Intelligent Fault Diagnosis Method for Shearer Rocker Gear Based on Swin Transformer and Multiscale Convolution Parallel Integration

In the harsh underground environment, the transmission gear in the rocker arm of the shearer is susceptible to impact load, frequently leading to failures that result in economic losses or casualties. Therefore, real-time and accurate gear fault diagnosis is crucial. Existing diagnostic models struggle with insufficient feature extraction and low diagnostic accuracy when addressing nonlinear, nonsmooth signals with strong noise in this environment. Therefore, an innovative parallel integration model of Swin Transformer and multiscale convolution is proposed to extract both global and local features under different fault modes and noise conditions. A spatial interaction block (SIB) is introduced into the Swin Transformer branch to enhance global information acquisition. In multiscale convolutional neural network (CNN) branches, depthwise separable convolutions with different expansion coefficients are utilized for multiscale extraction of local features to reduce computational complexity. Considering the differences between global and local features, a feature interaction module (FIM) is added between the two branches to realize the interaction between local and global features, considerably improving the model diagnosis performance. Furthermore, to meet the high real-time diagnosis requirements, a cloud-edge collaboration (CEC) framework is designed to realize the timely alarm of gear faults through the efficient collaboration between edge nodes and the industrial cloud platform. Using the vibration data collected from the rocker arm loading test bed of Taizhong Coal Machinery and the gear data provided by Southeast University for validation, the results show that the diagnostic precision of the proposed method can reach up to 99.55%. Even when the signal-to-noise ratio (SNR) is −2 db, the accuracy is still 93.67%, which is superior to other advanced comparison models, and significantly reduces the completion time of fault diagnosis tasks, and has strong anti-noise and real-time diagnosis capabilities.

I. Introduction

Shearers are key equipment for modern fully mechanized coal faces, featuring complex mechanical structures and numerous components [1]. Among these, the rocker arm is an essential component that operates in harsh underground environments for extended periods. It is easily affected by uncontrollable factors, such as impact load, leading to frequent failures and safety accidents. Based on statistics, rocker arm failures mainly originate from gears in the transmission system [2]. Under the influence of installation error, fatigue stress, coal dust corrosion, and other factors, pitting corrosion, tooth breakage, and wear will occur, resulting in economic losses and even safety accidents in serious cases. Therefore, developing an efficient, intelligent fault diagnosis method for shearer rocker arm gear is crucial. These challenges are further exacerbated by the noisy environment in underground coal mines, so it is crucial to develop an efficient and intelligent fault diagnosis method for shearer rocker arm gear.