铁路突发事件应急决策若干问题研究

发布时间：2018-06-19 18:41

本文选题：铁路应急决策 + 预案评估　；参考：《中国铁道科学研究院》2013年博士论文

【摘要】：当前对于铁路突发事件应急决策，主要依据决策者的自身经验，然而由于决策者的知识局限性，做出的决策可能会存在一定的不足，另外，决策者的自身压力可能较大，正常的决策能力会受到影响。因此，如何高效、及时地对铁路突发事件进行有效决策，已成为迫切需要解决的问题。本文综合运用模糊数学、评估理论、多属性群决策理论及计算机技术等多学科知识，采用分析与综合相结合、理论研究与数值试验相结合的方法，针对铁路突发事件应急决策的若干问题进行了研究。本研究的具体内容如下：（1）研究了铁路突发事件及铁路应急决策相关理论，包括铁路突发事件定义、分类分级、特点、基本应急属性，以及铁路应急决策定义、特点、流程和方法。（2）提出案例推理（CBR）应用到铁路应急决策中，①针对铁路突发事件案例表示，提出采用四元组（主题域、问题域、解决方案域、及效果域）描述案例，并提出该四元组中包含的属性；②提出铁路突发事件案例以及铁路应急预案框架法表示方法；③案例属性值上考虑了数值型、有序枚举型、无序枚举型、区间数型及模糊数型五种形式属性值，提出五种形式属性值的案例相似度计算方法；④结合案例属性的特点，采用层次分析法确定铁路突发事件案例属性权重，研究了案例属性局部相似度计算方法、案例总体相似度计算方法，以及基于结构相似度算法，研究案例属性缺失条件下的案例总体相似度计算方法；⑤提出基于案例推理的铁路突发事件应急决策流程。（3）在铁路应急预案评估方面，考虑评估值的不确定性和模糊性以及评估者的偏好和知识不完备性，本文提出四种铁路应急预案评估方法：①改进VIKOR方法评估铁路应急预案，针对的评估指标值为语言值，指标权重的求解运用基于熵的主客观赋权法，另外对铁路预案评估指标提出改进；②针对评估指标值为混合值，提出基于二元语义的混合多属性群决策评估方法，，提出模型及求解算法；③针对指标评估值为区间语言值，定义区间二元语义混合平均(IVTHA)算子及区间二元语义混合几何(IVTHG)新算子，提出基于区间二元语义混合平均(IVTHA)算子的决策评估方法，给出算法步骤；④针对评估指标具有不同优先级，评估值为语言值，提出二元语义优先加权平均（2TLPWA）算子、二元语义优先几何平均（2TLPWG）算子、二元语义优先有序加权平均（2TLPOWA）算子、二元语义优先有序加权几何（2TLPOWG）算子，提出基于二元语义优先有序平均算子（2TPOWA）算子的与预案评估方法，并给出算法步骤。（4）在决策支持系统的理论基础上，给出铁路突发事件应急决策系统的定义、目标，构建了铁路突发事件应急决策系统的框架，提出铁路突发事件应急决策系统的总体设计，并对功能模块做了较详细设计，另外对铁路突发事件应急决策系统“多库”系统中的知识库、模型库、方法库、基础信息库系统做出设计。本文的研究对改进铁路突发事件应急决策方法，提高铁路突发事件应急决策水平具有一定的现实意义，同时对案例推理人工智能技术、多属性群决策评估理论以及决策支持系统的结合研究提供一定的理论基础。
[Abstract]:At present, the decision of emergency railway emergency is mainly based on the own experience of the decision-makers. However, because of the knowledge limitation of the decision-makers, there may be some shortcomings in the decision making. In addition, the pressure of the decision-makers may be larger and the normal decision-making ability will be affected. Therefore, how to effectively and promptly to railway emergencies Effective decision making has become an urgent problem to be solved. In this paper, the multidisciplinary knowledge of fuzzy mathematics, evaluation theory, multi attribute group decision-making theory and computer technology, combined with analysis and synthesis, and a combination of theoretical research and numerical experiment are adopted in this paper, and some problems of emergency decision making for railway emergency are carried out. The specific contents of this study are as follows:
(1) the related theories of railway emergency and railway emergency decision are studied, including the definition, classification, classification, characteristics, basic emergency properties of railway emergency, and the definition, characteristics, process and methods of railway emergency decision.
(2) a case based reasoning (CBR) is applied to railway emergency decision making. (1) a case is described with four tuples (subject domain, problem domain, solution domain, and effect domain) for railway emergency cases, and the attributes included in the four tuple are proposed. Secondly, a railway emergency case and a framework for railway contingency plan are presented. In the case attribute value, five kinds of attribute values of numerical, ordered enumerated, unordered enumerated, interval number and fuzzy numbers are considered, and five kinds of case similarity calculation method of attribute values are put forward. (4) combining the characteristics of case properties, the weight of railway emergency case property is determined by analytic hierarchy process, and the case study is studied. The local similarity calculation method, the overall case similarity calculation method, and the structure similarity algorithm, study the overall similarity calculation method of the case under the absence of case property; 5. Put forward the emergency decision process of railway emergency case based on case-based reasoning.
(3) in the evaluation of railway emergency plan, considering the uncertainty and fuzziness of evaluation value and the preference and incompleteness of the evaluators, this paper puts forward four methods of evaluating railway emergency plan: (1) improving the VIKOR method to evaluate the railway emergency plan, the value of the evaluation index is the value of language, and the entropy based on the calculation of the weight of the index. The method of subjective and objective empowerment is also improved. Secondly, a mixed multi attribute group decision evaluation method based on two meta semantics is proposed to evaluate the evaluation index of railway plan, and the model and solving algorithm are proposed. Thirdly, the interval two element semantic mixed mean (IVTHA) operator and interval are defined in view of the value of the index evaluation as the interval language value. Two element semantic hybrid geometry (IVTHG) new operator, a decision evaluation method based on interval two element semantic mixed mean (IVTHA) operator is proposed, and the algorithm steps are given. (4) the evaluation index has different priority, the evaluation value is the language value, the two element semantic priority weighted average average (2TLPWA) operator and the two meta semantic priority geometric mean (2TLPWG) operator are proposed. The two element semantic prioritized weighted mean (2TLPOWA) operator and two meta semantic prioritized weighted geometric (2TLPOWG) operator are used to propose a preview evaluation method based on the two element semantic prioritized mean operator (2TPOWA) operator, and the algorithm steps are given.
(4) on the basis of the theory of the decision support system, the definition of the emergency decision system for railway emergency events is given. The framework of the emergency decision system for railway emergency events is set up. The overall design of the emergency decision system for railway emergency events is put forward, and the functional modules are designed in detail. In addition, the emergency decision system for emergency railway events is also made. The knowledge base, model base, method base and basic information base system of the "multi storehouse" system are designed.
The study of this paper has a certain practical significance for improving the emergency decision making method of railway emergency emergency and improving the level of emergency decision of railway emergency. At the same time, it provides a theoretical basis for the study of the artificial intelligence technology of case-based reasoning, the theory of multi attribute group decision making and the combination of decision support system.
【学位授予单位】：中国铁道科学研究院
【学位级别】：博士
【学位授予年份】：2013
【分类号】：U298

【参考文献】