提出了空调系统传感器故障检测、故障识别、故障重构的主成分分析方法。主成分分析法将测量空间分为主成分子空间和残差子空间。SPE 指数和SVI 指数分别用来检测和识别故障。沿着故障方向,测量数据逐步逼近主成分子空间可以实现数据的重构。通过对空调监测系统的传感器故障检测与诊断结果展示出PCA 方法具有良好的故障检测、识别和重构能力。关键词:主成分分析法;传感器故障;故障检测与诊断;空调系统Abstract :The principal component analysis(PCA) approach for sensor fault detection ,identification and reconstruction in HVAC system is presented. The PCA approach partitions the measurement space into principal component subspace (PCS) and residual subspace (RS) . The SPE index and the SVI index is used for fault detection and fault identification , respectively. Fault can be reconstructed by sliding the mea2 sure to principal component subspace along the direction of fault. It shows that the PCA approach has good ability of fault detection , fault identification and fault reconstructionthough employing in HVAC monitoring and controlling sys2tem.Key words : principal component analysis ( PCA) ; sensor fault ;fault detection and diagnosis ;HVAC sys2 tem
猜您喜欢
评论