資源簡介
本代碼主要利用MATLAB工具進行灰色神經(jīng)網(wǎng)絡的預測算法的仿真,實現(xiàn)訂單需求預測的模擬

代碼片段和文件信息
web?browser?http://www.ilovematlab.cn/thread-64645-1-1.html
%%?清空環(huán)境變量
clc
clear
load?data
%%?數(shù)據(jù)累加作為網(wǎng)絡輸入
[nm]=size(X);
for?i=1:n
????y(i1)=sum(X(1:i1));
????y(i2)=sum(X(1:i2));
????y(i3)=sum(X(1:i3));
????y(i4)=sum(X(1:i4));
????y(i5)=sum(X(1:i5));
????y(i6)=sum(X(1:i6));
end
%%?網(wǎng)絡參數(shù)初始化
a=0.3+rand(1)/4;
b1=0.3+rand(1)/4;
b2=0.3+rand(1)/4;
b3=0.3+rand(1)/4;
b4=0.3+rand(1)/4;
b5=0.3+rand(1)/4;
%%?學習速率初始化
u1=0.0015;
u2=0.0015;
u3=0.0015;
u4=0.0015;
u5=0.0015;
%%?權值閥值初始化
t=1;
w11=a;
w21=-y(11);
w22=2*b1/a;
w23=2*b2/a;
w24=2*b3/a;
w25=2*b4/a;
w26=2*b5/a;
w31=1+exp(-a*t);
w32=1+exp(-a*t);
w33=1+exp(-a*t);
w34=1+exp(-a*t);
w35=1+exp(-a*t);
w36=1+exp(-a*t);
theta=(1+exp(-a*t))*(b1*y(12)/a+b2*y(13)/a+b3*y(14)/a+b4*y(15)/a+b5*y(16)/a-y(11));
kk=1;
%%?循環(huán)迭代
for?j=1:10
%循環(huán)迭代
E(j)=0;
for?i=1:30
????
????%%?網(wǎng)絡輸出計算
????t=i;
????LB_b=1/(1+exp(-w11*t));???%LB層輸出
????LC_c1=LB_b*w21;???????????%LC層輸出
????LC_c2=y(i2)*LB_b*w22;????%LC層輸出
????LC_c3=y(i3)*LB_b*w23;????%LC層輸出
????LC_c4=y(i4)*LB_b*w24;????%LC層輸出
????LC_c5=y(i5)*LB_b*w25;????%LC層輸出
????LC_c6=y(i6)*LB_b*w26;????%LC層輸出?
????LD_d=w31*LC_c1+w32*LC_c2+w33*LC_c3+w34*LC_c4+w35*LC_c5+w36*LC_c6;????%LD層輸出
????theta=(1+exp(-w11*t))*(w22*y(i2)/2+w23*y(i3)/2+w24*y(i4)/2+w25*y(i5)/2+w26*y(i6)/2-y(11));???%閥值
????ym=LD_d-theta;???%網(wǎng)絡輸出值
????yc(i)=ym;
????
????%%?權值修正
????error=ym-y(i1);??????%計算誤差
????E(j)=E(j)+abs(error);????%誤差求和???????
????error1=error*(1+exp(-w11*t));?????%計算誤差
????error2=error*(1+exp(-w11*t));?????%計算誤差
????error3=error*(1+exp(-w11*t));
????error4=error*(1+exp(-w11*t));
????error5=error*(1+exp(-w11*t));
????error6=error*(1+exp(-w11*t));
????error7=(1/(1+exp(-w11*t)))*(1-1/(1+exp(-w11*t)))*(w21*error1+w22*error2+w23*error3+w24*error4+w25*error5+w26*error6);
????
????%修改權值
????w22=w22-u1*error2*LB_b;
????w23=w23-u2*error3*LB_b;
????w24=w24-u3*error4*LB_b;
????w25=w25-u4*error5*LB_b;
????w26=w26-u5*error6*LB_b;
????w11=w11+a*t*error7;
end
end??
%畫誤差隨進化次數(shù)變化趨勢
figure(1)
plot(E)
title(‘訓練誤差‘‘fontsize‘12);
xlabel(‘進化次數(shù)‘‘fontsize‘12);
ylabel(‘誤差‘‘fontsize‘12);
%print?-dtiff?-r600?28-3
%根據(jù)訓出的灰色神經(jīng)網(wǎng)絡進行預測
for?i=31:36
????t=i;
????LB_b=1/(1+exp(-w11*t));???%LB層輸出
????LC_c1=LB_b*w21;???????????%LC層輸出
????LC_c2=y(i2)*LB_b*w22;????%LC層輸出
????LC_c3=y(i3)*LB_b*w23;????%LC層輸出
????LC_c4=y(i4)*LB_b*w24;????%LC層輸出
????LC_c5=y(i5)*LB_b*w25;
????LC_c6=y(i6)*LB_b*w26;
????LD_d=w31*LC_c1+w32*LC_c2+w33*LC_c3+w34*LC_c4+w35*LC_c5+w36*LC_c6;????%LD層輸出
????theta=(1+exp(-w11*t))*(w22*y(i2)/2+w23*y(i3)/2+w24*y(i4)/2+w25*y(i5)/2+w26*y(i6)/2-y(11));???%閥值
????ym=LD_d-theta;???%網(wǎng)絡輸出值
????yc(i)=ym;
end
yc=yc*100000;
y(:1)=y(:1)*10000;
%計算預測的每月需求量
for?j=36:-1:2
????ys(j)=(yc(j)-yc(j-1))/10;
end
figure(2)
plot(ys(31:36)‘-*‘);
hold?on
plot(X(31:361)*10000‘r:o‘);
legend(‘灰色神經(jīng)網(wǎng)絡‘‘實際訂單數(shù)‘)
title(‘灰色系統(tǒng)預測‘‘fontsize‘12)
xlabel(‘月份‘‘fontsize‘12)
ylabel(‘銷量‘‘fontsize‘12)
web?browser?http://www.ilovematlab.cn/thread-64645-1-1.html
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????文件???????1504??2009-12-28?11:56??案例28?灰色神經(jīng)網(wǎng)絡的預測算法—訂單需求預測\data.mat
?????文件???????3151??2010-01-30?20:28??案例28?灰色神經(jīng)網(wǎng)絡的預測算法—訂單需求預測\Greynet.m
?????目錄??????????0??2018-08-07?18:28??案例28?灰色神經(jīng)網(wǎng)絡的預測算法—訂單需求預測
-----------?---------??----------?-----??----
?????????????????4655????????????????????3
評論
共有 條評論