Parameters optimization for single-track laser cladding based on MPA-SVR and A-NSGA-III

Abstract

Laser cladding as an emerging surface modification technology, the morphology of the single-track cladding layer is directly affected by the process parameters. To obtain the ideal cladding layer morphology, it is necessary to build the mapping relationship between the process parameters and the morphology and optimize the process parameters. A method for predicting the morphology of the single-track cladding layer is proposed by using the support vector regression optimized by the marine predators algorithm. Then, the adaptive non-dominated sorting genetic algorithm III is used for process parameter optimization to determine the optimal process parameters of laser cladding. The results of the validation experiments show that the aspect ratio of the optimized cladding layer has been improved by 41.78%, the dilution rate has been improved by 22.30%, and the wetting angle has been reduced by 35.20%. The proposed process parameters optimization method of laser cladding can significantly improve the morphology of the cladding layer.