基于混沌理论的再热汽温神经网络模型

在利用混沌理论揭示火电机组再热汽温混沌动力学特性的基础上，构建了再热汽温神经网络预测模型。该模型利用混沌特性处理输入样本并确定神经网络的结构，用神经网络映射混沌相空间的相点演化的非线性关系，采用改进型遗传算法对神经网络模型进行参数辨识。仿真结果表明：该模型精度较高，收敛速度快，为实际生产过程中再热汽温的预测提供了一种新的思路和方法。

The Model of Neural Network Based on Chaos Theory for Reheated Steam Temperature

Chaos theory is adopted to reveal the chaotic dynamics performance of reheated steam temperature in fossil fired power station, a new predictive model of neural network for reheated steam temperature is established based on the chaos theory. In the model, chaotic performance is used to deal with input samples and determine structure of neural network, the mapping with neural network is used to describe non-linearity of point evolution of chaotic phase space, and parameter identification is done by improved genetic algorithm. Simulation results show that the model features higher precision and faster convergence speed. It also offers a new thought and method for prediction of reheated steam temperature during actual production.