运筹与管理 ›› 2015, Vol. 24 ›› Issue (4): 198-205.DOI: 10.12005/orms.2015.0139

• 应用研究 • 上一篇    下一篇

基于小波神经网络的海上突发事件应急资源动态需求预测

张文芬, 杨家其   

  1. 武汉理工大学 交通学院,湖北 武汉 430063
  • 收稿日期:2014-05-21 出版日期:2015-08-12
  • 作者简介:张文芬(1987-),女,湖北武汉人,博士研究生,研究方向:应急管理;杨家其(1964-),男,湖北鄂州人,教授,博士生导师,研究方向:运输安全、应急物流。
  • 基金资助:
    国家自然基金资助项目(51279153);三峡库区水上突发事件应急资源配置鲁棒优化研究;国家交通部科技项目(2012-329-811-130):海上突发事件应急资源配置优化模型与仿真研究

Dynamic Demand Forecast of Maritime Emergency Response Resources Based on Wavelet Neural Network

ZHANG Wen-fen, YANG Jia-qi   

  1. Transportation School, Wuhan University of Technology, Wuhan 430063, China
  • Received:2014-05-21 Online:2015-08-12

摘要: 近年来海洋综合开发势头迅猛,海上船舶运输业的发展迅速,然而在创造可观的经济效益和社会效益的同时,海上险情事故频发,应急资源需求复杂多变。本文尝试将小波理论应用于海上应急管理领域,运用小波神经网络模型预测未来周期内的海域险情事故数。在海域险情事故预测的基础上,结合应急资源种类、海域的风险程度等影响因素,引入平均风险月度系数,构建了海上突发事件应急资源动态需求概念模型,间接预测应急资源需求,并提出部分可替代应急资源需求的预测思路。并以山东海事辖区为例,验证了该方法的有效性和可行性。

关键词: 交通运输规划与管理, 动态需求, 小波神经网络, 应急资源, 预测

Abstract: For the past few, ocean exploitation and maritime industry have developed rapidly, creating considerable economic and social benefits. Maritime accidents are frequent, and emergency resource demand is complex. This paper attempts to apply wavelet theory into maritime emergency management, predicting the number of maritime accidents in the future in the use of wavelet neural network (WNN) model. Based on the prediction of marine accidents, combined with factors ,such as the type of emergency resources ,the degree of waters risk and monthly average risk factor, the dynamic demand forecast model of emergency resource is built predicting the requirements indirectly. At last, the paper takes the Shandong maritime jurisdiction as example to verify the effectiveness and feasibility of the method.

Key words: WNN, emergency resources, dynamic demand, forecast

中图分类号: