Fault diagnosis method based on convolutional attention mechanism and ResNet34
TL;DR
A fault-diagnosis method that integrates a least-squares-loss and weight-normalization deep convolutional generative adversarial network (LW-DCGAN) with a convolutional-attention-enhanced 34-layer residual network (C-ResNet34) to improve fault-feature extraction and demonstrate the effectiveness of the proposed method.
Abstract
Fault diagnosis of transmission gears in the cutting drive of a coal-mining shearer is challenged by scarce field fault data and the production interruptions associated with drive failures. To alleviate performance degradation caused by blindly increasing network depth and to improve fault-feature extraction when real training data are limited, this study proposes a fault-diagnosis method that integrates a least-squares-loss and weight-normalization deep convolutional generative adversarial network (LW-DCGAN) with a convolutional-attention-enhanced 34-layer residual network (C-ResNet34). First, a particle-swarm-optimized symmetrized dot pattern (PS-SDP) transformation is used to convert vibration signals into image representations. The LW-DCGAN is then used to augment only the PS-SDP training images. Next, a convolutional attention mechanism is incorporated into the residual blocks of ResNet34 to construct C-ResNet34 and improve fault-feature extraction. The workflow was evaluated through image-transformation, multichannel-fusion, training-set-augmentation, and classifier-comparison experiments on a Drivetrain Diagnostics Simulator-based simulated shearer dataset and the public University of Connecticut gearbox dataset. Experimental results demonstrate the effectiveness of the proposed method.