Deep Neural Network-based Approach for Warpage and Weight Prediction of Plastic Injection Molding

摘要：

　　Injection molding is one of the most promising manufacturing processes for the plastic components,which enable the mass production with high dimensional accuracy.Since the process conditions have the significant influence on the quality of the final product,it is essential to model the relationship between process conditions and product quality.In this paper,we built a deep neural network(DNN)based quality prediction model with advanced artificial intelligence algorithms such as ELU activation function,He initialization and drop out.We got data from the CAE tool,Maps-3D with a full-factorial design.The result show DNN and advanced algorithms based model is a useful tool for the quality prediction of injection molding.The performance of the developed model also showed the necessity of controlling the standard deviation gap between the train and test data.

关键词： Injection Molding Neural network Warpage prediction Weight prediction

作者: Lee Chi Hun Yoon Sung Yong Kim Doo Hee Park Seung Jin

作者单位: Department of Mechanical Engineering,Pohang University of Science and Technology(POSTECH),Pohang,376 Graduate Institute of Ferrous Technology,Pohang University of Science and Technology(POSTECH),Pohang

会议类型: 国际会议

会议名称: 2018世界粉末冶金大会

会议地点: 北京

会议语种:英文

页码: 2016-2021

在线出版日期: 2018-09-16（万方平台首次上网日期，不代表论文的发表时间）