|
基于改进型遗传算法的再热汽温神经网络模型构建及预测分析
|
| 陈耀龙,张韵辉 |
(东南大学 动力系, 江苏 南京 210096) |
 摘要：在根据混沌理论非线性重构技术揭示火电机组再热汽温变化的混沌动力学特性的基础上,构建了
基于改进型遗传算法(AGA)的再热汽温神经网络模型。该模型利用混沌特性处理输入样本及确定神
经网络的网络结构,用神经网络映射混沌相空间相点演化的非线性关系,采用AGA对神经网络模型进
行参数辨识。训练结果表明,该模型精度较高,收敛速度快,为生产实际过程中预测机组再热汽温提供
了一种新的思路和方法。
|
| 关键词：混沌;改进型遗传算法;神经网络;再热汽温 |
| 中图分类号:TK323 文献标识码:A 文章编号:1000-8829(2006)06-0030-05 |
| Construction and Predict Analysis of a Neural Network Modelof Reheated Vapor Temperature Based on Advanced Genetic Algorithm |
| CHEN Yao-long, ZHANG Yun-hui |
| (Department of Power, Southeast University, Nanjing 210096, China) |
| Abstract：Reconstruction in nonlinear chaotictheory is adopted to reveal the chaotic dynamics performance of
reheated vaportemperature in power station. Chaotic performance is used to deal with input samples and determine structure of neural network, neural network mapping is used to describe nonlinear of point in reconstruction phasespace, and parameter identification is done by advancedgenetic algorithm(AGA).So a new predic-
ting model of neural network basedon AGA is made.By sample straining,the model has higher precision and
quick convergence speed,which is significant in predicting reheated vapor temperature.
|
| Key words：chaos; advanced genetic algorithm; neural network; reheated vapourtem perature |
|
|
|
