基于BP神经网络的工业锅炉房负荷预测

Boiler Plant Load Forecasting Based on BP Artificial Neural Network

针对工业锅炉房日负荷变化的特点,采用BP人工神经网络模型对热负荷进行预测。在建立模型时,考虑不同小时的热负荷差异,采用24个单输出的BP网络来分别预测每天24h负荷值;利用MATLAB神经网络工具箱NNT(Neural Network Toolbox)分别实现对24个BP网络预测模型的构建及算法改进;最后,应用一个实例对建立的预测模型和实现方法进行了仿真分析,结果证明,该负荷预测模型网络结构小、收敛速度快、预测精度高、具有较高的实用价值。

According to the varying characteristics of boiler plant daily thermal load, the thermal load forecasting method based on BP neural network is presented. Considering the thermal load diversity of different hour type, 24 single neural network models to forecast every hour load per day are built. Appropriate modified BP algorithms and constructing methods for 24 forecasting models are given based on MATLAB＇s neural networks toolbox. Finally the stimulating application example of prediction models and achieving methods is given out. The results shows the forecasting model has simple structure, shorting training time, better forecasting precision, and higher feasible value.