Data-Driven Fault Diagnosis Method Based on Second-Order Time-Reassigned Multisynchrosqueezing Transform and Evenly Mini-Batch Training

Abstract

To promote the progress of fault diagnosis system, this study proposes an intelligent and effective fault diagnosis algorithm based on data-driven. Firstly, we propose a new time-frequency analysis method named second-order time-reassigned multisynchrosqueezing transform (STMSST) based on Gaussian-modulated linear group delay (GLGD) model to deal with the vibration signals of fault object for obtaining time-frequency images with high resolution. Then, an improved training method named evenly mini-batch training method is combined with convolutional neural network (CNN) to train and learn fault features from those obtained time-frequency images. Further, the proposed fault diagnosis algorithm is tested on the Case Western Reserve University (CWRU) bearing dataset and the Machinery Failure Prevention Technology (MFPT) Society dataset, respectively, and the experimental results indicate that the feature representation and training effect in our method is superior to state-of-the-art fault diagnosis methods. Finally, the proposed method is applied on the loudspeaker pure-tone detection dataset, which achieves the loudspeaker anomaly diagnosis, and the diagnosis result has verified that the method can meet the needs of practical engineering.