超临界机组负荷汽压特性神经网络逆模型研究  

Study of Neural Network Inverse Model for Load and Main Steam Pressure Characteristics of Supercritical Power Generating Unit

作　　者：马良玉[1] 王智燕 高志元[1] 马永光[1] 

机构地区：[1]华北电力大学控制与计算机工程学院,保定071003

出　　处：《自动化与仪表》2013年第12期5-8,23,共5页Automation & Instrumentation

基　　金：国家自然科学基金项目(61174111);中央高校基本科研业务费专项资金项目(09MG21)

摘　　要：以采用先进的神经网络逆控制方法改善超临界机组协调控制品质为目的,针对某600 MW超临界机组,在分析机组运行特点和协调控制方式的基础上,采用BP神经网络分别建立了超临界机组负荷、主汽压力特性的逆系统模型。仿真实验表明:该模型结构简单、精度高、泛化能力强,可满足协调系统智能逆控制器的设计要求,具有较好的工程实用意义。To improve the supercritical power generating unit＇s coordinated control quality with advanced neural net- work inverse control method,BP neural network was applied to establish the inverse system models for the load and the main steam pressure of a 600MW supercritieal boiler unit by analyzing the characteristics of the supercritieal boiler unit and its coordinated control modes. Simulation results showed that the model of simple structure,high pre- cision and good generalization ability. It can be used for neural network inverse controller design for the coordinated control system and meet engineering application need.

关 键 词：超临界锅炉机组 协调控制 人工神经网络 逆系统模型 智能控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]