摘要
针对电子负载控制灵敏度低、稳定性差等问题,提出基于PSO-BP-PID的直流电子负载控制方法。分析电子负载基本结构,构建数学模型,分析电子负载在不同工作模式下的电流变化规律;建立三层BP网络模型,分别描述每层结构的输入与输出内容;为提高BP网络的学习能力,减少控制误差,将PSO算法作为学习算法,确定粒子群规模、惯性权重等重要参数,获得所有粒子适应度值,不断更新个体的位置与速度,当满足收敛条件时,输出最优解,实现控制参数的自适应调整;根据算法特征,设计控制器整体结构,利用该控制器即可实现直流电子负载控制。仿真结果表明,所提方法的控制误差小,响应速度快,且控制过程中能够有效抑制谐波。
In order to address the problems of low sensitivity and stability in electronic load control,this paper put forward a method of controlling DC electronic load based on PSO-BP-PID.Firstly,the basic structure of the electronic load was analyzed,and a mathematical model was constructed.Secondly,the current change rules of the electronic load under different working modes were analyzed.Then,a three-layer BP network model was constructed,and the input and output content at each layer were described respectively.In order to improve the learning ability of the BP network and reduce control error,the PSO algorithm was used as a learning algorithm,and then particle swarm size,inertia weight,and other important parameters were determined.Finally,all particle fitness values were obtained.Next,the individual position and speed were continuously updated.When the convergence condition was met,the optimal solution was outputted.Finally,the control parameters were adjusted adaptively.According to the characteristics of the algorithm,the overall structure of the controller was designed.This controller could control the DC electronic loads.Simulation results show that the control error of the proposed method is small,and the response speed is fast.Meanwhile,harmonic waves can be effectively suppressed during the control process.
作者
蒋利炜
何可人
陈航
JIANG Li-wei;HE Ke-ren;CHEN Hang(School of Microelectronics and Control Engineering,Changzhou University,Changzhou Jiangsu 213164,China)
出处
《计算机仿真》
2024年第1期306-310,共5页
Computer Simulation
关键词
粒子群算法
神经网络
控制器
直流电子负载
负载控制
Particle swarm optimization
Neural network
PID controller
DC electronic load
Load control