BP神经网络PID控制对液压伺服控制的改进  

Improvement of Thermo-Mechanical Simulator′s Hydraulic Servocontrol Based on BP-NN PID Control

作　　者：张殿华[1] 冯莹莹[1] 骆宗安[1] 苏海龙[1] 王黎筠 

机构地区：[1]东北大学轧制技术及连轧自动化国家重点实验室,辽宁沈阳110004 [2]鞍山科技股份有限公司,辽宁鞍山114001

出　　处：《钢铁研究学报》2009年第3期59-62,共4页Journal of Iron and Steel Research

基　　金：国家自然科学基金资助项目(50227401)

摘　　要：热力模拟实验机的液压系统既要求工作在大流量区域,又要求工作在微小流量区域,需要在极宽的工作范围内精确地控制锤头的位移。基于热力模拟实验机液压伺服系统的低阻尼、时变性、非线性等特点,应用传统的PID控制器不能达到理想的控制效果。结合BP神经网络的PID控制理论根据锤头在不同位置的实际值、设定值及误差在线整定参数Kp、Ki、Kd,通过测试矩形波实际曲线与设定曲线的对比得出,基于BP神经网络的PID控制方法对液压伺服的控制有了很大改进。Thermo-mechanical simulator＇s hydraulic servo system requires working both in big flux area and small flux area, and it needs to control peen＇s position exactly in a large range of work area. For the thermo-mechanical simulator＇s hydraulic servo system owns the characters of lower damping, time-variation, and nonlinearity, etc. Applying conventional PID controller can not achieve ideal control. Using PID control theory together with BP-NN online adjustment parameters Kp, Ki, Kd according to the actual value, setting value and error of peen＇s different position, the hydraulic servocontrol can be improved through the contrast of test rectangular wave＇s actual curve between setting curve.

关 键 词：热力模拟实验机 液压伺服系统 BP神经网络的PID控制 

分 类 号：TH87[机械工程—仪器科学与技术]