An intelligent parameters optimization method of titanium alloy belt grinding considering machining efficiency and surface quality

Abrasive belt grinding is widely used in typical difficult materials such as titanium alloy, due to its lower grinding temperature and flexible machining. Processing efficiency and processing quality are the two most concerning problems. However, when enhancing processing efficiency, it is a key issue to guarantee the quality of the machining surface. This study provided a parameter optimization model based on the optimization objectives of surface roughness (Ra) and material removal rate (MRR), and the grinding parameters obtained by the solution were verified by experiments. It is found that the performance of the improved non-dominated sorting genetic algorithm (CNSGA-II) is generally good. The algorithm can converge faster and the diversity of Pareto solutions is improved. Besides, when the process parameters obtained by the multi-objective optimization model are used for machining, the surface roughness of the workpiece is reduced to 0.499 mu m, and the material removal amount can reach 0.115 mg/min. This shows that the method can not only improve the grinding efficiency of titanium alloy workpiece, but also improve the surface quality. Furthermore, the surface morphology is better with the optimal combination of process parameters; there are no obvious tearing and wear debris on the surface of the CNSGA-II (Ra, MRR), which exhibited deeper wear scars than that of the DF (Ra) and improves surface fineness and flatness.