Imbalanced Fault Diagnosis of Bearing-Rotor System via Normalized Conditional Variational Auto-Encoder with Adaptive Focal Loss

Abstract

The distribution of mechanical system health data monitored in the industrial field is imbalanced mainly. To this end, this paper designs a new imbalanced fault diagnosis framework of the mechanical system based on Normalized Conditional Variational Auto-Encoder with Adaptive Focal Loss (NCVAE-AFL). The core of this diagnostic framework is to use the designed NCVAE model to enhance the data’s feature learning ability. The multi-layer sensitive feature vector of the data can be extracted, the generalization performance of the diagnostic model is further improved. Meanwhile, a new Adaptive Focus Loss (AFL) function is designed for NCVAE model, which focuses training on a few samples of health conditions that are difficult to classify and balance the diagnosis difficulty of samples of different categories. Finally, the double-span rotor-bearing system fault simulation experiment platform verifies the effectiveness and superiority of the proposed NCVAE-AFL algorithm and its diagnostic framework.