3DSMDA-Net: An improved 3DCNN with separable structure and multi-dimensional attention for welding status recognition. (January 2022)

• Record Type: Journal Article
• Authors: Liu, Tianyuan; Wang, Jiacheng; Huang, Xiaodi; Lu, Yuqian; Bao, Jinsong
• Is Part Of: Journal of manufacturing systems. Volume 62(2022)
• Page Start: 811
• Page End: 822
• Publication Date: 2022-01
• Subjects: Arc welding -- Status recognition -- Deep learning -- Time sequence images -- 3DCNN -- Model lightweight -- Multi-dimensional attention; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2021.01.017
• Languages: English
• ISSNs: 0278-6125

Abstract

Highlights: We make use of the time sequence information into deep learning-based welding status recognition to enhance accuracy. We propose a method of 3DCNN-oriented convolution kernel separation as a lightweight time sequence model. We propose multi-dimensional attention mechanism for reducing the loss of accuracy caused by the separation operation. Identification of globule transition mode and the types of molten pool. Abstract: The vision-based welding status recognition (WSR) provides a basis for online welding quality control. Due to the severe arc and fume interference in the welding area and limited computational resources at the welding edge nodes, it becomes a challenge to mine the most discriminative feature contained in welding images by using a lightweight model. In this paper, we propose an improved three-dimensional convolutional neural network (3DCNN) with separable structure and multi-dimensional attention (3DSMDA-Net) for WSR. The proposed 3DSMDA-Net uses 3DCNN to adaptively extract abstract spatiotemporal features in a welding process and then leverages such time sequence information to improve the recognition accuracy of WSR. In addition, we decompose the classical 3D convolution into depthwise convolution and pointwise convolution to produce a lightweight model. A multi-dimensional attention mechanism is further proposed to compensate for the loss of accuracy caused by the separation operation. The results of experiments reveal that the proposed method reduces the model size to 1/7 of the classical 3DCNN without sacrificing accuracy. The comparison experiment results have indicated that the accuracy of the proposed method is more accurate and noise-resistant than that of the conventional model.