Wang Xiaoqiang, Wang Haojie, Wang Paigang, Liu Zhifei
School of Mechatronics Engineering, Henan University of Science and Technology, Luoyang, 471003, China.
Collaborative Innovation Center of Advanced Manufacturing of Mechanical Equipment, Luoyang, 471003, Henan, China.
Sci Rep. 2022 Mar 9;12(1):3851. doi: 10.1038/s41598-022-07917-7.
To obtain the optimal processing parameters of ultrasonic roll extrusion, 42CrMo bearing steel was taken as the research object, and the orthogonal test method was used to design an ultrasonic roll extrusion experiment with spindle speed, feed speed, static pressure and amplitude as parameters. Based on the orthogonal test data, the prediction models of surface roughness, surface residual stress and surface hardness were established by a multiple regression method, and the reliability of the model was verified. An algorithm combining SPEA2 and the shift density estimation strategy (SPEA2SDE) was introduced. The performance of the SPEA2SDE algorithm, NSGA II algorithm and SPEA2 algorithm is tested and compared on a three-dimensional test function set to verify its effectiveness. The SPEA2SDE algorithm are used to solve the multi-objective optimization model to obtain the optimal combination of processing parameters, and the ultrasonic roll extrusion experiment is carried out. The research results show that the surface roughness, surface residual stress and surface hardness optimized by the SPEA2SDE algorithm are in good agreement with the experimental values, and the average error is controlled within 10%, which shows that the algorithm can achieve high precision. It can effectively solve the multi-objective optimization problem of ultrasonic roll extrusion process parameters and can be used to guide actual production machining.
为获得超声辊挤压的最优工艺参数，以42CrMo轴承钢为研究对象，采用正交试验法设计了以主轴转速、进给速度、静压和振幅为参数的超声辊挤压试验。基于正交试验数据，采用多元回归方法建立了表面粗糙度、表面残余应力和表面硬度的预测模型，并对模型的可靠性进行了验证。引入了一种结合SPEA2和移位密度估计策略（SPEA2SDE）的算法。在三维测试函数集上对SPEA2SDE算法、NSGA II算法和SPEA2算法的性能进行了测试和比较，以验证其有效性。采用SPEA2SDE算法求解多目标优化模型，得到最优工艺参数组合，并进行超声辊挤压试验。研究结果表明，SPEA2SDE算法优化得到的表面粗糙度、表面残余应力和表面硬度与试验值吻合良好，平均误差控制在10%以内，表明该算法具有较高的精度。它能有效解决超声辊挤压工艺参数的多目标优化问题，可用于指导实际生产加工。
