15ej??pijlnpij,j?1,2,?8. ?ln10i?1 （3）计算第j项指标的变异系数gj。对于第j项指标，ej越大，指标值的变异程度就越小。变异系数
gj?1?ej,j?1,2,?,9.
（4）计算第j项指标的权重
wj?gj?gj?19,j?1,2,?,9.
j（5）计算第i个评价对象的综合评价值
si??wjpij.
j?19评价值越大越好。
利用MATLAB计算得到的各指标变量的权重值如表 7所示，各矿井的综合评价值如表 8所示。综合排名次序依次为西铭矿、西曲矿、杜尔坪矿、官地矿、白
家庄矿。
表 7 各指标的评价权重 指标 原煤成本 原煤利润 原煤产量 原煤销售量 商品煤灰分 -0.0016 全员效率 0.0266 流动资金周转天数 -0.1380 资源回收率 0.0002 百万吨死亡率 -0.7540 权-0.0006 0.0750 0.0002 0.003 重 表 8 矿井的综合评价值 白家庄矿 -0.4082 杜尔坪矿 -0.1287 西铭矿 -0.0422 官地矿 -0.1379 西曲矿 -0.0718 si 附录 附录一
clc,clear
a=[99.89 103.69 97.42 101.11 97.21 96.91 124.78 66.44 143.96 88.36 102.63 101.85 104.39 100.94 100.64 98.47 103.16 109.17 104.39 91.90 87.51 90.27 93.77 94.33 85.21 108.35 106.39 142.35 121.91 158.61 71.67 137.16 97.65 171.31 204.52 103.25 100 100 99.13 100.22
171.2 51.35 15.9 53.72 20.78]; a=a';
[m,n]=size(a); for j=[1 5 7 9]
b(:,j)=(max(a(:,j))-a(:,j))/(max(a(:,j))-min(a(:,j))); end
for j=[2 3 4 6 8]
b(:,j)=(a(:,j)-min(a(:,j)))/(max(a(:,j))-min(a(:,j))); end
d=sum(b,2); f=d./9;
附录二
clc,clear
a=[99.89 103.69 97.42 101.11 97.21 96.91 124.78 66.44 143.96 88.36 102.63 101.85 104.39 100.94 100.64 98.47 103.16 109.17 104.39 91.90 87.51 90.27 93.77 94.33 85.21 108.35 106.39 142.35 121.91 158.61 71.67 137.16 97.65 171.31 204.52 103.25 100 100 99.13 100.22 171.2 51.35 15.9 53.72 20.78]; a=a';
[m,n]=size(a); for j=[1 5 7 9]
b(:,j)=(max(a(:,j))-a(:,j))/(max(a(:,j))-min(a(:,j))); end
for j=[2 3 4 6 8]
b(:,j)=(a(:,j)-min(a(:,j)))/(max(a(:,j))-min(a(:,j))); end
he=sum(b,2);
c=[1 2 4 4 4 6 6 6 6 1/2 1 2 2 2 3 3 3 3 1/4 1/2 1 1 1 1 2 2 2 1/4 1/2 1 1 1 1 2 2 2 1/4 1/2 1 1 1 1 2 2 2 1/6 1/3 1 1 1 1 2 2 2 1/6 1/3 1/2 1/2 1/2 1/2 1 1 1 1/6 1/3 1/2 1/2 1/2 1/2 1 1 1 1/6 1/3 1/2 1/2 1/2 1/2 1 1 1 ];
[w,d]=eigs(c,1) w=w/sum(w)
pj=b*w,[fenshu,ind]=sort(pj,'descend')
附录三
clc,clear
a=[99.89 103.69 97.42 101.11 97.21 96.91 124.78 66.44 143.96 88.36 102.63 101.85 104.39 100.94 100.64 98.47 103.16 109.17 104.39 91.90 87.51 90.27 93.77 94.33 85.21 108.35 106.39 142.35 121.91 158.61 71.67 137.16 97.65 171.31 204.52 103.25 100 100 99.13 100.22 171.2 51.35 15.9 53.72 20.78]; a=a';
[m,n]=size(a); for j=[1 5 7 9]
b(:,j)=(max(a(:,j))-a(:,j))/(max(a(:,j))-min(a(:,j))); end
for j=[2 3 4 6 8]
b(:,j)=(a(:,j)-min(a(:,j)))/(max(a(:,j))-min(a(:,j))); end
cankao=max(b')';
t=repmat(cankao,[1,n])-b; mmin=min(min(t)); mmax=max(max(t)); rho=0.5;
xs=(mmin+rho*mmax)./(t+rho*mmax) gld=mean(xs,2)
[sgld,ind2]=sort(gld,'descend') xlswrite('book1.xls',[xs,gld])
附录四
clc,clear
a=[99.89 103.69 97.42 101.11 97.21 96.91 124.78 66.44 143.96 88.36 102.63 101.85 104.39 100.94 100.64 98.47 103.16 109.17 104.39 91.90 87.51 90.27 93.77 94.33 85.21 108.35 106.39 142.35 121.91 158.61 71.67 137.16 97.65 171.31 204.52 103.25 100 100 99.13 100.22 171.2 51.35 15.9 53.72 20.78]; a=a';
[m,n]=size(a);
for j=[1 5 7 9]
b(:,j)=(max(a(:,j))-a(:,j))/(max(a(:,j))-min(a(:,j))); end
for j=[2 3 4 6 8]
b(:,j)=(a(:,j)-min(a(:,j)))/(max(a(:,j))-min(a(:,j))); end
cstar=max(b); c0=min(b); for i=1:m
dstar(i)=norm(b(i,:)-cstar); d0(i)=norm(b(i,:)-c0); end
f=d0./(d0+dstar);
[sf,ind]=sort(f,'descend');
附录五
clc,clear
a=[99.89 103.69 97.42 101.11 97.21 96.91 124.78 66.44 143.96 88.36 102.63 101.85 104.39 100.94 100.64 98.47 103.16 109.17 104.39 91.90 87.51 90.27 93.77 94.33 85.21 108.35 106.39 142.35 121.91 158.61 71.67 137.16 97.65 171.31 204.52 103.25 100 100 99.13 100.22 171.2 51.35 15.9 53.72 20.78]; a=a';
[m,n]=size(a); for j=1:n
p(:,j)=a(:,j)/sum(a(:,j));
e(j)=-sum(p(:,j).*log(p(:,j)))/log(m); end g=1-e; w=g/sum(g); for j=[1 5 7 9] w(j)=-w(j); end s=w*p'