摘要
从经济因素、交通因素、政治因素角度出发研究江西省11个市建立无水港的潜力,建立含9个评价指标的评价指标体系。给出了基于粒子群优化算法求解模糊目标C-均值聚类模型的求解步骤,然后将模糊C-均值聚类模型与粒子群优化算法相结合,建立江西省无水港选址的聚类模型,并进行求解,得到江西省无水港选址的3类聚类中心、以及江西省11个市归属3类聚类中心的录属度,进而将江西省11个市分为3类。从多经济重心联动发展视角,建议江西省近期应从第2类城市(九江、赣州、吉安、宜春、抚州、上饶)之中选址来建设无水港,从而推动江西省整体经济的发展;从区域平衡发展视角,建议应对第3类城市(景德镇、萍乡、新余、鹰潭)加大交通基础设施建设、大力发展物流产业等,促进地区经济的平衡。
This paper analyzes the capacity of eleven cities in Jiangxi Province to build dry port on the basis of economic, traffic and political factors,and obtains one evaluation index system including nine evaluation indexes. This paper puts forward the processes of solving the fuzzy c-mean clustering model by using particle swarm optimization algorithm.Then combine fuzzy c-mean clustering model with particle swarm optimization algorithm, the clustering model for dry port location of Jiangxi Province was built, three-class cluster-centers were obtained by solving the mode based on particle swarm optimization algorithm.According to the degree of membership of eleven cities, this paper divided eleven cities into three categories.From the view of development of multiple economy centers, the government should choose the second-class cities such as Jiujiang,Ganzhou, Ji’an,Yichun,Fuzhou and Shangrao to the candidate for dry ports, so as to propel the economy development of Jiangxi Province.At the same time, from the view of balance development of different regions, some measures should be taken in the third-class cities such as Jindezhen, Pingxiang,Xinyu and Yingtan to construct traffic basic facilities and develop logistic industry so as to realize the economy balance of different regions.
作者
徐兵
束斌
XU Bing;SHU Bin(Center for Central China Economic Development Research,Nanchang University,Nanchang 330031,China;School of Management,Nanchang University,Nanchang 330031,China)
出处
《南昌大学学报(工科版)》
CAS
2018年第4期403-408,共6页
Journal of Nanchang University(Engineering & Technology)
基金
国家自然科学基金项目(71561018)
2015年度江西省高校人文社会科学重点研究基地项目(JD1501)
2017年度教育部人文社会科学重点研究基地重大项目(17JJD790012)
关键词
无水港
模糊C-均值聚类模型
粒子群优化算法
选址规划
dry port
fuzzy c-clustering model
particle swarm optimization algorithm
location planning