遗传算法新手教学？（最好有案例，一步一步的分解）

这是本人见过最详细的步骤了：

需要如下主函数：

   编码和种群生成

 function [pop] = initializega(num,bounds,evalFN,evalOps,options)

% pop    - the initial, evaluated, random population

% num    - the size of the population, i.e. the number to create

% bounds - the number of permutations in an individual (e.g., number

%          of cities in a tsp

% evalFN - the evaluation fn, usually the name of the .m file for evaluation

% evalOps- any options to be passed to the eval function defaults [ ]

% options- options to the initialize function, ie. [eps, float/binary, prec]

%        where eps is the epsilon value and the second option is 1 for

%     orderOps, prec is the precision of the variables defaults [1e-6 1]

   交叉

function [c1,c2] = arithXover(p1,p2,bounds,Ops)

% Arith crossover takes two parents P1,P2 and performs an interpolation

% along the line formed by the two parents.

%

% function [c1,c2] = arithXover(p1,p2,bounds,Ops)

% p1      - the first parent ( [solution string function value] )

% p2      - the second parent ( [solution string function value] )

% bounds  - the bounds matrix for the solution space

% Ops     - Options matrix for arith crossover [gen #ArithXovers]

选择

normGeomSelect：NormGeomSelect is a ranking selection

 function based on the normalized geometric distribution.

（基于正态分布的序列选择函数）

变异

function[newPop] = normGeomSelect(oldPop,options)

% NormGeomSelect is a ranking selection function based on

 the normalized

% geometric distribution. 

%

% function[newPop] = normGeomSelect(oldPop,options)

% newPop  - the new population selected from the oldPop

% oldPop  - the current population

% options - options to normGeomSelect

[gen probability_of_selecting_best]

一些辅助函数：

    f2b ：Return the binary representation of the float number

 fval（将浮点数转化为二进制数）

    b2f：Return the float number corresponing to the binary

representation of bval. （将二进制数转化为

浮点数）

    nonUnifMutation： Non uniform mutation changes one

 of the parameters of the parent based on a non-uniform

probability distribution.  This Gaussian distribution starts wide,

 and narrows to a point distribution as the current generation

 approaches the maximum generation.

（基于非均一概率分布进行非均一变异）

maxGenTerm：Returns 1, i.e. terminates the GA when the

maximal_generation is reached.

（当迭代次数大于最大迭代次数时，终止遗传算法，返回

为1，否则返回为0。）

roulette：roulette is the traditional selection function with the

 probability of surviving equal to the fittness of i / sum of the

 fittness of all individuals

三、应用举例

1.计算下列函数的最大值。

 f(x)=x+10*sin(5x)+7cos(4x) , x∈[0,9]

 方式1  >>gademo

 方式2  

  step 1 编写目标函数gademo1eval1.m

function [sol, val] = gaDemo1Eval(sol,options)

x=sol(1);

val = x + 10*sin(5*x)+7*cos(4*x);

  step 2 生成初始种群，大小为10

  initPop=initializega(10,[0, 9],'gademo1eval1',[],[1e-6,1]);

step 3  25次遗传迭代

   [x, endPop,bpop,trace] = ga([0 9],'gademo1eval1',[],initPop,...

[1e-6 1 1],'maxGenTerm',25,...

              'normGeomSelect',[0.08],...

['arithXover'],[2],...

'nonUnifMutation',[2, 25 ,3])

% Output Arguments:

%   x    - the best solution found during the course of the

 run

%   endPop       - the final population

%   bPop         - a trace of the best population

                  (解的变化)

%   traceInfo    - a matrix of best and means of the ga

for each generation

(种群平均值的变化)

%

% Input Arguments:

%   bounds - a matrix of upper and lower bounds

 on the variables

%   evalFN  - the name of the evaluation .m function

%   evalOps

- options to pass to the evaluation function ([NULL])

%   startPop   - a matrix of solutions that can be initialized

%              from initialize.m

%   opts   - [epsilon, prob_ops ,display]

change required to consider two solutions

different, prob_ops 0 if you want to apply the

%            genetic operators probabilisticly to each