基于RBF神经网络的黄河含沙量测量数据融合研究

针对黄河含沙量高、泥沙时空分布不均和环境变化显著等特点,提出了采用电容式差压法来测量黄河含沙量,建立了基于RBF神经网络的含沙量测量的数学模型。将含沙量信息值与温度、深度和流速值作为RBF网络的输入,进行含沙量测量的反演和误差分析。试验结果表明,基于RBF的数据融合方法能够有效地消除环境影响,提高系统测量的精度和稳定性。

RBF neural networks based-study on data fusion for measurement of sediment concentration of Yellow River

In accordance with the characteristics of the Yellow River， such as high sediment concentration， uneven spatial and temporal distribution of sediment concentrations， significant environment change， etc.， it is proposed to measure the sediment concentration of the river with the of capacitive differential pressure， and then a RBF neural networks based-mathematical model for measuring the sediment concentration is established; for which the values of sediment concentration， water depth and velocity are taken as the input valued of the RBF networks for making the inversed and error analysis on the measurement of the sediment concentration. The experiment result shows that the RBF neural networks based-data fusion method can effectively eliminate the environmental impacts and then enhance both the accuracy and stability of the measurement.