A novel time–frequency Transformer based on self–attention mechanism and its application in fault diagnosis of rolling bearings. (1st April 2022)

• Record Type: Journal Article
• Authors: Ding, Yifei; Jia, Minping; Miao, Qiuhua; Cao, Yudong
• Is Part Of: Mechanical systems and signal processing. Volume 168(2022)
• Publication Date: 2022-04-01
• Subjects: Fault diagnosis -- Deep learning -- Transformer -- Self–attention mechanism -- Rolling bearings; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2021.108616
• Languages: English
• ISSNs: 0888-3270

Abstract

Abstract: The scope of data-driven fault diagnosis models is greatly extended through deep learning (DL). However, the classical convolution and recurrent structure have their defects in computational efficiency and feature representation, while the latest Transformer architecture based on attention mechanism has not yet been applied in this field. To solve these problems, we propose a novel time–frequency Transformer (TFT) model inspired by the massive success of vanilla Transformer in sequence processing. Specially, we design a fresh tokenizer and encoder module to extract effective abstractions from the time–frequency representation (TFR) of vibration signals. On this basis, a new end-to-end fault diagnosis framework based on time–frequency Transformer is presented in this paper. Through the case studies on bearing experimental datasets, we construct the optimal Transformer structure and verify its fault diagnosis performance. The superiority of the proposed method is demonstrated in comparison with the benchmark models and other state-of-the-art methods. Highlights: A novel model named time–frequency Transformer (TFT) is proposed. A fresh tokenizer and encoder module are designed to extract effective abstractions. A new end-to-end fault diagnosis framework based on TFT is presented. The proposed method shows superiority comparing to other state-of-the-art methods.