粒子群优化算法和python代码_粒子群优化算法（PSO）python实现（人工智能作业）...

1 importmath2 importrandom3 importmatplotlib.pyplot as plt4

5 c1 = 2 #学习因子 # Learning coefficient

6 c2 = 2

7

8 def fitness(x1,x2,x3): #适应度函数 # Fitness Function

9 return math.floor((2*x1**2 - 3*x2**2 - 4*x1 + 5*x2 + x3)*100) / 100

10

11 classPSO:12 def __init__(self):13 self.pop_size = 100 #粒子群个体数 # the number of the instance in Particle swarm

14 self.dim = 3 #变量数 # the number of variables

15 self.omega = 0.4 #惯性因子 # Inertia factor

16 self.x_max = 15

17 self.x_min =018 self.v_max = (self.x_max - self.x_min) * 0.05

19 self.v_min = -(self.x_max - self.x_min) * 0.05

20 self.position = [[]] #记录当前粒子位置 # record the current position of each particle

21 self.speed = [[]] #记录当前粒子速度 # record the moving speed

22 self.best_value = [[]] #记录全局最优 # record the global optimal

23 self.value = [[]] #记录当前值 # record the current fitness and position

24 definitial(self):25 for i inrange(self.pop_size):26 "第一轮初始化"

27 "first round of initialization"

28 x =[]29 v =[]30 for j inrange(self.dim):31 "所有math函数只为取两位小数"

32 "all the math.floor() are used for rounding the result up to two decimal places"

33 x.append(math.floor(random.uniform(self.x_min,self.x_max) * 100) / 100)34 v.append(math.floor(random.uniform(self.v_min,self.v_max) * 100) / 100)35 self.position.append(x)36 self.speed.append(v)37 #self.value.append((fitness(x[0],x[1],x[2]))

38 self.value.append(((fitness(x[0],x[1],x[2])),x[0],x[1],x[2]))39 self.value = self.value[1:]40 #-------------------选择取最大值/最小值-------------------#

41 "choose to get the max or the min value"

42 #index = self.value.index(max(self.value))

43 index =self.value.index(min(self.value))44 #-------------------选择取最大值/最小值-------------------#

45 self.best_value.append((self.value[index][0],self.position[index][0],self.position[index][1],self.position[index][2]))46 self.best_value = self.best_value[1:]47 self.position = self.position[1:]48 self.speed = self.speed[1:]49 print("the population and fitness after initialization:")50 print("position :",self.position)51 print("value:",self.value)52 print("best value:",self.best_value)53 print("------------------------split line------------------------")54 defsolving(self,times):55 for i inrange(times):56 #print(self.value)

57 #-------------------选择取最大值/最小值-------------------#

58 "choose to get the max or the min value"

59 #pbest = self.value[self.value.index(max(self.value))]

60 #gbest = self.best_value[self.best_value.index(max(self.best_value))]

61 pbest =self.value[self.value.index(min(self.value))]62 gbest =self.best_value[self.best_value.index(min(self.best_value))]63 #-------------------选择取最大值/最小值-------------------#

64 print("pbest:",pbest)65 print("gbest",gbest)66 for j inrange(self.pop_size):67 x =[]68 v =[]69 for k inrange(self.dim):70 v.append(math.floor((self.omega * self.speed[j][k] + c1 * random.uniform(0,1) * (pbest[1+k] - self.position[j][k]) + c2 * random.uniform(0,1) * (gbest[1+k] - self.position[j][k])) * 100) / 100)71 x.append(math.floor((self.position[j][k] + self.speed[j][k]) * 100) / 100)72 "将位置和速度限制在规定范围内"

73 "restrict the position and the speed"

74 if (v[k] self.v_max):77 v[k] =self.v_max78 if(x[k] self.x_max):81 x[k] =self.x_max82 "数据更新"

83 "updating"

84 self.position[j] =x85 self.speed[j] =v86 self.value[j] = (fitness(self.position[j][0],self.position[j][1],self.position[j][2]),self.position[j][0],self.position[j][1],self.position[j][2])87 #-------------------选择取最大值/最小值-------------------#

88 "choose to get the max or the min value"

89 #index = self.value.index(max(self.value))

90 index =self.value.index(min(self.value))91 #-------------------选择取最大值/最小值-------------------#

92 "获得全局最优"

93 "get the global optimal"

94 self.best_value.append((self.value[index][0], self.position[index][0], self.position[index][1],self.position[index][2]))95 defreturnbest(self):96 returnself.best_value97

98

99

100 if __name__ == '__main__':101 demo =PSO()102 demo.initial()103 demo.solving(100)104 result =demo.returnbest()105 for i inresult:106 print("value:",i[0],"x1:",i[1],"x2:",i[2],"x3:",i[3])107 X =[]108 Y =[]109 for i in range(100):110 X.append(i)111 Y.append(result[i][0])112 plt.plot(X, Y)113 plt.show()