Towards energy and material efficient laser cladding process: Modeling and optimization using a hybrid TS-GEP algorithm and the NSGA-II

The soaring global additive manufacturing (AM)market implies considerable potentials of energy and material savings. However, very few researches have addressed the energy and material efficiency issue in AM process through processing parameters optimization. In this study, we developed a predictive model of specific energy consumption (SEC)and metallic powder usage rate in laser cladding process. Three approaches were adopted to perform the modeling, namely, basic gene expression programming (GEP), response surface methodology (RSM), and integrated Tabu search and GEP (TS-GEP). Comparison amongst these methods revealed that TS-GEP demonstrated the highest fitting performance in terms of the root mean square deviation (RMSD)and coefficient of determination (R²). The experimental validation showed that TS-GEP enabled high robustness and precision of the modeling even though the accuracy of prediction was slightly lower than that of RSM in some cases. Analysis of variance was conducted to examine the contribution of the processing parameters. Results presented that the dominating factor was powder feed rate followed by laser power, Z-increment, and scanning speed irrespective of the interactive effects. With the predictive models, the Pareto front was determined by non-dominated sorting genetic algorithm II (NSGA-II)to provide the optimal set of processing parameters for the maximization of energy and metallic powder efficiency. This study would facilitate appropriate parameter selection of laser cladding process and assist the sustainable manufacturing in AM domain.