基于Moldflow和BP神经网络的火灾报警器壳体成型工艺参数优化  

Optimization of Forming Process Parameters for Fire Alarm Shell Based on Moldflow and BP Neural Network

作　　者：王一鸣 乔印虎 魏宝丽 贾茹 WANG Yiming;QIAO Yinhu;WEI Baoli;JIA Ru(School of Mechanical Engineering,Anhui Science and Technology University,Chuzhou Anhui 230009,China;Anhui Water Resources Development Co.,Ltd.,Bengbu Anhui 233000,China)

机构地区：[1]安徽科技学院机械工程学院,安徽滁州230009 [2]安徽水利开发有限公司,安徽蚌埠233000

出　　处：《佳木斯大学学报（自然科学版）》2024年第3期94-97,共4页Journal of Jiamusi University：Natural Science Edition

摘　　要：以火灾报警器壳体为研究对象,在Moldflow软件中进行壳体的模流分析,以寻求壳体的翘曲变形量最小为求解结果。通过设计正交试验和进行极差分析,确定了注塑工艺参数对壳体翘曲变形量的影响趋势,最终优化后的壳体最大翘曲程度降低了11.3%,此时的最佳注塑工艺参数为熔体温度为205℃,模具温度为50℃,保压时间为16s,注塑压力为95MPa,注射时间为1.6s。通过建立壳体翘曲变形量的BP神经网络参数模型,对塑件的翘曲值进行了预测,预测结果证明预测值的精度较高,可以有效提高模具的设计效率和可靠性。Taking the fire alarm shell as the research object,the mold flow analysis of the shell was carried out in Moldflow software to seek the minimum warping deformation of the shell as the solution result.The orthogonal experimental method was used to design the experimental plan,and the results were analyzed for mean and range.The combination of various process parameters after the first optimization was obtained.On the basis of the first optimization,a BP neural network parameter model was established for the warping deformation of the shell,and the influence trend of injection molding process parameters on the warping deformation of the shell was determined.The maximum warping degree of the optimized shell was reduced by 11.3%.At this time,the optimal injection molding process parameters were mold temperature of 50℃,melt temperature of 205℃,injection time of 1.6 seconds,holding time of 16 seconds,and holding pressure of 95 MPa.Based on BP neural network,the warping value of plastic parts was predicted,and the prediction results showed that the accuracy of the predicted values was high,which can effectively improve the design efficiency and reliability of the mold.

关 键 词：火灾报警器壳体 BP神经网络 MOLDFLOW 工艺参数 

分 类 号：TQ320[化学工程—合成树脂塑料工业]