Fault Diagnosis of Linear Guide Rails Based on SSTG Combined with CA-DenseNet

Abstract

Monitoring the status of linear guide rails is essential because they are important components in linear motion mechanical production. Thus, this paper proposes a new method of conducting the fault diagnosis of linear guide rails. First, synchrosqueezing transform (SST) combined with Gaussian high-pass filter, termed as SSTG, is proposed to process vibration signals of linear guide rails and obtain time-frequency images, thus helping realize fault feature visual enhancement. Next, the coordinate attention (CA) mechanism is introduced to promote the DenseNet model and obtain the CA-DenseNet deep learning framework, thus realizing accurate fault classification. Comparison experiments with other methods reveal that the proposed method has a high classification accuracy of up to 95.0%. The experimental results further demonstrate the effectiveness and robustness of the proposed method for the fault diagnosis of linear guide rails.