模糊神经网络在感应加热电源应用的研究  

The Research of Fuzzy Neural Network Applied in Induction Heating Power Supply

作　　者：张萌[1] 张强 王虹 李明旭[1] 

机构地区：[1]河北工业大学控制科学与工程学院 [2]解放军93756部队

出　　处：《自动化技术与应用》2014年第7期13-16,共4页Techniques of Automation and Applications

摘　　要：针对感应加热电源具有非线性、时变性、难以建立准确数学模型的特点,本文提出将神经网络与模糊PID相结合,并引入补偿运算,构成一种新的具有可学习的自适应控制方法。该方法利用神经网络的自学习和模糊控制的不确定性等特点,引入神经网络不仅能够适当地调整输入、输出模糊隶属函数,而且能够借助于补偿逻辑算法动态地优化模糊推理,从而优化整个控制系统。通过对本文提出的算法、传统模糊PID算法以及模糊神经网络算法的仿真结果的对比可以看出,该算法较之传统模糊PID控制算法以及模糊神经网络算法具有鲁棒性更强、控制精度更高、可靠性更强等优势。It＇s difficult to build an accurate mathematical model of the induction heating power supply, because of its nonlinearity and time-varying characteristics. According to the analysis of traditional induction heating power supply, the paper presents a new control method, which combines neural network with fuzzy control,and uses conpensatory arithmetic.Compares with the traditional methods, the new method possesses stronger robustness and easier control. The results of the simulation proves that the control accuracy and more reliability of compensatory fuzzy neural network selfadaptive controller is better than the conventional typeof PID controller.

关 键 词：感应加热电源 补偿模糊神经网络 模糊神经网络 温度控制 自适应 

分 类 号：TK32[动力工程及工程热物理—热能工程]