基于PID神经网络的弧焊电源控制器的研究  

Research on welding process controller based on PID neural network

作　　者：何宽芳[1] 黄石生[1] 

机构地区：[1]华南理工大学机械工程学院,广东广州510640

出　　处：《电焊机》2007年第7期58-60,共3页Electric Welding Machine

基　　金：国家自然科学基金资助项目(50375054)

摘　　要：为了实现弧焊过程弧焊电源输出特性到给定量的快速响应及其智能控制,提出了一种基于PID神经网络的控制器。将PID控制与BP神经网络相结合应用于弧焊过程的智能控制,既有PID控制规律的优点,又具有神经网络很强的信息综合处理能力特点。实验表明,该控制器用于弧焊电源输出特性的智能控制,具有控制响应速度快、超调量小、收敛速度快、稳态精度高的特点,满足弧焊过程控制的要求。A controller based on PID neural network（PIDNN） is proposed to for arc welding power of which output characteristic is responded to given value quickly and intelligently controlled in welding process.The new method which combines the PID controls strategy and neural net to control welding process intelligently,so it has the merit of P1D controlling rule and trait of better information disposal ability of neural network.The results of simulation show that the controller has properties of quick response,low adjustment,quick convergence and good stable accuracy,which meet the need of control of welding process.

关 键 词：弧焊过程 输出特性 PID神经网络 控制器 

分 类 号：TG409[金属学及工艺—焊接]