基于PID神经网络的拉深件变压边力控制方法研究

摘要

将传统的PID控制器与神经元网络融合,建立PID神经网络.运用VB语言编译了拉深过程中变压边力控制系统的PID神经网络仿真程序,并与传统的PID控制仿真进行了对比.建立了基于PIDNN的变压边力控制系统,并通过锥形件拉深实验,证实了PIDNN控制系统具有精度高,抗干扰能力强,能较准确达到变压边力控制要求等优越性.为后续的变压边力控制系统实验研究与工厂实际应用提供了理论与实践基础.%A PID neural network (PIDNN) based on the integration of PID controller and neural network is built. The PIDNN simulation program of variable BHF control system in deep drawing is compiled with VB, and compared with the traditional PID control simulation. Variable BHF control system based on PIDNN is built, and through the cone-shaped drawing experiment, PIDNN system is confirmed to have the advantages of high precision, anti-interference ability and achieving accurate control of variable BHF requirements, which provides theory and practice foundation for the further experiment and practical application.