基于RBFNN在线辨识的自适应PID预焙阳极焙烧炉温度控制  

Adaptive PID Control Based on RBFNN On-line Identification for Temperature System of Anode Pre-baking Furnace

作　　者：张明光[1] 王兆刚[1] 王鹏[1] 

机构地区：[1]兰州理工大学电气工程与信息工程学院,兰州730050

出　　处：《有色金属（冶炼部分）》2008年第4期16-19,23,共5页Nonferrous Metals（Extractive Metallurgy)

基　　金：国家高技术研究发展计划(863计划)项目(2002BA901A28);甘肃省省长基金项目(GS015-A52-012)

摘　　要：针对工况变化频繁的焙烧炉焙烧过程,提出了采用基于径向基函数(RBF)神经网络(NN)在线辨识的自适应PID控制策略。该方法通过RBF神经网络的自学习能力在线辨识系统模型,进而获得被控对象的Jacobian信息,实现对PID参数的在线调整。在对算法进行改进的基础上将其应用于预焙阳极焙烧炉温度过程控制中,实验结果表明,该方法具有很强的自适应能力和鲁棒性,达到了满意的控制效果。An adaptive PID control strategy based on Radial Basis Function （RBF） neural network（NN） on-line identification is proposed for the baking process of the furnace, whose operating conditions change frequently. The RBFNN is used to identify system model on-line using the self-learning ability of RBFNN, and the parameters of PID controller are tuned on-line by means of the Jacobian information of control plant. It was applied to the temperature control system of the anode pre-baking furnace with improved learning algorithm of neural network, the results show that the proposed controller has the adaptability, strong robustness and satisfactory control performance.

关 键 词：预焙阳极焙烧炉 RBF神经网络 自适应PID控制 温度控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]