An Approach for Bearing Anomaly Detection and Fault Assessment Based on Data-driven Techniques
In the context of highly imbalanced sample data in bearing health monitoring,this article proposes an a-nomaly detection approach employing a generative adversarial network(GAN).The model's training necessitates solely the utilization of samples from normal states.Subsequently,an anomaly detection threshold is determined through a grid search method.Following this,a similarity assessment is conducted on the detected faults.Finally,the effectiveness of the method is validated using a publicly available dataset.Experimental results demonstrate that this approach achieves a detection accuracy of over 95%for various faults and can provide assessments of the severity of these faults.
Rolling bearingsImbalanced dataAnomaly detectionGenerative adversarial networks
万方数据
维普
