基于RBF神经网络PID的阳极氧化电源电流控制  

Control of Anodic Oxidation Power Supply Current Based on RBF Neural Network PID

作　　者：韦成杰[1] 张惠敏[1] WEI Chengjie;ZHANG Huimin(Zhengzhou Railway Vocational&Technical College,Zhengzhou 451460,China)

机构地区：[1]郑州铁路职业技术学院

出　　处：《电镀与环保》2019年第6期70-72,共3页Electroplating & Pollution Control

基　　金：河南省高等学校重点科研项目计划教科技[2018]506号(项目编号19A120013)

摘　　要：阳极氧化电源系统是一个非线性、时变性的复杂系统,建立数学模型比较困难。传统PID控制方法无法保证阳极氧化电源电流拥有恒流、抗干扰能力强、超调小等特性。为了解决上述问题,开发了一种基于RBF神经网络PID的阳极氧化电源电流控制算法。利用RBF神经网络的自我学习能力,实现传统PID控制参数的自适应调整。仿真结果表明:基于RBF神经网络PID的控制算法响应速率快、超调小,拥有一定的抗干扰能力。Anodic oxidation power supply system was a complex non-linear and time-varying system, and it was difficult to establish a mathematical model. The traditional PID control method can not ensure that the anodic oxidation power supply current has the characteristics of constant current, strong anti-interference ability and small overshoot. In order to solve these problems, an algorithm for control of anodic oxidation power supply current based on RBF neural network PID was developed. RBF neural network has strong self-learning ability, which can adjust the parameters of traditional PID controller adaptively. The simulation results showed that the control algorithm based on RBF neural network PID has fast response speed, small overshoot and anti-interference ability.

关 键 词：阳极氧化电源电流 RBF神经网络 PID 仿真 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]