Fault Diagnosis of Bearings and Gears Based on LiteNet With Feature Aggregation

Significant progress has been made in the current fault diagnosis algorithms. However, they do not consider computational resources and require expensive equipment to complete the training of the models. To immediately complete model training and obtain higher accuracy rates using cheaper equipment, reduce the equipment cost in the industry, and build a bridge for industrial fault diagnosis with neural networks, this article proposes a convolutional neural network (CNN)-based architecture that uses a small number of computational resources with high accuracy. Simultaneously, a loss function is proposed that can further improve the accuracy of the network model without consuming too many computational resources. According to experimental comparisons, the proposed technique has clear advantages in terms of accuracy, computational resources, training time, and stability.

Automated summary

Significant progress has been made in fault diagnosis algorithms, but they do not consider computational resources and require expensive equipment. To address this issue, this article proposes a CNN-based architecture that uses fewer computational resources and achieves higher accuracy. A loss function is also introduced to improve the accuracy without consuming too many resources. Experimental comparisons demonstrate the clear advantages of the proposed technique in terms of accuracy, resources, training time, and stability.