A sparse fault degradation oriented fisher discriminant analysis (FDFDA) algorithm for faulty variable isolation and its industrial application

摘要

In a fault process, the variables may be influenced differently. In order to improve the diagnosis performance, it is an important issue to isolate those significant faulty variables that cover informative fault effects. However, those variables are selected one by one and their correlations are not considered in the previous work. As sparse-relevant methods can automatically and efficiently isolate significant correlated variables, it is natural to consider applying the criteria of sparsity to separate the significantly influenced faulty variables and analyze them by specific methods. First, the sparse version of the fault degradation oriented Fisher discriminant analysis (FDFDA) algorithm is proposed to produce informative discriminant directions with sparse loadings. Subsequently, a faulty variable selection strategy is proposed based on the sparse FDFDA algorithm to select significantly influenced faulty variables. By iteratively isolating correlated variables along each sparse fault direction, all the faulty variables can be automatically selected until the left fault data and normal data share the similar characteristics. Therefore, the whole measurement variables can be divided into faulty variable set and normal variable set. Then different fault diagnosis models can be developed according to their different characteristics for each fault class. For online application, a probabilistic fault diagnosis strategy is proposed to determine the fault cause of the new sample by the largest synthetic probability that integrates the diagnosis results of two variable sets. The performance of the proposed fault diagnosis method is illustrated using the data from the cut-made process of cigarette.