Applying Improved Fuzzy Grey Relation Analysis Algorithm in Multi-objective Optimization for High-Speed Milling of 4Cr5MoSiV Steel

This study presents an approach to optimize machining parameters with multi-response output using an experimental design in high-speed milling. For the experimental design, planned experiments are based on Taguchi's L-9 orthogonal array. In processing difficult-to-machine materials such as 4Cr5MoSiV hardened steel after heat treatment, machining performance indicators such as flank wear, vibration, cutting force, and surface roughness have been measured and surveyed. Process parameters including depth of cut, feed rate, and cutting speed are optimized by considering multiple output parameters simultaneously by combining two algorithms of fuzzy grey relation analysis (FGRA) and particle swarm optimization (PSO) based on the Taguchi experiment. After the experimental processes, optimization is performed for the grey relational grade (GRG), with large GRG parameters showing better performance characteristics and accordingly the levels at which the maximum response is achieved will give the parameter optimized for the survey object. The analysis shows that the feed rate has the largest GRG index meaning that it plays the most important role in multi-objective optimization in high-speed milling of 4Cr5MoSiV steel, followed by depth of cut and finally cutting speed degree. The results of multi-objective optimization in high-speed milling of 4Cr5MoSiV materials by the proposed algorithm give the surface quality is improved by 11.11%, and tool wear, vibration amplitude, and force are reduced by 13.72, 15.78, and 16.59%, respectively. It is clear that the performance indicators are significantly improved using this method. Research shows that this method has given positive results in the application of optimized design of multi-objective technological parameters and has extraordinary suitability.