Explore the vast range of titles available.

Due to the emergence of mass personalized production, intelligent welding systems must achieve high levels of productivity and flexibility. Therefore, a self-learning welding-task sequencing method that is driven by data and knowledge was developed during this study. First, a minimized dataset of welding sequences, which is required to predict the welding deformation, was designed according to the number and directions of the welds included in the welding tasks. The dataset consisted of a finite number of welding sequences and their corresponding welding deformation data. Then, an algorithm to predict the welding deformation was developed. To improve the interpretability of the results, domain knowledge was integrated into the construction and training processes of a self-learning model. Finally, a case study regarding bracket welding was investigated. With FEA as the benchmark, the maximum relative error of the welding deformation predicted by the algorithm designed to predict the welding deformation was 8%. The maximum deformation of the optimal welding-task sequence output by the self-learning welding-task sequencing method driven by data and knowledge was 32.31% less than that produced by the rule-based reasoning method. The study results demonstrate that the proposed welding-task sequencing method is effective for welding sequence planning of laser welding bracket structures.