Bearing Fault Detection by a Novel Condition-Monitoring Scheme Based on Statistical-Time Features and Neural Networks

TLDR

Bearing degradation is the most common fault source in electrical machines, and developing diagnostics that address both local and distributed bearing defects is a key concern, with statistical‑time feature methods proving powerful and promising. The study introduces a novel monitoring scheme to diagnose bearing faults. The scheme analyzes key statistical‑time vibration features, compresses and visualizes them with a curvilinear component analysis manifold, and classifies bearing conditions using a hierarchical neural network. Experimental results across varied operating conditions confirm that the scheme accurately interprets underlying physical phenomena and effectively diagnoses bearing faults.

Abstract

Bearing degradation is the most common source of faults in electrical machines. In this context, this work presents a novel monitoring scheme applied to diagnose bearing faults. Apart from detecting local defects, i.e., single-point ball and raceway faults, it takes also into account the detection of distributed defects, such as roughness. The development of diagnosis methodologies considering both kinds of bearing faults is, nowadays, subject of concern in fault diagnosis of electrical machines. First, the method analyzes the most significant statistical-time features calculated from vibration signal. Then, it uses a variant of the curvilinear component analysis, a nonlinear manifold learning technique, for compression and visualization of the feature behavior. It allows interpreting the underlying physical phenomenon. This technique has demonstrated to be a very powerful and promising tool in the diagnosis area. Finally, a hierarchical neural network structure is used to perform the classification stage. The effectiveness of this condition-monitoring scheme has been verified by experimental results obtained from different operating conditions.