中文说明：利用了2层BP网络的各种train函数得到了 不同的函数逼近效果。其中，建议诸位采用trainlm作为训练函数，收敛速度快，效果好。bp网络第一层传输函数选择0-1之间，而第二层采用2500，目标误差设为10，初始学习率设为0.05
English Description：
Use of the two-layer BP network function of various train got different function approximation results.Which recommended you for using trainlm as a training function, convergence speed, good effect.bp network transfer function to choose between the first layer 0-1, and the second layer is made of 2500, the target is set to 10 errors, the initial learning rate is set to 0.05