汽车消声器连结法兰盘冲压成形工艺参数优化  

Optimization of Stamping Process Parameters of Automobile Muffler Connecting Flange

作　　者：李宇[1] 赵博宁[1] 李国坚 Li Yu;Zhao Bo-ning;Li Guo-jian(School of Equipment Manufacturing,Liuzhou Railway Vocational Technical College,Liuzhou,545616,China;Liuzhou Wuling Automobile Industry Co.,Ltd.,Liuzhou 545000,China)

机构地区：[1]柳州铁道职业技术学院装备制造学院,广西柳州545616 [2]柳州五菱汽车工业有限公司,广西柳州545000

出　　处：《内燃机与配件》2023年第19期33-35,共3页Internal Combustion Engine & Parts

基　　金：广西中青年能力提升项目(2020KY44005);柳州铁道职业技术学院校级课题(2021-KJB12)。

摘　　要：选取了某企业生产的汽车消声器连结法兰盘零件为参数优化对象。利用Dynaform软件对零件冲压过程进行有限元数值模拟并记录27组实验数据。建立BP神经网络模型并完成神经网络模型的训练及测试,最后结合遗传算法优化工艺参数,得到最优值的试验条件为:压边力68kN,凸模圆角半径12mm,摩擦系数0.12,凸凹模间隙2.5mm。经过冲压试验,观察该零件,成形质量完好,孔口处未见明显的开裂。将神经网络和遗传算法相结合优化法兰盘冲压成形工艺参数的方法寻优范围更大,获取的最优值也更加准确。The automobile muffler connecting flange produced by a certain enterprise is selected as the parameter optimization object.Dynaform software was used to simulate the stamping process and record 27 groups of experimental data.The BP neural network model is established and the training and testing of the neural network model are completed.Finally,the genetic algorithm is used to optimize the process parameters.The optimal test conditions are obtained as follows:BHF 68 kn,punch radius 12 mm,friction coefficient 0.12,clearance Between Punch and die 2.5 mm.The stamping test shows that the forming quality of the part is good,and there is no obvious crack at the hole mouth.The method of combining neural network and genetic algorithm to optimize the stamping process parameters of Flange has wider optimization range and more accurate optimal value.

关 键 词：神经网络 遗传算法 参数优化 法兰盘 冲压成形 

分 类 号：TG386[金属学及工艺—金属压力加工]