神经网络在加热炉温度控制系统检测环节改进方法的应用  

The Application of Neural Network on the Improving Methods of Detection of the Temperature Control System for the Furnace

作　　者：刘会景[1] 

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650051

出　　处：《工业加热》2010年第3期23-25,34,共4页Industrial Heating

基　　金：云南省教育厅科学研究基金项目(042140D)

摘　　要：在控制系统中,除了控制器和控制算法很重要之外,传感器检测在控制系统中的地位也很重要。针对钢厂加热炉温度控制系统中的检测环节,以MATLAB为工具,提出应用前向多层神经网络建立热电偶的逆模型进行非线性映射,使得热电偶测量温度更加方便。这种方法准确、实用、控制精度高,大大方便了热电偶温度传感器在测控系统中的应用。In addition to the controller and the control algorithms, the measurement of the sensors is also important in the control system. This paper is aimed at the detection part of the steel furnace temperature control system, using MATLAB as a tool, and offers the proposal about application of multi-layer neural networks to the inverse of thermal resistance model of non-linear mapping, making the temperature measurement of thermocouple more convenient. It has been shown in practical applications that the method proposed not only is correct, practical and has high control precision, but also make it convenient for thermocouple to be applied on measurement and control systems.

关 键 词：加热炉 神经网络 热电偶 温度控制 

分 类 号：TF068.21[冶金工程—冶金物理化学] TP316.2[自动化与计算机技术—计算机软件与理论]