附页:一.遗传算法源程序:clc;clear;population;%评价目标函数值foruim=1:popsizevector=population(uim,:);obj(uim)=hanshu(hromlength,vector,phen);end%obj%min(obj)clearuim;objmin=min(obj);forsequ=1:popsizeifobj(sequ)==objminopti=population(sequ,:);endendclearsequ;fmax=22000;%==forgen=1:maxgen%选择操作%将求最小值的函数转化为适应度函数forindivi=1:popsizeobj1(indivi)=1/obj(indivi);endclearindivi;%适应度函数累加总合total=0;forindivi=1:popsizetotal=total+obj1(indivi);endclearindivi;%每条染色体被选中的几率forindivi=1:popsizefitness1(indivi)=obj1(indivi)/total;endclearindivi;%各条染色体被选中的范围forindivi=1:popsizefitness(indivi)=0;forj=1:indivifitness(indivi)=fitness(indivi)+fitness1(j);endendclearj;fitness;%选择适应度高的个体forranseti=1:popsizeran=rand;while(ran1||ran0)ran=rand;endran;ifran=fitness(1)newpopulation(ranseti,:)=population(1,:);elseforfet=2:popsizeif(ranfitness(fet-1))&&(ran=fitness(fet))newpopulation(ranseti,:)=population(fet,:);endendendendclearran;newpopulation;%交叉forint=1:2:popsize-1popmoth=newpopulation(int,:);popfath=newpopulation(int+1,:);popcross(int,:)=popmoth;popcross(int+1,:)=popfath;randnum=rand;if(randnumPcpoint1=round(rand*hromlength);cpoint2=round(rand*hromlength);while(cpoint2==cpoint1)cpoint2=round(rand*hromlength);endifcpoint1cpoint2tem=cpoint1;cpoint1=cpoint2;cpoint2=tem;endcpoint1;cpoint2;forterm=cpoint1+1:cpoint2forss=1:hromlengthifpopcross(int,ss)==popfath(term)tem1=popcross(int,ss);popcross(int,ss)=popcross(int,term);popcross(int,term)=tem1;endendcleartem1;endforterm=cpoint1+1:cpoint2forss=1:hromlengthifpopcross(int+1,ss)==popmoth(term)tem1=popcross(int+1,ss);popcross(int+1,ss)=popcross(int+1,term);popcross(int+1,term)=tem1;endendcleartem1;endendclearterm;endclearrandnum;popcross;%变异操作newpop=popcross;forint=1:popsizerandnum=rand;ifrandnumcpoint12=round(rand*hromlength);cpoint22=round(rand*hromlength);if(cpoint12==0)cpoint12=1;endif(cpoint22==0)cpoint22=1;endwhile(cpoint22==cpoint12)cpoint22=round(rand*hromlength);ifcpoint22==0;cpoint22=1;endendtemp=newpop(int,cpoint12);newpop(int,cpoint12)=newpop(int,cpoint22);newpop(int,cpoint22)=temp;endendnewpop;clearcpoint12;clearcpoint22;clearrandnum;clearint;forium=1:popsizevector1=newpop(ium,:);obj1(ium)=hanshu(hromlength,vector1,phen);endclearium;obj1max=max(obj1);forar=1:popsizeifobj1(ar)==obj1maxnewpop(ar,:)=opti;endend%遗传操作结束二.粒子群算法源程序:%------初始格式化--------------------------------------------------clearall;clc;formatlong;%------给定初始化条件----------------------------------------------c1=1.4962;%学习因子1c2=1.4962;%学习因子2w=0.7298;%惯性权重MaxDT=100;%最大迭代次数D=2;%搜索空间维数(未知数个数)N=40;%初始化群体个体数目eps=10^(-6);%设置精度(在已知最小值时候用)%------初始化种群的个体(可以在这里限定位置和速度的范围)------------fori=1:Nforj=1:Dx(i,j)=randn;%随机初始化位置v(i,j)=randn;%随机初始化速度endend%------先计算各个粒子的适应度,并初始化Pi和Pg----------------------fori=1:Np(i)=fitness(x(i,:),D);y(i,:)=x(i,:);endpg=x(1,:);%Pg为全局最优fori=2:Niffitness(x(i,:),D)FITNESS(pg,D)pg=x(i,:);endend%------进入主要循环,按照公式依次迭代,直到满足精度要求------------fort=1:MaxDTtfori=1:Nv(i,:)=w*v(i,:)+c1*rand*(y(i,:)-x(i,:))+c2*rand*(pg-x(i,:));x(i,:)=x(i,:)+v(i,:);iffitness(x(i,:),D)p(i)p(i)=fitness(x(i,:),D);y(i,:)=x(i,:);endifp(i)FITNESS(pg,D)pg=y(i,:);endendPbest(t)=fitness(pg,D);end%------进入主要循环,按照公式依次迭代,直到满足精度要求------------fort=1:MaxDTfori=1:Nv(i,:)=w*v(i,:)+c1*rand*(y(i,:)-x(i,:))+c2*rand*(pg-x(i,:));x(i,:)=x(i,:)+v(i,:);iffitness(x(i,:),D)p(i)p(i)=fitness(x(i,:),D);y(i,:)=x(i,:);endifp(i)FITNESS(pg,D)pg=y(i,:);endendPbest(t)=fitness(pg,D);end%------最后给出计算结果disp('*************************************************************')disp('函数的全局最优位置为:')Solution=pg'disp('最后得到的优化极值为:')Result=fitness(pg,D)disp('*************************************************************')[X,Y]=meshgrid(-500:2:500);Z=X.*sin(sqrt(X))+Y.*(sin(sqrt(Y)));holdoncontour(X,Y,Z)plot(x(:,1),x(:,2),'*');holdoff