An Enhanced Sparse Filtering Fusion Method for Bearing Fault Diagnosis

Sparse filtering and its variants have been used in the field of weak feature extraction of bearing. However, the fault features extracted by the current sparse filtering methods are still subject to contamination of strong noises. Therefore, an enhanced sparse filtering fusion method is proposed for bearing fault diagnosis in this study. Specifically, the proposed method is conducted through the following steps. First, extract the fault features under background noise by an enhanced sparse filtering. Second, Gini index is used to select the sparser fault features in the extracted fault features for constructing a multi-dimensional enhanced fault feature fusion source. Third, obtain the intrinsic manifolds of the multi-dimensional enhanced fault feature fusion source by the manifold learning algorithm. Finally, the intrinsic manifolds are weighted to recover the fault-related transients. Analysis and comparison results of the experiment data from defective bearings indicates that the proposed method shows a prominent superiority in bearing fault diagnosis.

I. Introduction

As one of the most widely used mechanical parts, the bearing plays an important role in carrying load and reducing friction loss in mechanical systems [1]. However, the bearing often works in a harsh environment with variable loads. Thus, the bearing is also one of the most vulnerable components in mechanical equipment [2]. If the bearing fault cannot be diagnosed as soon as possible, it may lead to immeasurable accidents. However, in the early stage of bearing fault, due to the influence of background noise and signal attenuation, the signal-to-noise ratio (SNR) of the collected vibration signal is low. How to extract weak fault feature from strong background noise and conduct accurate fault diagnosis for bearings have become a hotspot and difficulty in the field of fault diagnosis of rotating machinery [3].