212 / 2024-09-02 10:05:01

Application of ResNet CNN Model in Rolling Bearing Fault Diagnosis

Rolling bearing, Fault diagnosis, ResNet CNN, Random forest.

The diagnosis of rolling bearing faults is crucial for ensuring the safe operation of rotating machinery equipment. Based on the open-source dataset provided by Case Western Reserve University's Bearing Data Center, ResNet's CNN model was used to diagnose the fault status of normal bearings as well as bearings with faults in the inner, outer, and rolling elements, and compared with two other machine learning models, Random Forest and CNN. The research results indicate that the ResNet CNN model outperforms the other two methods in key performance indicators such as accuracy and recall, demonstrating its effectiveness and superiority in bearing fault diagnosis.