Paper Info
Title
An Explainable Laser Welding Defect Recognition Method Based on Multi-Scale Class Activation Mapping
Abstract
Vision-based online defect recognition can provide insights for laser welding quality control systems. Although the visual signal contains richer quality information than the one-dimensional signal, the quality features contained in the visual signal are more abstract. To improve the explainability of current convolutional neural networks (CNNs) for laser welding defect recognition (LWDR), a class activation mapping method based on multi-scale fusion features (CAM-MSFF) is proposed. In addition, a multi-scale features adaptive fusion method is proposed with three steps of feature squeeze, feature mapping, and feature recalibrating. In order to facilitate the learning and utilization of multi-scale features by the proposed method, supervisory information is applied to multiple scales. The experimental results show that the proposed CAM-MSFF method has higher accuracy and convergence speed than the conventional model. The results of the explainability tests show that the proposed method can provide a more accurate and human-comprehensible explanation of the model & x2019;s decision basis.
Year
DOI
Venue
2022
10.1109/TIM.2022.3148739
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
Keywords
DocType
Volume
Welding, Feature extraction, Visualization, Convolutional neural networks, Lasers, Adaptation models, Sensors, Class activation mapping (CAM), convolutional neural network (CNN), defect recognition, explainable deep learning (XDL), laser welding, multi-scale
Journal
71
ISSN
Citations 
PageRank 
0018-9456
0
0.34
References 
Authors
0
7
Name
Order
Citations
PageRank
Tianyuan Liu1124.03
Hangbin Zheng200.34
Jin-Song Bao363.20
Pai Zheng402.03
Junliang Wang500.34
Changqi Yang600.34
Jun Gu700.34