基于改进PIDNN滑模控制的电压型PWM整流器

彭一芯; 魏建勋; 黄辉先; 方鑫; 陆建龙

基于改进PIDNN滑模控制的电压型PWM整流器

引用本文：彭一芯，魏建勋，黄辉先，方鑫，陆建龙.基于改进PIDNN滑模控制的电压型PWM整流器[J].计算技术与自动化,2015,(3):26-32

摘要点击次数: 1482

全文下载次数: 65

作者	单位
彭一芯，魏建勋，黄辉先，方鑫，陆建龙	（1.湘潭大学信息工程学院，湖南湘潭411105；2. 湘潭电机股份有限公司，湖南湘潭411105）

中文摘要:针对传统滑模变结构控制在三相电压型PWM整流器中应用时参数摄动所引起的抖动现象，提出一种改进PID神经网络的滑模变结构在线控制方法，将PID三个参数作为神经网络隐藏层的神经元，利用PID算法响应快、无静差的特点以及神经网络的在线自学习能力，实时对滑模趋近律参数进行修改，从而缩短系统状态进入滑模面的时间并减小抖动。对选取的价值函数进行改进，使算法不会陷入局部最优而逼近全局最优解，并对系统的全局稳定性进行分析。通过仿真和实验验证，结果表明该方法能使系统全局稳定，抖动有明显削弱且具有更好的动态响应。

中文关键词:PWM整流器滑模变结构 PID神经网络趋近律全局最优解

Improved PID Neural Network Sliding-mode Controller for Voltage Source PWM Rectifier

Abstract:For the problem that the system input parameters exists disturbances when the traditional sliding-mode variable-structure control(SMVSC) is applied to the three-phase voltage source PWM rectifier， an online solution that sliding-mode variable-structure control base on improved PID neural network design was presented in this paper, taking three parameters of PID as neurons of neural network in the hidden layer and considering that PID algorithm is of fast response, no static error and the online self-learning ability of neural network, the PID algorithm and neural network is combined to modify the sliding approaching rate parameter in real-time, thus the time of system state into the sliding surface and jitter is reduced. Through improving the selected value function, the algorithm cannot fall into local minimum and the global optimal solution is approached; also, the overall stability of the system is analyzed. Finally into simulation and experimental validation research, show that the method possesses smaller shake and preferable dynamic response.

keywords:PWM rectifier sliding-mode variable-xstructure PID neural network reaching law globally optimal

查看全文 查看/发表评论 下载pdf阅读器