python实现粒子群算法

main.py

# -*- coding: utf-8 -*-
"""
Created on Mon Jan 21 21:05:57 2019

@author: Administrator
"""
from PSO import PSO
pso_example = PSO(popsize =30,maxgen = 100,dim = 5,popmin = -50,popmax = 50,c1 = 1.5,c2 = 1.5,w1 = 0.8,vmax = 3,vmin = -3)
pso_infromation = pso_example.iter_optimize()
pso_example.drawpicrure(pso_infromation)

PSO.py

import numpy as np
from numpy.random import rand
import matplotlib.pyplot as plt
from copy import deepcopy
from Sphere import Sphere

class PSO(object):
    'popsize--------> 种群规模\
    maxgen----------> 最大迭代次数\
    dim-------------> 优化维度\
    popmin,popmax---> 搜寻限值\
    c1,c2-----------> 动态因子\
    vmax vmin-------> 速度限值\
    w1--------------> 权值 '
    def __init__(self,popsize,maxgen,dim,popmin,popmax,c1,c2,w1,vmax,vmin):
        self.popsize = popsize
        self.maxgen = maxgen
        self.dim = dim
        self.popmin = popmin
        self.popmax = popmax
        self.c1 = c1
        self.c2 = c2
        self.w1 = w1
        self.vmax = vmax
        self.vmin = vmin
        
    def init_population(self):
        pop = rand(self.popsize,self.dim)*(self.popmax-self.popmin)
        v = rand(self.popsize,self.dim)*(self.vmax-self.vmin)
        return pop,v

    def fitness(self,pop):
        fitness_1 = Sphere(pop)
        return fitness_1        
        
    def iter_optimize(self):
        pop,v = PSO.init_population(self)
        current_fit = rand(self.popsize,1)
        pop_cbest = deepcopy(pop)
        pop_gbest = rand(1,self.dim)
        fit_record = [None]*self.maxgen
        
        for j in range(self.popsize):
             current_fit[j,:] = PSO.fitness(self,pop_cbest[j,:])
             
        fit_cbest = deepcopy(current_fit)
        fit_gbest = deepcopy(np.min(fit_cbest))
        bestindex = np.argmin(fit_cbest)
        pop_gbest =  pop_cbest[bestindex,:]
        
        for i in range(self.maxgen):
            for j in range(self.popsize):
                v[j,:] = self.w1*v[j,:]+self.c1*rand(1,self.dim)*(pop_cbest[j,:]-pop[j,:])+self.c2*rand(1,self.dim)*(pop_gbest-pop[j,:])
                v[j,v[j,:] > self.vmax ] = self.vmax
                v[j,v[j,:] < self.vmin ] = self.vmin
                pop[j,:] = pop[j,:] + v[j,:]
                pop[j,pop[j,:] > self.popmax] = self.popmax
                pop[j,pop[j,:] < self.popmin] = self.popmin
                current_fit[j,:] = PSO.fitness(self,pop[j,:])
                
                if current_fit[j,:]

Sphere.py

def Sphere(data):
    total = 0
    data = data**2
    for i in data:
        total += i
    return total

Benchmark function_picture.py

def test_func():
    fig = plt.figure()
    ax = Axes3D(fig)
    X = np.arange(-2, 2, 0.05)
    Y = np.arange(-2, 2, 0.05)
    X, Y = np.meshgrid(X, Y)
    Z = np.sin(np.sqrt(X**2+Y**2))/np.sqrt(X**2+Y**2)+np.exp((np.cos(2*np.pi*X)+np.cos(2*np.pi*Y))/2)-2.71289
    ax.plot_surface(X, Y, Z, rstride=1, cstride=1, cmap='hot')
    ax.grid('False')

def Sphere1():
    fig = plt.figure()
    ax = Axes3D(fig)
    X = np.arange(-2, 2, 0.05)
    Y = np.arange(-2, 2, 0.05)
    X, Y = np.meshgrid(X, Y)
    Z = (X**2+Y**2)
    ax.plot_surface(X, Y, Z, rstride=1, cstride=1, cmap='hot')
    ax.grid('False')
    
def Schaffer():
    fig = plt.figure()
    ax = Axes3D(fig)
    X = np.arange(-2, 2, 0.05)
    Y = np.arange(-2, 2, 0.05)
    X, Y = np.meshgrid(X, Y)
    Z = 0.5-(np.sin(np.sqrt(X**2+Y**2))**2-0.5)/(1+0.001*(X**2+Y**2))**2
    ax.plot_surface(X, Y, Z, rstride=1, cstride=1, cmap='hot')
    ax.grid('False')

结果

 

Sphere测试函数图像