Transfer Learning Enabled Bearing Fault Detection Methods Based on Image Representations of Single-Dimensional Signals

Bearings are vital components in rotating machinery. Undetected bearing faults may result not only in financial loss, but also in the loss of lives. Hence, there exists an abundance of studies working on the early detection of bearing faults. The rising use of deep learning in recent years increased the number of imaging types/neural network architectures used for bearing fault classification, making it challenging to choose the most suitable 2-D imaging method and neural network. This study aims to address this challenge, by sharing the results of the training of eighteen imaging methods with four different networks using the same vibration data and training metrics. To further strengthen the results, the validation dataset size was taken as five times the training dataset size. The best results obtained is 99.89% accuracy by using Scattergram Filter Bank 1 as the image input, and ResNet-50 as the network for training. Prior to our work, Scattergram images have never been used for bearing fault classification. Ten out of 72 methods used in this work resulted in accuracies higher than 99.5%.

Automated summary

Bearings are critical components in rotating machinery, and undetected faults can result in financial and human losses. This study addresses the challenge of choosing the most suitable 2-D imaging method and neural network for early detection of bearing faults. By training eighteen imaging methods with four different networks using the same vibration data and training metrics, the study identifies Scattergram Filter Bank 1 as the best image input and ResNet-50 as the most effective network, achieving an accuracy of 99.89%. Prior to this research, Scattergram images have never been used for bearing fault classification. Ten out of 72 methods used in this study achieved accuracies higher than 99.5%.