Abstract:The groove of ultra narrow gap welding is narrow and deep, so it is difficult to evaluate the welding quality directly through vision. To solve the above problems, this paper proposed a prediction model of ultra narrow gap welding quality based on chaos multi strategy disturbed sparrow search algorithm (CMDSSA) optimized support vector machine (SVM). Firstly, the Sparrow search algorithm (SSA) is improved to improve the performance of sparrow search algorithm; Then the CMDSSA-SVM quality prediction model is constructed, and the parameters of SVM are optimized by using CMDSSA; Finally, the classification accuracy of the SVM welding quality prediction model optimized by SSA, chaos sparrow search optimization algorithm (CSSOA), particle swarm optimization algorithm (PSO), genetic algorithm (GA), whale optimization algorithm (WOA) is compared with that of the SVM welding quality prediction model. The results show that the prediction accuracy of CMDSSA-SVM is 97.541%, which is higher than other welding quality prediction models, which verifies the high accuracy and feasibility of the proposed ultra narrow gap welding quality prediction method.