分析了神经网络导向控制器的设计方法，选择了神经网络导向控制器的输入、输出变量，并建立了神经网络导向控制器的结构。
The design method of the new controller was analyzed, the input and output variables of the neural network navigation controller were selected, the structure of the controller was also established.
结果表明：对于矩形平面厅堂，选择少数与厅堂声级相关性高的几何、物理参量作为神经网络模型的输入变量，可以准确地预测厅堂声级。
It shows that the good agreements between measured and calculated results can be obtained if the basic parameters used as inputs to the first layer of the neutral network are reasonable.
应用推荐