摘要
针对半导体泵浦固体激光器温度控制过程中存在的非线性、大滞后特性,提出一种基于仿人智能策略的前馈组合控制器。前馈控制部分通过在线优化滞后参数估计值以获得被控对象的静态逆模型,逆模型辨识与直接逆控制由两个神经网络分别实现,可以在线调整网络权值。基本模糊控制器可在模糊PID和模糊PD控制算法之间进行转换,适用于控制系统的各工作状态。仿人智能控制策略根据输出误差变化的不同阶段调整所使用的控制组合,并具有自寻优功能。仿真表明,该方法可取得较好的控制效果。
This paper puts forward a kind of feed- forward combination controller for a kind of nonlinear large- lag object in temperature control of DPL. The feed - forward controller can optimize the estimated value of parameters to get the static counter model of object controlled. Identifying counter model is realized by a neural network that is separated from which is used for counter control, therefore they can adjust weight value of network online, The basic fuzzy controller can be switched between fuzzy PID control algorithm and fuzzy PD control algorithm so that it can be adapted to all kind of active state of the system, The control strategy simulating human intelligence adjusts combination of control algorithm according to various stage of output error. It can self- optimize too. A simulation case shows that the controller is effective.
出处
《计算技术与自动化》
2008年第2期28-31,共4页
Computing Technology and Automation
基金
河南省自然科学基金资助项目(0511010800)
关键词
DPL激光器
温度控制
神经网络
逆模型辨识
DPL
temperature control
neural network
identification of counter model
