Application of Improved ChOA-SVM in Ship Welding Penetration State Recognition

During the welding process, the sound characteristics of the welding arc are closely related to the penetration state of the molten pool. The support vector machine is used as a classifier to evaluate the sound characteristics of welding arc. In view of the challenges of the support vector machine in the selection of penalty factors and kernel function parameters, an improved ChOA algorithm is proposed, and the Difference of Gaussians mutation strategy, leverage turning strategy and Gauss random walk strategy are introduced to improve the ability of the population to jump out of the local optimum. And optimize the parameters of the support vector machine. By using benchmark testing functions to verify the performance of the optimized model, the results show that the improved ChOA algorithm has better classification accuracy and optimization ability compared to PSO algorithm and ChOA algorithm. Applying it to the recognition of penetration state in the welding process, the experimental results show that the improved ChOA algorithm can search for better support vector machine parameters. This paper provides a feasible method to evaluate the penetration status of the weld pool during the welding process, and provides a new optimization strategy for support vector machine parameter selection.