Question

求教：基于BP神经网络的Matlab故障诊断代码总是显示错误，哪位大哥帮忙给改一下吧代码在下面

P=[2.50 0.11 10.40 12.60 45.5;
0.24 0.36 10.30 0.30 48.2;
1.81 0.27 11.72 11.50 46.3;
1.77 0.22 10.33 14.43 50.0;
1.75 0.23 10.40 9.80 49.9;
1.82 0.25 10.33 12.50 72.2;
1.84 0.26 10.10 11.20 18.5];
T=[0.9 0.1 0.1 0.1 0.1 0.1 0.1;
0.1 0.9 0.1 0.1 0.1 0.1 0.1;
0.1 0.1 0.9 0.1 0.1 0.1 0.1;
0.1 0.1 0.1 0.9 0.1 0.1 0.1;
0.1 0.1 0.1 0.1 0.9 0.1 0.1;
0.1 0.1 0.1 0.1 0.1 0.9 0.1;
0.1 0.1 0.1 0.1 0.1 0.1 0.9];
threshold=[0.11 45.5;0.24 48.2;0.27 46.3;0.22 50.0;
0.23 49.9;0.25 72.2;0.26 18.5];
net=newff(threshold,[11 7],{'tansig','logsig'},'trainlm');
net.trainParam.epochs=15;
net.trainParam.goal=0.01;
LP.lr=0.1;
net=train(net,P,T);
选了3层神经网络，输入层有5个输入量，故障分为7个，针对每个故障选择了一个样本，在Matlab程序执行中总是弹出
??? Error using ==> network.train
Targets are incorrectly sized for network.
Matrix must have 5 columns.
这样的对话框，本人刚接触Matlab，不太明白咋回事，希望有哪位高手帮忙解决一下，先谢过大家啦～～

Answer 1

P=[2.50 0.11 10.40 12.60 45.5;
0.24 0.36 10.30 0.30 48.2;
1.81 0.27 11.72 11.50 46.3;
1.77 0.22 10.33 14.43 50.0;
1.75 0.23 10.40 9.80 49.9;
1.82 0.25 10.33 12.50 72.2;
1.84 0.26 10.10 11.20 18.5];
P=P'; %转置矩阵格式就对了
T=[0.9 0.1 0.1 0.1 0.1 0.1 0.1;
0.1 0.9 0.1 0.1 0.1 0.1 0.1;
0.1 0.1 0.9 0.1 0.1 0.1 0.1;
0.1 0.1 0.1 0.9 0.1 0.1 0.1;
0.1 0.1 0.1 0.1 0.9 0.1 0.1;
0.1 0.1 0.1 0.1 0.1 0.9 0.1;
0.1 0.1 0.1 0.1 0.1 0.1 0.9];
net=newff(minmax(P),[11 7],{'tansig','logsig'},'trainlm');%这里的矩阵大小范围可用minmax
net.trainParam.epochs=15;
net.trainParam.goal=0.01;
LP.lr=0.1;
net=train(net,P,T);