一种柔性直流输电系统PID-ANFIS优化控制方法.pdfVIP

第43 卷 第17 期 电力系统保护与控制 Vol.43 No.17 2015 年9 月1 日 Power System Protection and Control Sep. 1, 2015 一种柔性直流输电系统PID-ANFIS 优化控制方法 杨 天，霍琳琳 (山东省电力公司威海供电公司，山东 威海 264200) 摘要：针对柔性直流输电系统(Voltage Source Converter based High-Voltage Direct-Current, VSC-HVDC)双闭环控制中 PI 控制存在参数整定困难及控制器数量过多等问题，提出一种具有PID 功能的自适应神经元模糊推理系统(Adaptive Neuro-Fuzzy Inference System with PID function, PID-ANFIS)控制器用于该系统控制。其中，PID-ANFIS 控制器兼有神 经网络控制、二阶模糊控制及 PID 功能；同时提出的基于三重合作粒子群算法(Treble Cooperative Particle Swarm Optimization, TCPSO)用于优化该控制器中神经网络参数。TCPSO 采用由降维合作、分组合作与记忆合作组成的三重 合作策略，极大程度上提升了神经网络参数优化的精度。深入研究了TCPSO 优化PID-ANFIS 控制器参数的步骤。 基于TCPSO 优化的PID-ANFIS 控制器能够实现VSC-HVDC 系统的直接功率控制效果。仿真结果表明该控制器具有 控制速度快、超调量小、抗干扰能力强等优点，是VSC-HVDC 控制系统的一个可行方案。 关键词：柔性直流输电；PID ；自适应神经元模糊推理系统；三重合作粒子群算法；直接功率控制 A control method of PID-ANFIS controller for VSC-HVDC YANG Tian, HUO Linlin (Weihai Electric Power Company, State Grid Shandong Electric Power Company, Weihai 264200, China) Abstract: Due to the PI control system for VSC-HVDC has problems of parameters difficult to set, too many control users, and so on, a novel controller composed of PID function and multiple-output ANFIS (PID-ANFIS) is presented, which is made up of neural network, two order fuzzy control and PID control. A treble cooperative PSO (TCPSO) is also presented to optimize PID-ANFIS controller ’s neural parameters. TCPSO is forged by harmonizing the grouping cooperation, the dimension-reduced cooperation and memory cooperation, which is able to improve the precision of optimizing neural networks. This paper provides the process of PID-ANFIS parameters training by TCPSO. Then, t