LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attention

Abstract

In recent studies, Transformer collaborated with convolution neural network (CNN) have made certain progress in the field of intelligent fault diagnosis by leveraging their respective advantages of global and local feature extraction. However, the multihead self-attention block used by Transformer and cross-channel convolution mechanism existing in CNN would make the collaborative models overly complex, leading to higher hardware requirements and limited industrial application scenarios. Therefore, this paper proposes a lightweight fault diagnosis framework called LiConvFormer to address the aforementioned challenges. First, a separable multiscale convolution block is designed to extract multilocal receptive field features of vibration signals and greatly reduce the learning parameters and computations. Second, a broadcast self-attention block is developed to capture critical fine-grained features within the signal’s global scope, while avoiding cumbersome operations such as matrix multiplication and multidimensional exponentiation. Experimental results on three mechanical systems show that the proposed framework can accommodate advantages of lightweight and robustness compared to the recent Transformer and CNN-based fault diagnosis methods; moreover, the superiority of the above two blocks is also verified. The code library is available at: https://github.com/yanshen0210/LiConvFormer-a-lightweight-fault-diagnosis-framework.