Multisensor Fused Fault Diagnosis for Rotation Machinery Based on Supervised Second-Order Tensor Locality Preserving Projection and Weighted k-Nearest Neighbor Classifier under Assembled Matrix Distance Metric

Abstract

In order to sufficiently capture the useful fault-related information available in the multiple vibration sensors used in rotation machinery, while concurrently avoiding the introduction of the limitation of dimensionality, a new fault diagnosis method for rotation machinery based on supervised second-order tensor locality preserving projection (SSTLPP) and weighted k-nearest neighbor classifier (WKNNC) with an assembled matrix distance metric (AMDM) is presented. Second-order tensor representation of multisensor fused conditional features is employed to replace the prevailing vector description of features from a single sensor. Then, an SSTLPP algorithm under AMDM (SSTLPP-AMDM) is presented to realize dimensional reduction of original high-dimensional feature tensor. Compared with classical second-order tensor locality preserving projection (STLPP), the SSTLPP-AMDM algorithm not only considers both local neighbor information and class label information but also replaces the existing Frobenius distance measure with AMDM for construction of the similarity weighting matrix. Finally, the obtained low-dimensional feature tensor is input into WKNNC with AMDM to implement the fault diagnosis of the rotation machinery. A fault diagnosis experiment is performed for a gearbox which demonstrates that the second-order tensor formed multisensor fused fault data has good results for multisensor fusion fault diagnosis and the formulated fault diagnosis method can effectively improve diagnostic accuracy.