A new weak fault diagnosis method b

A new weak fault diagnosis method based on feature reduction with Supervised Orthogonal Local FisherDiscriminant Analysis (SOLFDA) is proposed. In this method, the Shannon mutual information (SMI)between all samples and training samples is combined into SMI feature sets to represent the mutualdependence of samples as incipient fault features. Then, SOLFDA is proposed to compress the highdimensionalSMI fault feature sets of testing and training samples into low-dimensional eigenvectorswith clearer clustering. Finally, Optimized Evidence-Theoretic k-Nearest Neighbor Classifier (OET-KNNC)is introduced to implement weak failure recognition for low-dimensional eigenvectors. Under thesupervision of class labels, SOLFDA achieves good discrimination property by maximizing the betweenmanifolddivergence and minimizing the within-manifold divergence. Meanwhile, an orthogonalityconstraint on SOLFDA can make the output sparse features statistically uncorrelated. Therefore, SMIfeature set combining SOLFDA is able to extract the essential but weak fault features of rotatingmachinery effectively, compared with popular signal processing techniques and unsupervised dimensionreduction methods. The weak fault diagnosis example on deep groove