遗传算法 多目标 c++

admin

1. #include <iostream>
2. #include <vector>
3. #include <algorithm>
4. #include <random>
6. // 定义染色体结构体
7. struct Chromosome {
8.     std::vector<int> genes;
9.     int fitness;
11.     Chromosome(int size) : genes(size), fitness(0) {
12.         std::random采用device rd;
13.         std::mt19937 gen(rd());
14.         std::uniform采用int采用distribution<> dis(0, 1);
15.         for (int& gene : genes) {
16.             gene = dis(gen);
17.         }
18.     }
19. };
21. // 定义比较函数，用于选择操作
22. bool compare(Chromosome& c1, Chromosome& c2) {
23.     return c1.fitness > c2.fitness;
24. }
26. // 计算适应度函数
27. int calculateFitness(const std::vector<Chromosome>& population) {
28.     int sum = 0;
29.     for (const Chromosome& c : population) {
30.         // 在这里根据具体的问题定义适应度函数
31.         // 这里只是作为示例，假设适应度函数为基因中1的个数
32.         int fitness = std::count采用if(c.genes.begin(), c.genes.end(), [](int g) { return g == 1; });
33.         sum += fitness;
34.         c.fitness = fitness;
35.     }
36.     return sum;
37. }
39. // 选择操作
40. std::vector<Chromosome> selection(const std::vector<Chromosome>& population, int size) {
41.     std::vector<Chromosome> selected;
42.     std::random采用device rd;
43.     std::mt19937 gen(rd());
44.     std::uniform采用int采用distribution<> dis(0, population.size() - 1);
46.     while (selected.size() < size) {
47.         int idx1 = dis(gen);
48.         int idx2 = dis(gen);
49.         Chromosome c1 = population[idx1];
50.         Chromosome c2 = population[idx2];
52.         // 使用比较函数进行选择
53.         if (compare(c1, c2)) {
54.             selected.push采用back(c1);
55.         } else {
56.             selected.push采用back(c2);
57.         }
58.     }
60.     return selected;
61. }
63. // 交叉操作
64. void crossover(const std::vector<Chromosome>& parents, std::vector<Chromosome>& offspring) {
65.     std::random采用device rd;
66.     std::mt19937 gen(rd());
67.     std::uniform采用int采用distribution<> dis(1, parents[0].genes.size() - 2);
69.     for (size采用t i = 0; i < parents.size() / 2; i++) {
70.         size采用t idx = i * 2;
71.         Chromosome parent1 = parents[idx];
72.         Chromosome parent2 = parents[idx + 1];
73.         Chromosome child1, child2;
75.         size采用t crossoverPoint = dis(gen);
76.         std::vector<int> genes1(parent1.genes.begin(), parent1.genes.begin() + crossoverPoint);
77.         std::vector<int> genes2(parent2.genes.begin() + crossoverPoint, parent2.genes.end());
79.         child1.genes = genes1;
80.         child1.genes.insert(child1.genes.end(), genes2.begin(), genes2.end());
81.         child1.fitness = calculateFitness({ parent1, parent2 }) / 2;
83.         genes1 = parent2.genes.begin(), parent2.genes.begin() + crossoverPoint;
84.         genes2 = parent1.genes.begin() + crossoverPoint, parent1.genes.end();
86.         child2.genes = genes1;
87.         child2.genes.insert(child2.genes.end(), genes2.begin(), genes2.end());
88.         child2.fitness = calculateFitness({ parent1, parent2 }) / 2;
90.         offspring.push采用back(child1);
91.         offspring.push采用back(child2);
92.     }
93. }
95. // 变异操作
96. void mutation(std::vector<Chromosome>& population, double mutationRate) {
97.     std::random采用device rd;
98.     std::mt19937 gen(rd());
99.     std::uniform采用int采用distribution<> dis(0, 1);
101.     for (Chromosome& c : population) {
102.         for (int& gene : c.genes) {
103.             if (dis(gen) < mutationRate) {
104.                 gene = 1 - gene;
105.             }
106.         }
107.     }
108. }
110. // 主函数
111. int main() {
112.     const int populationSize = 50;
113.     const int generationCount = 100;
114.     const double mutationRate = 0.01;
115.     const int tournamentSize = 4;
116.     const int elitismCount = 2;
118.     std::vector<Chromosome> population(populationSize);
120.     // 初始化种群
121.     for (Chromosome& c : population) {
122.         c = Chromosome(c.genes.size());
123.     }
125.     // 进行遗传算法优化
126.     for (int generation = 0; generation < generationCount; generation++) {
127.         // 计算种群的适应度
128.         int sumFitness = calculateFitness(population);
130.         // 选择操作
131.         std::vector<Chromosome> selected = selection(population, populationSize);
133.         // 交叉操作
134.         std::vector<Chromosome> offspring;
135.         crossover(selected, offspring);
137.         // 变异操作
138.         mutation(offspring, mutationRate);
140.         // 选择精英个体
141.         std::vector<Chromosome> elite(population.begin(), population.begin() + elitismCount);
142.         std::sort(population.begin() + elitismCount, population.end(), compare);
143.         std::vector<Chromosome> newPopulation(elite.begin(), elite.end());
144.         std::sort(offspring.begin(), offspring.end(), compare);
145.         std::copy采用n(offspring.begin(), populationSize - elitismCount, std::back采用inserter(newPopulation));
147.         population = newPopulation;
148.     }
150.     // 输出最优解
151.     std::cout << "Best solution found: " << std::endl;
152.     std::cout << "Fitness: " << population[0].fitness << std::endl;
153.     std::cout << "Genes: ";
154.     for (int gene : population[0].genes) {
155.         std::cout << gene << " ";
156.     }
157.     std::cout << std::endl;
159.     return 0;
160. }

复制代码