发泡成型机蒸汽压力的神经网络自适应逆控制研究  

Study on Neural Network Adaptive Inverse Control of Steam Pressure in Foaming Machine

作　　者：刘哲纬[1] 张索[1] 吴起行 LIU Zhe-wei;ZHANG Suo;WU Qi-xing(School of Automation,Zhejiang Institute of Mechanical&Electrical Engineering,Hangzhou 310053,China)

机构地区：[1]浙江机电职业技术学院自动化学院,浙江杭州310053

出　　处：《塑料科技》2021年第3期89-91,共3页Plastics Science and Technology

基　　金：浙江省教育厅访问工程师“校企合作项目”(FG2019071)。

摘　　要：针对发泡成型机蒸汽压力的非线性系统存在控制精度差和动态性能不佳的问题,设计了基于神经网络的自适应逆控制方法。建立了发泡成型机蒸汽压力的参考模型,利用参考模型的输入输出对训练单层神经网络逆模型作为逆控制器,并采用LMS自适应算法在线调节神经网络权向量。通过与PID控制器进行对比实验,结果表明,所设计的神经网络自适应逆控制方法提高了蒸汽压力的稳定性以及快速响应能力,几乎不存在系统超调。In view of the problems of poor control accuracy and poor dynamic performance in the nonlinear system of steam pressure of foaming molding machine,an adaptive inverse control method based on neural network was designed.A reference model of steam pressure of foaming molding machine was established.The input and output of the reference model were used to train the inverse model of single-layer neural network as the inverse controller,and LMS adaptive algorithm was used to adjust the spirit online through the network weight vector.Compared with PID controller,the experimental results show that the designed neural network adaptive inverse control method improves the stability and fast response ability of steam pressure,almost no system overshoot.

关 键 词：发泡成型机 压力控制 神经网络 自适应逆控制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TQ320.52[自动化与计算机技术—控制科学与工程]