鲸鱼算法matlab程序

以下是一个简单的鲸鱼算法的 Matlab 实现。在这个例子中，我们尝试最小化一个已知函数的值。请注意，这个程序只是一个示例，您需要根据自己的要求进行修改。

function [best, fmin] = whale_algorithm(max_iter, dim, lb, ub, fobj)
% Whale algorithm implementation in Matlab
% Inputs:
%   max_iter: Maximum number of iterations
%   dim: Number of dimensions
%   lb: Lower bound of search space
%   ub: Upper bound of search space
%   fobj: Objective function to minimize
% Outputs:
%   best: Best solution found
%   fmin: Best objective function value found

% Initialize population
pop_size = 30;
X = zeros(pop_size, dim);
for i = 1:pop_size
    X(i,:) = lb + (ub - lb) .* rand(1, dim);
end

% Initialize best solution
fX = feval(fobj, X');
[fmin, idx] = min(fX);
best = X(idx,:);

% Main loop
for t = 1:max_iter
    % Update position of whales
    a = 2 - t * (2 / max_iter); % Eq. (2.3)
    a2 = -1 + t * ((-1) / max_iter); % Eq. (2.4)
    for i = 1:pop_size
        r1 = rand(); % r1 is a random number in [0,1]
        r2 = rand(); % r2 is a random number in [0,1]
        A = 2 * a * r1 - a; % Eq. (2.1)
        C = 2 * r2; % Eq. (2.2)
        b = 1; % parameters in Eq. (2.5)
        l = (a2 - 1) * rand() + 1; % Eq. (2.5)
        p = rand(); % p in Eq. (2.6)
        if p < 0.5
            if abs(A) >= 1
                rand_leader_idx = floor(pop_size * rand() + 1);
                X_rand = X(rand_leader_idx, :);
                D_X_rand = abs(C * X_rand - X(i, :)); % Eq. (2.7)
                X(i, :) = X_rand - A * D_X_rand; % Eq. (2.8)
            else
                D_best = abs(C * best - X(i, :)); % Eq. (2.1)
                X(i, :) = best - A * D_best; % Eq. (2.3)
            end
        else
            distance_to_leader = abs(best - X(i, :));
            X(i, :) = distance_to_leader * exp(b * l) .* cos(2 * pi * l) + best; % Eq. (2.5)
        end
    end
    
    % Apply boundary constraints
    X(X < lb) = lb;
    X(X > ub) = ub;
    
    % Update best solution
    fX = feval(fobj, X');
    [fmin_new, idx] = min(fX);
    if fmin_new < fmin
        best = X(idx,:);
        fmin = fmin_new;
    end
    
    % Display progress
    disp(['Iteration ' num2str(t) ', Best objective function value = ' num2str(fmin)]);
end
end

在这个示例中，我们定义了一个需要最小化的目标函数，并将其传递给鲸鱼算法。在每次迭代中，算法更新每个鲸鱼的位置，并根据当前位置更新最佳解决方案。算法还对搜索空间进行了边界约束，确保每个鲸鱼的位置都在定义的搜索范围内。

您可以使用以下代码来运行这个示例：

% Define objective function to minimize
fobj = @(x) sum(x.^2);

% Define search space bounds
lb = -5;
ub = 5;

% Run whale algorithm
max_iter = 100;
dim = 10;
[best, fmin] = whale_algorithm(max_iter, dim, lb, ub, fobj);

在这个例子中，我们最小化了一个简单的二次函数，并将搜索空间限制在 -5 和 5 之间。您可以根据自己的需求修改这些参数。