自适应神经PID在挤塑机温控系统中的应用

针对塑料挤出机的多段料筒温度控制,以及常规PID控制在非线性的、时变系统中控制效果的局限性,提出了一种基于BP神经网络整定的PID控制方法.给出了计算机控制系统设计及系统软件开发.由于神经网络具有强大的非线性映射能力,自学习、自适应等优势,通过对系统性能的学习来实现具有最佳组合的PID控制,建立比例、积分和微分三种参数自学习的PID控制器.对锥形双螺杆塑料挤出机的温度控制实验结果表明,用该方法整定的PID控制系统,逼近精度高、鲁棒性好.

Self-adaptive Neural PID and Its Application to Temperature Control System of Plastic Machine

A PID control method based on BP neural network is put forward, concerning the temperature control of multi-layered containers in plastic machine and the limitations of the conventional PID control which resulted from the control of the nonlinear and time-varying system.The system design and software development are also presented.Possessing such merits as the ability of nonlinear mapping, self-learning, self-adaptation and ete, this neural network can help to realize the PID control with the best combinations by means of the understanding of the system pefforrnanee. The network has hing precision and good robustness. The experiment results show that the method is feasible and effective.