GAMULTIOBJ function does not take into account the upper bound (ub)

1 次查看（过去 30 天）

Haritz Odriozola Olalde 2021-7-29

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/888357-gamultiobj-function-does-not-take-into-account-the-upper-bound-ub

编辑： Haritz Odriozola Olalde 2021-7-29

Hi everyone,

I am designing an Genetic Algorythm for which the genes of the population must be between the values 0 and 150. For thius purpose, I have established the lower bound (lb) and the upper bound (ub) to 0 and 150 respectively as it can be seen in the code below.

    for i=1:numberOfVariables
        lb(i)= 0;                  % lower bound of the genes
        ub(i)= 150;                % upper bound of the genes
    end
            
    % Inequality restrictions definition
    A = []; b = [];                 % without inequality restrictions
    Aeq = []; beq = [];
    % GAMULTIOBJ solver execution
    options = gaoptimset('PlotFcns',[]);
    options = gaoptimset(options,'PopulationSize',numPop);   
    options = gaoptimset(options,'PopInitRange',[(-1);(1)]);
    options = gaoptimset(options,'CrossoverFcn',@crossoverheuristic);   
    options = gaoptimset(options,'MutationFcn',@mutationadaptfeasible);
    options = gaoptimset(options,'TimeLimit',tm);
    options = gaoptimset(options,'Generations',numGenerations);
   
    [x,Fval,exitFlag,Output] = gamultiobj (FitnessFunction,...
                              numberOfVariables,A,b,Aeq,beq,lb,ub,options);
     

Every time I execute the code, I have observed that the genes of the population values are between 0 and around 1.2 (it rarely exceeds 1 in any value) as it can be seen in the image below.