摘要
构造了一个自适应动态模型,实现对注塑成型过程参数的实时智能控制,使产品成型总处于最优状态。作者基于一个优化的BP神经网络,建立一个计算质量指标的数学控制模型,并通过正交试验为自适应控制模型提供过程参数调整顺序的动态规则,通过研究专家知识为自适应控制模型提供过程参数调整方向的经验规则。该系统显著降低了废品率,实用性强。
A real-time intelligent system for controlling the injection molding process parameters was realized by constructing a self-adaptive dynamic model, therefore the product properties remained the optimum state throughout. A mathematical control model about quality indexes was set up, based on an optimized back propagation ANN ,and the self-adaptive dynamic model was offered some dynamic rules about the adjustment sequence of process parameters by orthogonal method,and some empirical rules about the adjustment orientation of process parameters were given by studying specialist knowledge. The results showed that the system reduced notably the ratio of disqualified products and was more practical.
出处
《塑料》
CAS
CSCD
北大核心
2006年第6期87-90,共4页
Plastics
基金
广西科学基金资助项目(0575012)
广西大学科技基金资助项目(X051024)
关键词
过程参数
正交法
神经网络
动态规则
经验规则
自适应模型
process parameters
orthogonal method
artificial neural networks
dynamic rules
empirical rules
self-adaptive model