基于自适应模拟退火PSO算法建筑管道布置研究  

A Study of Adaptive Simulated Annealing Particle Swarm Optimization(ASAPSO) Algorithm for Building Pipe Routing Design

作　　者：王长涛[1] 孙晓彤 韩忠华[1] 朱毅[1] Wang Changtao;Sun Xiaotong;Han Zhonghua;Zhu Yi(School of Information and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China)

机构地区：[1]沈阳建筑大学信息与控制工程学院,沈阳110168

出　　处：《系统仿真学报》2018年第5期1941-1949,共9页Journal of System Simulation

基　　金：住建部科学技术项目(2011-K1-32)

摘　　要：为解决建筑空间下的管道自动布置问题,建立了建筑环境和管道数学模型,将管道长度、弯头数、敷设区域作为评价指标。采用自适应模拟退火粒子群算法对管道进行优化,该算法引入随适应值大小自适应调整进化参数及结合模拟退火算法调整粒子最优位置的策略,以增强算法跳出局部极值的能力。设计了一种基于选择概率代价的初始种群建立方法,提高初始解的质量。通过仿真实验,将该算法与标准粒子群算法进行比较,结果表明自适应模拟退火粒子群算法在解的质量上有显著的提高。To solve the building pipe routing design problem, a mathematical model was formulated. The length of pipe, the number of bends and the laying area were taken as the comprehensive evaluation indexes. Adaptive Simulated Annealing Particle Swarm Optimization （ASAPSO） algorithm was proposed for optimization. In the ASAPSO algorithm, a self-adaptive parameter adjusting strategy and simulated annealing algorithm adjusting the optimal particle location were introduced to enhance the capacity in escaping from the local optimal. A new population initialization method based on the cost of selection probability was designed at the initial population. The simulation showed that compared with the PSO, the ASAPSO can achieve a significant improvement in the quality of the solutions.

关 键 词：建筑管道自动布置 自适应模拟退火粒子群算法 模拟退火 选择概率 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]