基于故障诊断性能优化的主元个数选取方法

主元分析 (PCA)作为一种有效的多元统计监测方法，在化工过程的产品质量控制与故障诊断等方面得到广泛应用.其中主元个数作为PCA监测模型的关键参数，其选取直接决定了PCA的故障诊断性能.传统的主元个数选取方法主观性较大，且一般不能考虑故障诊断的要求.通过对主元空间和残差空间中临界故障幅值的分析，提出一种基于故障检测与识别性能优化的主元个数选取方法.并且能够对故障的检测类型、幅值等重要信息进行预测和估计.通过对双效蒸发过程的仿真故障检测，证实了该主元个数选取方法的上述优点.

SELECTION OF NUMBER OF PRINCIPAL COMPONENTS BASED ON FAULT DIAGNOSING PERFORMANCE OPTIMIZATION

Principal component analysis (PCA) is a powerful tool in chemical process monitoring and product quality control. The number of principal components (PCs) is the essential parameter of PCA and ultimately determines the performance of this useful statistical method. Traditional selection methods are very subjective due to the monotonically increasing or decreasing indices they adopt. By exploring the minimum detectable fault magnitudes in the PCs space and residual space simultaneously, a new index of optimal critical fault magnitude (OCFM) was introduced and the number of PCs was selected by optimizing a function of the OCFM. The proposed method could incorporate the PCA fault diagnosing performance with the PCs selection procedure effectively, and has the advantages of forecasting PCA detection behavior of a specific fault and estimating the fault magnitude. The acquired results were then illustrated and verified by monitoring a simulated double-effect evaporator.