Bearing Cross-Domain Fault Diagnosis Based on Wavelet Time-Frequency Map and Resnet Transfer Learning in Industrial IoT-Enabled Environments

Abstract

To overcome the difficulties faced by current bearing fault diagnosis methods in industrial applications, such as the difficulty in obtaining sufficient labeled real fault training samples and the subpar performance of cross-domain fault diagnosis due to data distribution deviation, a new bearing cross-domain fault diagnosis method based on wavelet time-frequency maps and Resnet transfer learning (CDF-WTI-RTL) is proposed.In the context of the Industrial Internet of Things (IIoT) and Industry 5.0, real-time condition monitoring and intelligent predictive maintenance have become critical for ensuring manufacturing system resilience and sustainability. First, raw vibration signals are processed using continuous wavelet transform to obtain two-dimensional time-frequency maps. Second, a Resnet network adapted for bearing fault diagnosis is constructed to autonomously mine deep features from source and target domains. A random forest classifier is then employed to build a cross-domain fault pattern recognition classifier. Experimental analysis of training samples using two different bearing fault datasets shows that the accuracy of the CDF-WTI-RTL model reaches 98.38% and 91.5% with unbalanced training samples respectively, notably surpassing the other 5 comparative models. The results demonstrate that the proposed method can be effectively deployed in IIoT architectures for reliable, cross-condition bearing fault diagnosis.