close all
clear
echo on
clc
%BP建模
%原始數據歸一化
m_data=[1047.92 1047.83 0.39 0.39 1.0 3500 5075;
1047.83 1047.68 0.39 0.40 1.0 3452 4912;
1047.68 1047.52 0.40 0.41 1.0 3404 4749;
1047.52 1047.27 0.41 0.42 1.0 3356 4586;
1047.27 1047.41 0.42 0.43 1.0 3308 4423;
1046.73 1046.74 1.70 1.80 0.75 2733 2465;
1046.74 1046.82 1.80 1.78 0.75 2419 2185;
1046.82 1046.73 1.78 1.75 0.75 2105 1905;
1046.73 1046.48 1.75 1.85 0.70 1791 1625;
1046.48 1046.03 1.85 1.82 0.70 1477 1345;
1046.03 1045.33 1.82 1.68 0.70 1163 1065;
1045.33 1044.95 1.68 1.71 0.70 849 785;
1044.95 1045.21 1.71 1.72 0.70 533 508;
1045.21 1045.64 1.72 1.70 0.70 567 526;
1045.64 1045.44 1.70 1.69 0.70 601 544;
1045.44 1045.78 1.69 1.69 0.70 635 562;
1045.78 1046.20 1.69 1.52 0.75 667 580];
%定義網絡輸入p和期望輸出t
pause
clc
p1=m_data(:,1:5);
t1=m_data(:,6:7);
p=p1';t=t1';
[pn,minp,maxp,tn,mint,maxt]=premnmx(p,t)
%設置網絡隱單元的神經元數(5~30驗證后5個最好）
n=5;
%建立相應的BP網絡
pause
clc
net=newff(minmax(pn),[n,2],{'tansig','purelin'},'traingdm');
inputWeights=net.IW{1,1};
inputbias=net.b{1};
layerWeights=net.IW{1,1};
layerbias=net.b{2};
pause
clc
% 訓練網絡
net.trainParam.show=50;
net.trainParam.lr=0.05;
net.trainParam.mc=0.9;
net.trainParam.epochs=2000;
net.trainParam.goal=1e-3;
pause
clc
%調用TRAINGDM算法訓練BP網絡
net=train(net,pn,tn);
%對BP網絡進行仿真
A=sim(net,pn);
E=A-tn;
M=sse(E)
N=mse(E)
pause
clc
p2=[1046.20 1046.05 1.52 1.538 0.75;
1046.05 1046.85 1.538 1.510 0.75;
1046.85 1046.60 1.510 1.408 0.75;
1046.60 1046.77 1.408 1.403 0.75;
1046.77 1047.18 1.403 1.319 0.75];
p2=p2';
p2n=tramnmx(p2,minp,maxp);
a2n=sim(net,p2n);
a2=postmnmx(a2n,mint,maxt)
echo off
pause
clc