摘要
采用析因实验的方法,进行模腔压力数据的采集,通过数据研究了不同注射阶段模腔压力的变化规律,分析了各工艺参数对模腔压力值的影响,得出保压压力设定是模腔压力变化的主因。基于采集到的模腔压力数据,建立了以工艺参数、部分模腔压力值作为输入、剩余各阶段模腔压力值为输出的BP神经网络压力预测模型,测试结果显示预测精度很高。
The transform regulation of cavity pressure in each injection stage was studied through the cavity pressure data obtained from factorial experiment. The influence of each process parameter on cavity pressure was analyzed and found out that dwell pressure （ the max system pressure） was the primary cause of cavity pressure change. The process parameters and part of cavity pressure value as input, and the cavity pressure value remaining in the other periods as output, a BP neural network prediction model based on the cavity pressure data collected was established. The test result showed that the forecasting precision of the model was very high.
出处
《塑料》
CAS
CSCD
北大核心
2014年第1期97-100,80,共5页
Plastics
关键词
模腔压力
析因设计
神经网络
注塑制品
压力预测
cavity pressure
factorial design
neural network
injection product
pressure prediction
