交通噪声预测的神经网络模型

运用 Matlab语言编程 ,构造预测交通噪声的 LM算法 BP神经网络模型 ,把预测因子 (轻、重型车流量、平均车速、受声点距路肩距离、敏感点高差 )作为样本输入到网络模型 ,噪声等效声级作为样本输出 ,反复训练网络 ,通过增加隐含层节点数、改进算法 ,以降低误差 ,缩短训练时间。

Neural network for predicting traffic noise

BP neural network of LM calculation method was designed with Matlab language for predicting the road traffic noise.The fluence factors as the traffic flowing ,average vehicle speed, height differences at sensitive locations and the distance between the noise reception location and the road shoulder at the monitoring spots were input as samples,and the equivalent acoustic levels were output. The results show that the errors is reduced and the training time is shorted by increasing the number of hidden layer neuron and improving the calculation method.