gademoleeval.asv

根据解空间的维数可以将优化问题分为一维空间优化和多元优化问题。本程序以求函数：f(x)=x+10*sin(5x)+7*cos(4x),0=<x<=9为例说明遗传算法的源程序

function[sol,eval]=gaDemolEeval(sol,options)
x=sol(1);
eval=x+10*sin(5*x)+7*cos(4*x);
clc
fplot('x+10*sin(5*x)+7*cos(4*x)',[0 9])
initPop=initializega(10,[0 9],'gademoleeval1');
plot(initPop(:,1),initPop(:,2),'b*')
[x endPop]=ga([0 9],'gademoleeval1',[],initPop,[le-5...1 1],
   'maxGenTerm',1,'normGeomSelect',[0.08],['arithXover'],...[20],
    'nonUnifMutation',[2 1 3]);
plot(endPop(:,1),endPop(:,2),'bo')
[x endPop bpop trace]=ga([0 9],'gademoleeval1',[],initPop,[le-6 1 1],
   'maxGenTerm',25,'normGeomSelect',[0.08],['arithXover'],[2],
    'nonUnifMutation',[2 25 3]);
plot(endPop(:,1),endPop(:,2),'y*')
figure(2)
plot(trace(:,1),trace(:,3),'y-')
hold on
plot(trace(:,1),trace(:,2),'r-')
xlabel('Generation');ylabel('Fittness');
legend('解的变化','种群平均值的变化')；