基于支持向量机的巴拿马型干散货船队运营区域选择

关峰; 于少强; 靳廉洁; 孙冬石; 于滨

doi:10.16411/j.cnki.issn1006-7736.2017.02.012

大连海事大学学报 >

2017 , Vol. 43 >Issue 2: 75 - 80

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2017.02.012

交通运输工程

基于支持向量机的巴拿马型干散货船队运营区域选择

关峰 ,
于少强 ,
靳廉洁 ,
孙冬石 ,
于滨

展开

(1．大连海事大学交通运输管理学院，辽宁大连 116026；2.东软信息学院商务管理系,辽宁大连 116023；3.北京航空航天大学交通科学与工程学院,北京 100191）

关峰(1983 — )，男，博士生.于滨*(1977 — )，男，博士，教授，博士生导师，E-mail：yubinyb@163.com.

收稿日期: 2016-10-10

修回日期: 2016-11-29

网络出版日期: 2016-11-29

基金资助

国家自然科学基金面上资助项目(71571026).

收起

Operation region selection for Panamax fleet based on support vector machine

GUAN Feng ,
YU Shao-qiang ,
JIN Lian-jie ,
SUN Dong-shi ,
YU Bin

Expand

(1.Transportation Management College, Dalian Maritime University, Dalian 116026, China;2.Department of Business and Management, Dalian Neusoft University of Information, Dalian 116023, China; 3.School of Transportation Science and Engineering,Beihang University, Beijing 100191, China)

Received date: 2016-10-10

Revised date: 2016-11-29

Online published: 2016-11-29

Fold

摘要

提出一种基于支持向量机的巴拿马型干散货船队运营区域选择方法.该方法考虑4条航线的波罗的海巴拿马型指数对巴拿马型干散货船队经营者在进行运营区域选择时的影响，从而为船东对自身船舶运营决策提供参考.为验证模型的准确性，本文整理了市场上2000多条巴拿马型散货船的运营信息，结合本文提出的模型进行计算.结果表明：模型计算出的船舶航线选择在大西洋和太平洋上与实际情况平均相对误差分别为4.05 %和9.06 %.

关键词： 巴拿马型船队; 航线选择; 波罗的海巴拿马型指数（BPI）; 支持向量机

本文引用格式

关峰 , 于少强 , 靳廉洁 , 孙冬石 , 于滨 . 基于支持向量机的巴拿马型干散货船队运营区域选择[J]. 大连海事大学学报, 2017 , 43(2) : 75 -80 . DOI: 10.16411/j.cnki.issn1006-7736.2017.02.012

Abstract

This paper proposed a selection method of operation region for Panamax fleet based on the support vector machine. The influence of four Baltic Panamax indexes on the ship owners’ choice of the operation region was considered, which is helpful for the ship owner to make policy decision of ships as reference. In addition, to verify the accuracy of the model, the operating informations of more than 2000 Panamax bulk carriers were collected to calculate by using the model in this paper. Result shows that the average relative errors of the Atlantic line and the Pacific line are about 4.05 % and 9.06 % respectively as compared to practical data.

Key words： Panamax fleet; line choice; Baltic Panama Index (BPI); support vector machine

参考文献

［1］ UNCTAD. Review of maritime transport［R］.Geneva: UNCTAD,2014.

［2］谢新连,李树范,纪卓尚,等.船队规划的线性模型研究与应用［J］.中国造船,1989,30(3):59-66.

XIE Xin-lian, LI Shu-fan,JI Zhuo-shang,et al. Study and application on the linear model of fleet planning［J］.Shipbuilding of China,1989,30(3):59-66.(in Chinese)

［3］谢新连.船队规划的动态模型与算法［J］.中国造船, 1992,33(3):102-110.

XIE Xin-lian.A dynamic model and algorithm for fleet planning［J］.Shipbuilding of China,1992,33(3):102-110.(in Chinese)

［4］ ALVAREZ J F,TSILINGIRIS P,ENGEBRETHSEN E S,et al.Robust fleet sizing and deployment for industrial and independent bulk ocean shipping companies［J］.INFOR:Information Systems and Operational Research,2011,49(2):93-107.

［5］ MENG Qiang,WANG Ting-song,WANG Shuai-an.Short-term liner ship fleet planning with container transshipment and uncertain container shipment demand［J］.European Journal of Operational Research,2012,223(1):96-105.

［6］ YANG Qiu-ping,ZHANG Hao,SANG Hui-yun,et al.Mathematical approach for fleet planning under complicated circumstances［J］.Journal of Shanghai Jiaotong University（Science）,2014,19(2):241-250.

［7］ STEPHANEDES Y J, KWON E, MICHALOPOULOS P.On-line diversion prediction for dynamic control and vehicle guidance in freeway corridors［J］.Transportation Research Record,1990，1287:11-19.

［8］ DELURGIO S A. Forecasting principles and applications［M］.Boston:Irwin/McGraw-Hill,1998:5-10.

［9］ SMITH B L,DEMETSKY M J.Short-term traffic flow prediction:neural network approach［J］.Transportation Research Record,1994(1453)：98-104.

［10］ LAWRENCE S, GILES C L,TSOI A C. Lessons in neural network training: overfitting may be harder than expected［C］//Fourteenth National Conference on Artificial Intelligence and Ninth Conference on Innovative Applications of Artificial Intelligence, 1997.

［11］ MOODY J E.The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems［C］//Advances in Neural Information Processing Systems 4(NIPS) ,1991.

［12］ SARLE W S. Stopped training and other remedies for overfitting［C］//Proceedings of the 27th Symposium on the Interface,1995.

［13］ VAPNIK V N. An overview of statistical learning theory［J］.IEEE Transactions on Neural Networks,1999, 10(5):988-999.

［14］ VAPNIK V N.The nature of statistical learning theory ［M］.New York: Springer,2000:1-20.

［15］杨忠振,靳廉洁,王明华.基于支持向量机的巴拿马型船舶运价指数预测方法［J］.交通运输系统工程与信息, 2011,11(3):50-57.

YANG Zhong-zhen,JIN Lian-jie,WANG Ming-hua. Forecasting Baltic Panamax index with support vector machine［J］.Journal of Transportation Systems Engineering and Information Technology,2011,11(3):50-57.(in Chinese)

［16］吴奇,严洪森,王斌.基于鲁棒小波ν-支持向量机的产品销售预测模型［J］.自动化学报,2009,35(7):1027-1032.

WU Qi,YAN Hong-sen,WANG Bin.Based on robust wavelet v-support vector machine［J］.Acta Automatica Sinica,2009,35(7):1027-1032.(in Chinese)

［17］ DONG Bing,CAO Cheng,LEE S E.Applying support vector machines to predict building energy consumption in tropical region［J］.Energy and Buildings,2005,37(5):545-553.

［18］ CAO L J,TAY F E H.Support vector machine with adaptive parameters in financial time series forecasting［J］. IEEE Transactions on Neural Networks, 2003, 14(6):1506-1518.

［19］王定成,方廷健,高理富,等.支持向量机回归在线建模及应用［J］.控制与决策,2003,18(1):89-91.

WANG Ding-cheng,FANG Ting-jian,GAO Li-fu,et al.Support vector machines regressing on-line modelling and its application［J］.Control and Decision,2003,18(1):89-91.(in Chinese)

［20］ GUO Xue-song,SUN Lin-yan,LI Gang,et al.A hybrid wavelet analysis and support vector machines in forecasting development of manufacturing［J］.Expert Systems with Applications,2008,35(1-2):415-422.

［21］吕靖,陈庆辉.海运价格指数的波动规律［J］.大连海事大学学报,2003,29(1):1-4.

LU Jing,CHEN Qing-hui.Study on fluctuation of Baltic freight index［J］.Journal of Dalian Maritime University,2003,29(1):1-4.(in Chinese)

［22］宫晓婞,吕靖,王尧.远期运费市场与即期运费市场的关系研究［J］.大连海事大学学报,2010,36(1):55-58.

GONG Xiao-xing,LV Jing,WANG Yao.Relationship between forward freight and spot freight in shipping market［J］.Journal of Dalian Maritime University,2010,36(1):55-58.(in Chinese)

［23］陈飞儿,赵一飞.航运指数对航运金融双中心建设的启示研究［J］.中国航海,2010,33(2):100-105.

CHEN Fei-er,ZHAO Yi-fei.Message from shipping index study-its meaning to construction of Shanghai shipping and finance center［J］.Navigation of China,2010,32(2):100-105.(in Chinese)

［24］ RUAN Qing-song,WANG Yao,LU Xin-sheng,et al.Cross-correlations between Baltic Dry Index and crude oil prices［J］.Physica A:Statistical Mechanics & its Applications,2016,453:278-289.

［25］ ALIZADEH A H,STRANDENES S P,THANOPOULOU H.Capacity retirement in the dry bulk market: A vessel based logit model［J］.Transportation Research Part E:Logistics & Transportation Review,2016,92:28-42.

［26］ DAI Lei,HU Hao,ZHANG Di.An empirical analysis of freight rate and vessel price volatility transmission in global dry bulk shipping market［J］.Journal of Traffic & Transportation Engineering,2015,2(5):353-361.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献