首页 | 官方网站   微博 | 高级检索  
     

采用RFR-GA算法的薄壁注塑件质量多目标优化
引用本文:曹艳丽,范希营,郭永环,刘欣,李春晓.采用RFR-GA算法的薄壁注塑件质量多目标优化[J].塑料工业,2021(1):65-70,101.
作者姓名:曹艳丽  范希营  郭永环  刘欣  李春晓
作者单位:江苏师范大学机电工程学院
基金项目:国家自然科学基金(51475220);徐州市科技计划项目(KC18239);江苏省研究生科研与实践创新计划项目(KYCX20_2333)。
摘    要:汽车内饰件可由注塑加工获得,但成型过程中塑件产生的翘曲、体积收缩较大,针对该问题,以某汽车薄壁注塑件为例,研究了其注塑工艺参数的优化方法。通过以注塑过程中的最小翘曲和最小体积收缩率为目标函数,以注塑温度、模具温度、注射压力、保压压力、保压时间以及冷却时间等参数作为设计变量,构建了多目标全局优化模型。利用Moldflow软件结合正交试验获得的试验结果训练随机森林回归模型,采用遗传算法对多目标模型进行全局寻优,获得最佳成型工艺参数,即对其成型缺陷进行了优化。结果表明,所提出的优化方法能够得到全局最优解,并同时优化了该汽车薄壁注塑件的翘曲和体积收缩率。将得到的最佳成型工艺参数进行Moldflow试验,可知翘曲和体积收缩率分别优化了74.6%和42.7%。将获得的最佳注塑成型工艺参数进行生产验证,结果表明生产出的薄壁汽车件成型质量较好,满足生产要求。

关 键 词:多目标优化  随机森林  遗传算法  翘曲  体积收缩

Multi-objective Optimization of Injection Process Parameters for Thin-walled Parts Based on RFR-GA Algorithm
CAO Yan-li,FAN Xi-ying,GUO Yong-huan,LIU Xin,LI Chun-xiao.Multi-objective Optimization of Injection Process Parameters for Thin-walled Parts Based on RFR-GA Algorithm[J].China Plastics Industry,2021(1):65-70,101.
Authors:CAO Yan-li  FAN Xi-ying  GUO Yong-huan  LIU Xin  LI Chun-xiao
Affiliation:(School of Mechanical and Electrical Engineering,Jiangsu Normal University,Xuzhou 221116,China)
Abstract:Automotive interior parts could be manufactured by injection molding,however,the warpage and volume shrinkage of the plastic parts during the process were large.For this problem,taking an automobile thin-walled injection molded part as an example,the optimization method for injection molding process parameters was studied.A multi-objective global optimization model for warpage and volume shrinkage based on injection temperature,mold temperature,injection pressure,packing pressure,packing time and cooling time were established.Using the Moldflow software and orthogonal experimental method to obtain the training data and the random forest regression model was established based on the training data,and the multi-objective model was solved by genetic algorithm.The optimal molding process parameters were obtained and the defects were optimized.The results show that the proposed optimization method can obtain the global optimal solution and optimize the warpage and volume shrinkage of the automobile thin-wall injection molded parts.The Moldflow software is carried out on the optimum injection molding process parameters,and the warpage and volume shrinkage are improved 74.6%and 42.7%,respectively.The obtained best injection molding process parameters are verified for production,and the results show that the quality of thin-walled automotive parts are good and it could meet the production requirements.
Keywords:Multi-objective Optimization  Random Forest  Genetic Algorithm  Warpage  Volume Shrinkage
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号