摘要
为了进一步提高BP神经网络对含沙量预测的精度,采用小波函数作为BP神经网络的隐含层节点传递函数。结果表明:该方法克服了单一BP神经网络易陷入局部收敛等缺点,提出的小波神经网络模型预测结果更接近实际值。
In order to improve the precision of BP neural network for suspended sediment forecasting, a wavelet neural network model was established with the wavelet function as the transfer function between the panel points in the hidden layer of the BP neural network.The results show that the method overcame the shortcomings of the single BP neural network that it could easily fall into local convergence. The forecasting result of wavelet neural network model is closer to the actual value.
出处
《人民珠江》
2015年第6期47-49,共3页
Pearl River
关键词
小波函数
BP神经网络
含沙量
wavelet function
BP neural network
suspended sediment
