基于MATLAB实现的粒子群算法与人工鱼群算法的比较，体现了两种算法各自的优缺点+使用说明文档.rar

clc clear N=20; visual=1; step=0.01; maxnum=200; for i=1:N x(i,:)=4*rand(1,2)-2*ones(1,2); fitness(i)=f(x(i,:)); [fmin,index]=min(f(x(i,:))); xmin=x(index); end for k=1:maxnum for i=1:N nf=1; xc=[0,0]; for j=1:N if abs(x(i,:)-x(j,:))>0&((x(i,1)-x(j,1))^2+(x(i,2)-x(j,2))^2)^1/2<visual xc=xc+x(j,:); nf=nf+1; end end xc=xc/nf; if f(xc)<f(x(i,:)) xsnext(i,:)=x(i,:)+step.*(xc-x(i,:))./((xc(1)-x(i,1))^2+(xc(2)-x(i,2))^2)^1/2; else xsnext(i,:)=prey2(x(i,:)); end xmin=x(i,:); fmin=f(x(i,:)); for j=1:N if abs(x(i,:)-x(j,:))>0&((x(i,1)-x(j,1))^2+(x(i,2)-x(j,2))^2)^1/2<visual&f(x(j,:))<fmin xmin=x(j,:); fmin=f(x(j,:)); end end if xmin~=x(i,:) xfnext(i,:)=x(i,:)+step.*(xmin-x(i,:))./((xmin(1)-x(i,1))^2+(xmin(2)-x(i,2))^2)^1/2; xfnext(i,find(xfnext(i,:)>2))=2; xfnext(i,find(xfnext(i,:)<-2))=-2; else xfnext(i,:)=prey2(x(i,:)); end xnext=zeros(1,2); if f(xsnext(i,:))<f(xfnext(i,:)) xnext(i,:)=xsnext(i,:); else xnext(i,:)=xfnext(i,:); end x(i,:)=xnext(i,:); if f(xnext(i,:))<fmin fmin=f(xnext(i,:)); xmin=xnext(i,:); end end yy(k)=fmin ; end plot(yy,'r--') grid on title(['适应度曲线 ''终止代数=' num2str(maxnum)]); xlabel('进化代数'); ylabel('适应度'); xmin fmin %% 参数初始化 %粒子群算法中的两个参数 c1 = 1.49445; c2 = 1.49445; maxgen=200; % 进化次数 sizepop=20; %种群规模 Vmax=1; Vmin=-1; popmax=5; popmin=-5; %% 产生初始粒子和速度 for i=1:sizepop %随机产生一个种群 pop(i,:)=5*rands(1,2); %初始种群 V(i,:)=rands(1,2); %初始化速度 %计算适应度 fitness(i)=f(pop(i,:)); %染色体的适应度 end %找最好的染色体 [bestfitness bestindex]=min(fitness); zbest=pop(bestindex,:); %全局最佳 gbest=pop; %个体最佳 fitnessgbest=fitness; %个体最佳适应度值 fitnesszbest=bestfitness; %全局最佳适应度值 %% 迭代寻优 for i=1:maxgen for j=1:sizepop %速度更新 V(j,:) = V(j,:) + c1*rand*(gbest(j,:) - pop(j,:)) + c2*rand*(zbest - pop(j,:)); V(j,find(V(j,:)>Vmax))=Vmax; V(j,find(V(j,:)<Vmin))=Vmin; %种群更新 pop(j,:)=pop(j,:)+0.5*V(j,:); pop(j,find(pop(j,:)>popmax))=popmax; pop(j,find(pop(j,:)<popmin))=popmin; %自适应变异 if rand>0.8 k=ceil(2*rand); pop(j,k)=rand; end %适应度值 fitness(j)=f(pop(j,:)); end %个体最优更新 if fitness(j) < fitnessgbest(j) gbest(j,:) = pop(j,:); fitnessgbest(j) = fitness(j); end %群体最优更新 if fitness(j) < fitnesszbest zbest = pop(j,:); fitnesszbest = fitness(j); end yyy(i)=fitnesszbest; end hold on %% 结果分析 plot(yyy,'b') legend('AFSA','PSO') title(['适应度曲线 ' '终止代数＝' num2str(maxgen)]); xlabel('进化代数');ylabel('适应度'); hold off zbest fitnesszbest