Rolling Bearing Fault Diagnosis Under Different Severity Based on Statistics Detection Index and Canonical Discriminant Analysis

Bearing failures are the most frequent causes of breakdowns in rotating machinery. Different levels severity these exhibit distinct fault characteristics vibration signal. This paper presents a bearing diagnosis method that considers different levels, involving selection statistics detection index symptom parameter and application canonical discriminant analysis (CDA). Initially, kurtosis is employed to detect abnormalities bearing. Subsequently, statistical theory utilized extract efficient parameters from time domain frequency signals. As method, CDA can discriminate between signals by maximizing between-group difference minimizing inter-group difference. By analyzing distribution scores, faults be intuitively diagnosed. The proposed validated using obtained an experimental bench with three conditions (normal, inner race fault, outer fault) exhibiting varying levels. results demonstrate effectiveness feasibility diagnosing under