【优化求解】基于蝗虫算法求解单目标问题matlab代码

你的名字 2022-09-17 05:18 245阅读 0赞

## 1 简介 ##

蝗虫算法( Grasshopper Optimization Algorithm，GOA ) 是 由 Saremi 等\[1\]于2017 年提出的一种元启发式仿生优化算法。具体原理如下：

![img][]

![img][img 1]

## 2 部分代码 ##

%**\_\_****\_\_****\_\_****\_\_****\_\_****\_\_****\_\_****\_\_****\_\_****\_\_****\_\_****\_\_****\_\_**\_\_\_

% Multi-objective Grasshopper Optimization Algorithm (MOGOA) source codes version 1.0

clc;

clear;

close all;

% Change these details with respect to your problem%%%%%%%%%%%%%%

ObjectiveFunction=@ZDT1;

dim=5;

lb=0;

ub=1;

obj\_no=2;

if size(ub,2)==1

ub=ones(1,dim)\*ub;

lb=ones(1,dim)\*lb;

end

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

flag=0;

if (rem(dim,2)~=0)

dim = dim+1;

ub = \[ub, 1\];

lb = \[lb, 0\];

flag=1;

end

max\_iter=100;

N=200;

ArchiveMaxSize=100;

Archive\_X=zeros(100,dim);

Archive\_F=ones(100,obj\_no)\*inf;

Archive\_member\_no=0;

%Initialize the positions of artificial whales

GrassHopperPositions=initialization(N,dim,ub,lb);

TargetPosition=zeros(dim,1);

TargetFitness=inf\*ones(1,obj\_no);

cMax=1;

cMin=0.00004;

%calculate the fitness of initial grasshoppers

for iter=1:max\_iter

for i=1:N

Archive\_mem\_ranks=RankingProcess(Archive\_F, ArchiveMaxSize, obj\_no);

\[Archive\_X, Archive\_F, Archive\_mem\_ranks, Archive\_member\_no\]=HandleFullArchive(Archive\_X, Archive\_F, Archive\_member\_no, Archive\_mem\_ranks, ArchiveMaxSize);

else

Archive\_mem\_ranks=RankingProcess(Archive\_F, ArchiveMaxSize, obj\_no);

end

Archive\_mem\_ranks=RankingProcess(Archive\_F, ArchiveMaxSize, obj\_no);

index=RouletteWheelSelection(1./Archive\_mem\_ranks);

if index==-1

index=1;

end

TargetFitness=Archive\_F(index,:);

TargetPosition=Archive\_X(index,:)';

c=cMax-iter\*((cMax-cMin)/max\_iter); % Eq. (3.8) in the paper

for i=1:N

temp= GrassHopperPositions;

for k=1:2:dim

S\_i=zeros(2,1);

for j=1:N

if i~=j

Dist=distance(temp(k:k+1,j), temp(k:k+1,i));

r\_ij\_vec=(temp(k:k+1,j)-temp(k:k+1,i))/(Dist+eps);

xj\_xi=2+rem(Dist,2);

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % Eq. (3.2) in the paper

s\_ij=((ub(k:k+1)' - lb(k:k+1)') .*c/2)*S\_func(xj\_xi).\*r\_ij\_vec;

S\_i=S\_i+s\_ij;

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

end

S\_i\_total(k:k+1, :) = S\_i;

end

X\_new=c\*S\_i\_total'+(TargetPosition)'; % Eq. (3.7) in the paper

GrassHopperPositions\_temp(i,:)=X\_new';

end

% GrassHopperPositions

GrassHopperPositions=GrassHopperPositions\_temp';

display(\['At the iteration ', num2str(iter), ' there are ', num2str(Archive\_member\_no), ' non-dominated solutions in the archive'\]);

end

if (flag==1)

TargetPosition = TargetPosition(1:dim-1);

end

figure

Draw\_ZDT1();

hold on

plot(Archive\_F(:,1),Archive\_F(:,2),'ro','MarkerSize',8,'markerfacecolor','k');

legend('True PF','Obtained PF');

title('MOGOA');

set(gcf, 'pos', \[403 466 230 200\])

img =gcf; %获取当前画图的句柄

print(img, '-dpng', '-r600', './img.png') %即可得到对应格式和期望dpi的图像

## 3 仿真结果 ##

![a44a237e2247a57a5571ac4497838af5.png][]

![598e0c9aa33daa16defe9dc329556ac3.png][]

## 4 参考文献 ##

\[1\]潘峰, and 孙红霞. "基于蝗虫算法的图像多阈值分割方法." 电子测量与仪器学报 033.001(2019):149-155.

![图片][88f53a26c4d6c3a7e9304c9298bb5582.png]

[img]: /images/20220828/bd648d1ec793425f8d5285d036bbe411.png
[img 1]: /images/20220828/c3dec3f81f5a44bfb9e0672e2c8d6909.png
[a44a237e2247a57a5571ac4497838af5.png]: /images/20220828/7c0e1d600d324c1ab04fe94abba97eb2.png
[598e0c9aa33daa16defe9dc329556ac3.png]: /images/20220828/c9bfde72507d45c3ab689f7a5f4361b3.png
[88f53a26c4d6c3a7e9304c9298bb5582.png]: /images/20220828/4c36f925cdb447d9a32e049679fd4c91.png