求助

422258511

p=[724.570000000000,739.774223126620,771.489090673942,804.563606600594,839.056060404793,875.027240514377,912.540541418428,951.662075391767,992.460789009143,1035.00858465455]
t=[724.570000000000,746.620000000000,778.270000000000,800.800000000000,827.750000000000,871.100000000000,912.370000000000,954.280000000000,995.010000000000,1037.20000000000]
- e# W( u# G, v: ?. ^7 b [pn,minp,maxp,tn,mint,maxt]=premnmx(p,t);          %原始数据归一化

: I8 i0 f3 E5 r" ?* Enet=newff(minmax(pn),[9,1],{'tansig','purelin'},'traingdx'); %设置网络,建立相应的BP网络
net.trainParam.show=2000; % 训练网络
+ L1 D8 Z3 G2 V1 S" P. n+ @net.trainParam.lr=0.01;
/ e; U# t! _8 q9 I% ^9 T4 anet.trainParam.epochs=10000;
net.trainParam.goal=1e-5;
$ u% C! f7 F  j" @8 }8 A) U[net,tr]=train(net ,pn,tn);                              %调用TRAINGDM算法训练BP网络
2 |! G, {$ }2 p, {8 b/ x3 _& R
an=sim(net,pn);                               %对BP网络进行仿真
a=postmnmx(an,mint,maxt);                     %还原数据
- O0 x! B: _" b* |x=2001:2010;
newk=a(1,;
plot(x,newk,'r-o',x,t,'b--+')
. M: \1 w4 r9 q1 alegend('网络输出值/万人','实际人口数/万人');
xlabel('年份');
4 p8 w! i1 D1 p' O) b8 mylabel('人口数');
title('预测人口数对比表');

2 v' V+ w- x2 ~, Ypnew1=[1079.38044723977,1125.65457635540,1173.91252408743,1224.23933874207,1276.72371473226,1331.45814888992,1388.53910347951,1448.06717620014,1510.14727747579,1574.88881534617]
pnew=pnew1
' K& O3 {' Z" R5 ipnewn=tramnmx(pnew,minp,maxp);
& [  U) g6 s/ @, sanewn=sim(net,pnewn);                               %对BP网络进行仿真
0 K  D3 b5 B- S$ H5 zanew=postmnmx(anewn,mint,maxt);                     %还原数据
y=anew'

- o9 l3 @) r) W3 Q3 f3 E9 s/ E
: Y, V( @* k* f. u预测的结果怎么都一样呀？》？？求助

wssl103050