Yanli Cao, Xiying Fan, Y. Guo, Wen-Juan Ding, Xin Liu, Chunxiao Li
{"title":"基于BO-RFR和NSGAⅡ方法的注射成型工艺参数多目标优化","authors":"Yanli Cao, Xiying Fan, Y. Guo, Wen-Juan Ding, Xin Liu, Chunxiao Li","doi":"10.1515/ipp-2020-4063","DOIUrl":null,"url":null,"abstract":"Abstract Injection molding of thin-walled plastic parts with minimum deformation in warpage and volume shrinkage is crucial for part quality. Simulation combined Latin hypercube sampling approach was used to research the effects of different process parameters on deformation. Then, random forest regression (RFR) is used to construct the mathematical relationship between process parameters and defects, such as warpage and volume shrinkage. The gaussian process is used as probabilistic surrogate model, while the probability of improvement is used as acquisition function to construct a Bayesian optimization for RFR’s hyperparameters, and the performance of random search is compared. In addition, the gradient boosting regression (GBR) and support vector regression (SVR) were also adopted to establish the prediction models, respectively. Comparing all the above prediction models, it can be found that the Bayesian optimized random forest regression (BO-RFR) has the highest accuracy. The Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is interfaced with the predictive models to find the optimum design parameters for the purpose of effectively predicting and controlling warpage and volume shrinkage. The results show that warpage is reduced by 66.03% while volume shrinkage is 46.20% after optimizing. The final finite element simulation and physical tests indicate that this proposed method can effectively achieve the multi-objective optimization of injection molding.","PeriodicalId":14410,"journal":{"name":"International Polymer Processing","volume":"38 1","pages":"8 - 18"},"PeriodicalIF":1.1000,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multi-objective optimization of injection molding process parameters based on BO-RFR and NSGAⅡ methods\",\"authors\":\"Yanli Cao, Xiying Fan, Y. Guo, Wen-Juan Ding, Xin Liu, Chunxiao Li\",\"doi\":\"10.1515/ipp-2020-4063\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Injection molding of thin-walled plastic parts with minimum deformation in warpage and volume shrinkage is crucial for part quality. Simulation combined Latin hypercube sampling approach was used to research the effects of different process parameters on deformation. Then, random forest regression (RFR) is used to construct the mathematical relationship between process parameters and defects, such as warpage and volume shrinkage. The gaussian process is used as probabilistic surrogate model, while the probability of improvement is used as acquisition function to construct a Bayesian optimization for RFR’s hyperparameters, and the performance of random search is compared. In addition, the gradient boosting regression (GBR) and support vector regression (SVR) were also adopted to establish the prediction models, respectively. Comparing all the above prediction models, it can be found that the Bayesian optimized random forest regression (BO-RFR) has the highest accuracy. The Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is interfaced with the predictive models to find the optimum design parameters for the purpose of effectively predicting and controlling warpage and volume shrinkage. The results show that warpage is reduced by 66.03% while volume shrinkage is 46.20% after optimizing. The final finite element simulation and physical tests indicate that this proposed method can effectively achieve the multi-objective optimization of injection molding.\",\"PeriodicalId\":14410,\"journal\":{\"name\":\"International Polymer Processing\",\"volume\":\"38 1\",\"pages\":\"8 - 18\"},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2022-10-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Polymer Processing\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1515/ipp-2020-4063\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, CHEMICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Polymer Processing","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1515/ipp-2020-4063","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
引用次数: 0
摘要
摘要薄壁塑料零件的注射成型是保证零件质量的关键。采用模拟结合拉丁超立方体采样的方法,研究了不同工艺参数对变形的影响。然后,利用随机森林回归(RFR)构建工艺参数与翘曲、体积收缩等缺陷之间的数学关系;采用高斯过程作为概率代理模型,采用改进概率作为获取函数对RFR的超参数构造贝叶斯优化,并比较随机搜索的性能。此外,还分别采用梯度增强回归(GBR)和支持向量回归(SVR)建立预测模型。比较上述所有预测模型,可以发现贝叶斯优化随机森林回归(BO-RFR)具有最高的精度。将非支配排序遗传算法- ii (NSGA-II)与预测模型相结合,寻找最优设计参数,有效地预测和控制翘曲和体积收缩。结果表明,优化后的翘曲量减少了66.03%,体积收缩率减少了46.20%。最后的有限元仿真和物理试验表明,该方法可以有效地实现注射成型的多目标优化。
Multi-objective optimization of injection molding process parameters based on BO-RFR and NSGAⅡ methods
Abstract Injection molding of thin-walled plastic parts with minimum deformation in warpage and volume shrinkage is crucial for part quality. Simulation combined Latin hypercube sampling approach was used to research the effects of different process parameters on deformation. Then, random forest regression (RFR) is used to construct the mathematical relationship between process parameters and defects, such as warpage and volume shrinkage. The gaussian process is used as probabilistic surrogate model, while the probability of improvement is used as acquisition function to construct a Bayesian optimization for RFR’s hyperparameters, and the performance of random search is compared. In addition, the gradient boosting regression (GBR) and support vector regression (SVR) were also adopted to establish the prediction models, respectively. Comparing all the above prediction models, it can be found that the Bayesian optimized random forest regression (BO-RFR) has the highest accuracy. The Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is interfaced with the predictive models to find the optimum design parameters for the purpose of effectively predicting and controlling warpage and volume shrinkage. The results show that warpage is reduced by 66.03% while volume shrinkage is 46.20% after optimizing. The final finite element simulation and physical tests indicate that this proposed method can effectively achieve the multi-objective optimization of injection molding.
期刊介绍:
International Polymer Processing offers original research contributions, invited review papers and recent technological developments in processing thermoplastics, thermosets, elastomers and fibers as well as polymer reaction engineering. For more than 25 years International Polymer Processing, the journal of the Polymer Processing Society, provides strictly peer-reviewed, high-quality articles and rapid communications from the leading experts around the world.