摘要
静止无功补偿器(SVC)是电力系统中应用广泛的动态无功补偿装置。针对传统比例积分微分(PID)在SVC动态调节过程中由于控制器参数固定而存在动态响应、自适应能力差的问题,提出了一种基于小波神经网络PID(WNNPID)的SVC电流反馈电压稳定控制方法。首先,分别选取SVC的电压差ΔUr、电压误差ΔU和补偿电压USL作为WNNPID控制器的输入信号,而控制器的输出为SVC的参考电纳。然后,采用小波神经网络(WNN)和增量式PID控制对WNNPID控制器的结构进行设计。最后,采用Matlab/Simulink仿真平台对所提控制方法进行仿真,并与基于反向传播(BP)神经网络PID的控制效果进行了对比。仿真结果表明,所提WNNPID控制方法具有更稳定的电压控制效果、较快的响应速度、较好的动静态响应性能和较强的自适应能力。
Static var compensator(SVC)is a widely used dynamic var compensation device in power system.Aiming at the traditional proportional integral differential(PID)in the dynamic regulation process of SVC,which has the problems of poor dynamic response and adaptive ability due to the fixed controller parameters,a current feedback voltage stabilization control method of SVC based on wavelet neural network PID(WNNPID)is proposed.Firstly,the voltage differenceΔUr,voltage errorΔU and compensation voltage USL of the SVC are selected as the input signals of the WNNPID controller respectively,while the output of the controller is the reference electrode of the SVC.Then,the wavelet neural network(WNN)and incremental PID control are used to design the structure of the WNNPID controller.Finally,the proposed control method is simulated using Matlab/simulink simulation platform,and the control effect is compared with that of the back propagation(BP)-based neural network PID.The simulation results show that the proposed WNNPID control method has more stabilization voltage control effect,faster response speed,better dynamic and static response performance,and stronger adaptive capability.
作者
周晓华
冯雨辰
王月武
蓝会立
ZHOU Xiaohua;FENG Yuchen;WANG Yuewu;LAN Huili(School of Automation,Guangxi University of Science and Technology,Liuzhou 545616,China)
出处
《自动化仪表》
CAS
2023年第11期48-53,共6页
Process Automation Instrumentation
基金
广西高校中青年教师科研基础能力提升基金资助项目(2022KY0331)。
关键词
静止无功补偿器
电流反馈
电压稳定控制
小波神经网络
反向传播神经网络
动态响应
自适应能力
比例积分微分
Static var compensator(SVC)
Current feedback
Voltage stabilization control
Wavelet neural network(WNN)
Back propagation(BP)neural network
Dynamic response
Adaptive capability
Proportional integral differential(PID)
