基于知识元的突发事件风险分析

中国管理科学 ›› 2014, Vol. 22 ›› Issue (8): 108-114.

基于知识元的突发事件风险分析

卢小丽¹, 于海峰²

1. 大连理工大学管理与经济学部, 辽宁大连 116024;
2. 大唐国际核电有限公司, 辽宁大连 116010

收稿日期:2012-02-28 修回日期:2013-02-26 出版日期:2014-08-20 发布日期:2014-08-23
作者简介:卢小丽（1976- ），女（满族），辽宁丹东人，大连理工大学管理与经济学部，副教授，博士，研究方向：生态安全、应急管理.
基金资助:
国家自然科学基金重大研究计划重点项目（91024029）；国家自然科学基金资助项目（41201174，71373034）；教育部人文社科项目（12YJC790131）；辽宁省经济社会发展课题（2013lslktjjx-09）

Emergency Risk Analysis based on Knowledge Element

LU Xiao-li¹, YU Hai-feng²

1. Faculty of Management and Economics, Dalian University of Technology, Dalian 116024, China;
2. Datang International Nuclear Power Co., Ltd., Dalian 116010, China

Received:2012-02-28 Revised:2013-02-26 Online:2014-08-20 Published:2014-08-23

摘要/Abstract

摘要： 科学地分析突发事件的风险，有利于应急管理部门正确制定应对方案，降低事件损失。突发事件风险分析中受到多因素高维数据和小样本数据信息不完备的约束，无法全面识别突发事件的风险。本文从突发事件系统观点出发，以知识元模型、投影寻踪方法和信息扩散理论为基础，提出了基于知识元的突发事件风险分析方法。该方法采用知识元模型描述了突发事件已认知的共性本体特征，通过探寻事件风险等级标准数据的最佳投影方向降低了输入元素观测数据的维数，将输入元素观测样本所包含的风险信息扩散到输出属性的风险指标论域的控制点上，从而确定了突发事件发生的风险概率。实例分析中，根据国家《地表水环境质量标准（GB3838-2002）》划分水污染风险等级，利用某湖泊8个监测点实时检测数据，分析该湖泊突发水污染事件的风险性。研究结果表明基于知识元的突发事件风险分析方法能够根据研究区域突发事件风险等级标准和观测点的样本数据，动态定量的分析和评估突发事件潜在风险，为突发事件的应急管理提供科学依据。本文提出的突发事件风险方法对于已经建立实时监测系统的危险区域分析突发事件的风险性具有一定的借鉴意义。

关键词: 知识元, 突发事件, 风险分析

Abstract: Scientific risk analysis of emergency is helpful to make correct contingency plans for Emergency Management Agency and to reduce event loss. However, most emergency risk analyses are under restrictions of multi factors, high dimensional data, small samples and incomplete information, and cannot fully recognize the risk of an emergency. In emergency system viewpoint and under the assistance of knowledge element model, projection pursuit method and information diffusion theory, a method of emergency risk analysis is developed in this paper based on knowledge element. By making use of the knowledge element model, the common ontological characteristics are described. Reducing dimensionality of the observed data on the input elements through searching for the optimum projection direction of the standard data on emergency risk grade, risk information contained in the observed data of the input elements is diffused into the points of the risk index universe on the output elements, and the emergency risk probability is carried out. Taking a lake as an example, risk of the water pollution is graded according to the national standard of environmental quality for surface water, with the data collected from 8 real-time monitoring sites of the lake. The results show that the emergency risk analysis based on knowledge element could analyze and evaluate potential risk of an emergency according to the risk standard grade and the observed data on site. The model of emergency risk analysis based on knowledge element expands the study of risk analysis and provides a scientific basis for the emergency management.Further, the results will provide references to emergency risk analysis in the dangerous areas where real-time monitoring system has been established.

Key words: knowledge element, emergency, risk analysis

中图分类号:

C931.2

卢小丽, 于海峰. 基于知识元的突发事件风险分析[J]. 中国管理科学, 2014, 22(8): 108-114.

LU Xiao-li, YU Hai-feng. Emergency Risk Analysis based on Knowledge Element[J]. Chinese Journal of Management Science, 2014, 22(8): 108-114.

参考文献

[1] 范维澄.国家突发公共事件应急管理中科学问题的思考和建议[J].中国科学基金,2007,(2):71-76.
[2] Guzzetti F, Reichenbach P, Ardizzone F, et al. Estimating the quality of landslide susceptibility models [J]. Geomorphology, 2006, 81(1/2): 166-184.
[3] Guikema S D. Natural disaster risk analysis for critical infrastructure systems: An approach based on statistical learning theory [J]. Reliability Engineering and System Safety, 2009, 94(4): 885-860.
[4] Iliadis L S, Spartalis S I. Fundamental fuzzy relation concepts of a D.S.S. for the estimation of natural disasters' risk [J]. Mathematical and Computer Modelling, 2005, 42(7): 747-758.
[5] Liu Hexiang, Zhang Dalin. Analysis and prediction of hazard risks caused by tropical cyclones in Southern China with fuzzy mathematical and grey models [J]. Applied Mathematical Modeling, 2012, 36(2): 626-637.
[6] 王文圣,金菊良,李跃清.基于集对分析的自然灾害风险度综合评价研究[J].四川大学学报(工程科学版),2009,41(6):6-12.
[7] 吴益平,唐辉明,葛修润.BP模型在区域滑坡灾害风险预测中的应用[J].岩土力学,2005,26(9):1409-1413.
[8] 金菊良,张欣莉,丁晶.评估洪水灾情等级的投影寻踪模型[J].系统工程理论与实践,2002,22(2):140-144.
[9] Wang Shunjiu, Zhang Xinli, Yang Zhifeng, et al. Projection pursuit cluster model based on genetic algorithm and its application in karstic water pollution evaluation[J]. International Journal of Environment and Pollution, 2006, 28(34): 253-260.
[10] Huang Chongfu. Principle of information diffusion[J]. Fuzzy Sets and Systems, 1997, 91(1): 69-90.
[11] Liu Xingpeng, Zhang Jiquan, Cai Weiying, et al. Information diffusion-based spatio-temporal risk analysis of grassland fire disaster in northern China[J]. Knowledge-Based Systems, 2010, 23(1): 53-60.
[12] 王洪德,郑玉钱.基于网格划分及信息扩散的化工园区安全风险评价技术[J].系统工程理论与实践,2010,30(7):1286-1292.
[13] 裘江南,师花艳,叶鑫,等.基于事件的定性知识表示模型[J].系统工程,2009,27(10):1-8.
[14] 王延章.模型管理的知识及其表示方法[J].系统工程学报,2011,26(6):850-856.
[15] Friedman J H, Tukey J W. A projection pursuit algorithm for exploratory data analysis[J]. IEEE Trans on Computer, 1974, C-23(9): 881-890.
[16] 付强,赵小勇.投影寻踪模型原理及其应用[M].北京:科学出版社,2006.
[17] 黄崇福.自然灾害风险评价一理论与实践[M].北京:科学出版社,2005.
[18] 李凤超,刘存歧,管越强,等.应用多元分析方法评价白洋淀水质现状[J].河北大学学报(自然科学版),2006,26(4):405-410.
[19] 余航,王龙,田琳,等.基于信息扩散理论的云南农业旱灾风险评估[J].中国农村水利水电,2011,12:91-94.