基于BP-PSO的智能阀门定位器控制算法研究  

Research on control algorithm of intelligent valve positioner based on BP-PSO

作　　者：高阳 傅连东[1,2] 邓江洪[1,2] 湛从昌 GAO Yang;FU Liandong;DENG Jianghong;ZHAN Congchang(School of Mechanical Automation,Wuhan University of Science and Technology,Wuhan 430081,China;Key Laboratory of Metallurgical Equipment and Its Control,Ministry of Education,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]武汉科技大学机械自动化学院,武汉430081 [2]武汉科技大学冶金装备及其控制教育部重点实验室,武汉430081

出　　处：《流体机械》2023年第5期49-54,共6页Fluid Machinery

基　　金：国家自然科学基金资助项目(51975425)。

摘　　要：针对五步开关控制算法易超调以及控制参数取值具有近似性和不确定性等不足,提出了一种参数自整定和参数寻优的控制算法,并在最关键的脉冲调制控制环节运用了改进的BP神经网络算法和粒子群(PSO)算法来寻找最优阀门控制参数。搭建智能阀门定位器实验平台,采用传统五步开关控制算法和本控制算法分别对阀门进行控制试验。结果表明,本控制算法相较于传统五步开关控制算法的适用性大大增强,避免了超调,缩短了响应时间,阀门控制精度达到0.03%,阀门开度稳定时间缩短至1 s以内。In view of the shortcomings,such as susceptibility of the five-step switch control algorithm to overshooting,and the approximateness and uncertainty of the values of control parameters,a control algorithm of parameter self-tuning and parameter optimization was proposed,and the improved BP neural network algorithm and particle swarm optimization(PSO)algorithm were used in the most critical pulse modulation control link to find the optimal valve control parameters.The experimental platform of intelligent valve positioner was built,and the valve control experiments were carried out using the traditional five-step switch control algorithm and this control algorithm,respectively.The experimental results show that compared with the traditional fivestep switch control algorithm,the applicability of this control algorithm is greatly enhanced,which avoids overshooting,shortens the response time,achieves 0.03%valve control accuracy,and shortens the valve opening stabilization time to less than 1 second.

关 键 词：智能阀门定位器 参数自整定 BP神经网络优化 PSO粒子群算法 

分 类 号：TH137[机械工程—机械制造及自动化]