分分析(KPCA) 移动窗 时变过程 故障检测 

分 类 号：TL363[核科学技术—核技术及应用]