Interpretable multi-task neural network modeling and particle swarm optimization of process parameters in laser welding

Abstract

The process parameters directly affect the quality and performance of laser welding (LW) by shaping the molten pool appearance. However, with the increase in the dimensions of process parameters and the number of samples, the relationship between process parameters and molten pool often exhibits high levels of uncertainty and nonlinearity. Machine learning (ML) techniques have been used for complex LW systems modeling, but they may be limited and unable to fully capture the complex relationships when faced with complex systems. Additionally, traditional ML techniques may lack interpretability within the model, making it difficult to understand the input features and their impact on the output. To address these issues, a method that combines an interpretable multi-task neural network (MTNN) and particle swarm optimization (PSO) is proposed. Firstly, an LW experimental platform is constructed, and the orthogonal design is conducted for data collection. In the data preparation stage, the curriculum learning strategy is employed to reorganize the raw experimental data. Subsequently, the MTNN is constructed to automatically learn feature representations among input process parameters, capture nonlinear relationships between data, and share weights across multiple related tasks to improve efficiency and performance. Furthermore, the PSO is designed to determine the constraints and objective functions. In addition, the shapley additive explanation (SHAP) method is utilized to calculate the importance of process parameters and enhance the interpretability. Finally, the optimization results are validated, and the results demonstrate that the optimized results of the proposed method have achieved satisfactory performance compared to the traditional ML methods.