Modeling and Optimization Method of Laser Cladding Based on GA-ACO-RFR and GNSGA-II

Laser cladding is an environmentally friendly and reliable surface modification technology. The quality characteristics of the coating are directly affected by the process parameters of laser cladding. The reasonable selection of process parameters is essential to obtain high-quality coating. In this study, the single-track 15-5PH alloy coating was fabricated on the surface of 12Cr13 stainless steel. In view of the hybrid Genetic Algorithm and Ant Colony Optimization (GA-ACO) can effectively improve the prediction ability and robustness of Random Forest Regression (RFR), a prediction method of cladding layer quality characteristics based on GA-ACO-RFR was proposed. The fast non-dominated ranking genetic algorithm with elite strategy by introducing the Gaussian distribution crossover operator (GNSGA-II) was used to optimize the process parameters of laser cladding. The results showed that the multi-objective optimization method of laser cladding process parameters proposed in this paper can obtain high-quality laser cladding coating. This work demonstrated the potential of the proposed method in laser cladding process prediction and optimization.