流域产流产沙BP网络预报模型的初步研究

运用 BP神经网络模型的基本原理 ,以流域降水条件为基本因子 ,建立了流域产流产沙 BP网络预报模型。该模型能用于定量分析流域人类活动因素对流域产流产沙的影响。西汉水、大通江、香溪河流域资料验证表明 ,模型基本合理、可靠。

汽雾冷却时炉壳温度的BP网络预报

为了提高转炉炉壳的寿命,有必要对炉壳温度进行量化。用有限元计算采集训练数据,以BP网络为手段,对不同水流通量、不同时刻的汽雾冷却转炉炉壳的瞬态温度进行了预报。预报结果同有限元结果对比表明,预报精度可满足工程应用。

基于BP神经网络模型的月径流预报

针对水文系统的高度非线性关系,采用BP神经网络模型,通过经验公式和迭代得到隐藏层个数,使用L-M(Levenberg-Marquardt)算法优化权值,分别建立2-3-1和4-8-1网络拓扑结构的BP_(1)、BP_(2)模型,选取永翠河流域中的带岭(二)站的实测数据进行径流预报。结果表明,BP_(1)模型的拟合度高,预测结果的合格率低,出现此情况的原因可能为数据样本较少,模型陷入局部最优。BP_(2)模型的拟合较前者低,但合格率高,且预测结果可达到精度要求,可作为径流模拟的方法之一,为流域径流模拟提供依据。

Water quality forecast through application of BP neural network at Yuqiao reservoir

This paper deals with the study of a water quality forecast model through application of BP neural network technique and GUI (Graphical User Interfaces) function of MATLAB at Yuqiao reservoir in Tianjin. To overcome the shortcomings of traditional BP algorithm as being slow to converge and easy to reach extreme minimum value,the model adopts LM (Leven-berg-Marquardt) algorithm to achieve a higher speed and a lower error rate. When factors affecting the study object are identified,the reservoir's 2005 measured values are used as sample data to test the model. The number of neurons and the type of transfer functions in the hidden layer of the neural network are changed from time to time to achieve the best forecast results. Through simulation testing the model shows high efficiency in forecasting the water quality of the reservoir.