基于遗传算法的强力旋压连杆衬套工艺参数多目标优化  

Multi-objective optimization on process parameters of power spinning for connecting rod bushing based on genetic algorithms

作　　者：佘勇[1] 占刚[1,2] 樊文欣[3] 毛卫秀 余世捷 She Yong;Zhan Gang;Fan Wenxin;Mao Weixiu;Yu Shijie(Guizhou Vocational Technology College of Electronics&Information,Kaili 556000,China;Key Laboratory of Advanced Manufacturing Technology,Ministry of Education,Guizhou University,Guiyang 550025,China;School of Mechanical and Power Engineering,North University of China,Taiyuan 030051,China)

机构地区：[1]贵州电子信息职业技术学院,贵州凯里556000 [2]贵州大学现代制造技术教育部重点实验室,贵州贵阳550025 [3]中北大学机械与动力工程学院,山西太原030051

出　　处：《锻压技术》2019年第12期187-191,共5页Forging & Stamping Technology

基　　金：国家自然科学基金资助项目(51665007);贵州省经济和信息化委员会资助项目(2017GH063)

摘　　要：针对连杆衬套的强力旋压成形工艺参数与力学性能之间的复杂关系,建立了工艺参数(减薄率、进给比)与力学性能(抗拉强度、伸长率)之间的RBF神经网络非线性关系。利用正交试验所得的数据结果对神经网络进行训练和测试,通过实测值与预测值的对比,发现所建立的神经网络模型具有较高的预测精度。并将此非线性关系作为适应度函数,基于遗传算法建立了工艺参数(减薄率、进给比)的多目标(抗拉强度、伸长率)优化模型,得出了多目标Pareto最优解集,并通过试验分析验证了最优解集的可行性,可以有效提高工艺参数的设计效率和产品的力学性能。For the complex relationship between process parameters and mechanical property of connecting rod bushing formed by power spinning, the non-linear relationship of RBF neural network between process parameters(thinning rate, feeding ratio) and mechanical properties(tensile strength, elongation) was established, and the neural network was trained and tested by the results of orthogonal experiment. Then, comparing the measured values with the predicted values, it was found that the established neural network model had high prediction accuracy. Furthermore, this non-linear relationship was regarded as the fitness function, and the multi-objective optimization model(tensile strength, elongation) of the process parameters(thinning rate, feeding ratio) was established based on the genetic algorithm theory. Finally, the multi-objective Pareto optimal solution set was obtained, and the feasibility of the optimal solution set was verified by experimental analysis to effectively improve the design efficiency of process parameters and the mechanical properties of products.

关 键 词：强力旋压 连杆衬套 神经网络 遗传算法 多目标优化 

分 类 号：TG376[金属学及工艺—金属压力加工]