论文部分内容阅读
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 characteristics of daily load change of industrial boiler room, the BP artificial neural network model is used to predict the heat load. In the model establishment, considering the difference of heat load in different hours, 24 single-output BP networks were used to predict the daily 24-hour load respectively. Using MATLAB neural network toolbox NNT (Neural Network Toolbox), 24 BP network prediction models Finally, an example is used to simulate the established forecasting model and its realization method. The results show that the load forecasting model has the advantages of small network structure, fast convergence rate and high prediction accuracy, and has high practical value.