说明：  一个简单的BP网络拟合问题，把位置系统看成是一个黑箱，首先用系统输入输出数据训练BP神经网络，使网络能够表达该未知函数，然后用训练好的BP神经网络预测系统输出。
(A simple BP network fitting problem regards the position system as a black box. First, the BP neural network is trained with the input and output data of the system so that the network can express the unknown function. Then, the trained BP neural network is used to predict the output of the system.)