基于CBR的重大环境事故应急响应专家系统研究进展与展望

针对当前社会环境事故频发现象,分析国内外重大环境事故应急响应策略的研究进展,指出目前应急响应决策存在的问题.分析了基于案例推理(CBR)的理论和应用研究现状,拟将CBR技术引入重大环境事故应急响应领域,提出了基于案例推理的重大环境事故应急响应专家系统(CBR-MEAERES),并介绍了CBR-MEAERES的结构和核心问题.     

基于WebGIS的危险化学品污染事故应急决策支持系统

通过对危险化学品污染事故危害性的分析,指出环境污染事故应急处置的紧迫性和必要性;给出了事故应急决策支持机制,采用案例推理与规则推理相结合的推理技术来实现事故应急方案的自动生成;借助于WebGIS技术,建立起集成污染事故风险评估与预警、监测分析、快速处理等多项技术的系统平台;该系统创建了集成空间信息、属性信息和文档信息的污染应急决策数据库,提供了环境污染危险的评估技术,建立了环境污染的扩散模型,实现了环境污染事故应急监测与处置技术的集成应用。实践证明,该系统能为危险化学品污染事故的应急处理提供及时、有效的决策支持。     

基于案例推理的油罐区重大事故应急资源配置技术

油品储罐区是安全生产监管的重点,总体来说,我国缺乏处置油罐区重特大和复杂事故灾难的救援装备,应对重大、复杂事故的能力不足。目前,应急救援资源需求配置预测与估计以专家经验为主,在对油罐区应急资源进行重新分类的基础上,提出基于风险分析与案例推理的应急资源配置思路与框架,采用CASST-QRA定量风险评价软件实现对油罐区的风险分析,得到可能的事故类型、事故结果等计算结果,综合考虑事故对周边环境的影响,最终通过案例推理(CBR)分析过程来指导应急资源配置的数量、质量和类型,通过案例研究与计算,得到适用于油罐区重大事故的基于CBR的应急资源配置技术。     

基于案例推理的城市典型灾害应急处置专家系统构建研究

全球自然灾害频发、强度不断增强,且城市化进程飞速发展,其所带来的相关城市灾害风险与日俱增.在重视灾害预报、预警的同时,城市灾害应急处置工作的有效组织与开展,亦是至关重要.把人工智能和城市灾害学知识相结合,通过构建灾害应急处置专家系统来解决该问题是目前的一个研究方向.本文运用案例推理等人工智能领域知识进行相关问题研究,阐述了如何对典型城市灾害案例进行知识化存储处理,给出了典型城市灾害分类推理规则和应急救援案例匹配计算方法.最后,利用VC++和CLIPS相结合,构建了基于案例决策的城市灾害应急处置专家系统.通过研究,充分验证了该模型方法的可行性,对于提高城市应急处置能力具有很好的现实意义.     

旧工业建筑再生利用施工风险应急管理研究

为了解决旧工业建筑再生利用施工风险难以快速应对以及特征属性数据缺失的问题,通过对近年历史案例的收集,将规则推理（RBR）引入案例推理（CBR）中,构建旧工业建筑再生利用施工风险应急管理模型。利用组合权重的方法,求出各特征属性的权值;通过计算结构相似度来处理缺失的属性数据,并结合特征属性相似度,求出全局相似度,检索出相似度最大的案例;通过RBR对检索案例的应对措施进行适用性修正,提高应对措施的针对性;最后,选取案例对模型进行应用说明,结果表明:模型具有较强的适用性,可用于旧工业建筑再生利用施工阶段的风险应急管理。     

基于案例推理的地铁非常规突发事件应急决策方法研究

针对地铁非常规突发事故发生时,由于地下环境复杂且封闭,很难获取较全面、准确的事件信息等问题,非常规突发事件的地铁应急决策是一个复杂的过程。通过对地铁事件原则性机理进行分析和研究,得到地铁发生重大火灾事故情景分析的贝叶斯网络节点变量,借鉴CBR模型的思想,将基于结构和属性的双重情景检索的事故案例推理应急决策方法应用到地铁火灾非常规突发事件应急决策中,该方法排除了因属性值缺失造成相似度无法计算或计算有误的情况,可为地铁交通应急平台的后期建设提供理论支持     

中国安全生产科学研究院“十三·五”系列科研成果

正典型危险化学品爆炸事故现场应急处置辅助决策系统依托项目:基于实际情景动态风险分析的事故应急处置辅助决策系统(2017YFC0804706)研究内容:中国安全生产科学研究院、中共中央党校(国家行政学院)、中国人民警察大学、北京优锘科技有限公司开展合作研究,从危险化学品爆炸事故应急决策特征及流程分析入手,开展相关事故应急辅助决策支持系统的业务与功能需求分析,设计并实现了1套能够应用于危险化学品爆炸事故现场应急处置辅助决策的专业化信息系统。     

基于3S技术的危险废物污染事故预警系统

运用卫星遥感(RS)技术、地理信息系统(GIS)和全球定位系统(GPS),按国家、省、市、县4级模式,建立突发性危险废物污染事故预警系统.国家级预警系统主要对跨省界及跨国突发性污染事故进行应急处置,对省级应急事故处置进行指导;省级预警系统主要对跨市界突发性污染事故进行应急处置,并指导市级污染事故应急处置;市级预警系统主要负责跨县界突发性污染事故的应急处置并指导县级污染事故应急处置;县级预警系统主要负责本行政区内的突发性污染事故的应急处置.建立4级预警系统的主要目的是使各级政府突出重点,集中解决本行政区域内突发性环境污染事故的应急处置,从管理层面上在全国建立一个能对突发性污染事故实施统一指挥协调、现场快速监测和应急处理,又能对污染隐患进行监控和警告的应急响应系统.以辽宁省辽河为案例,通过3S技术的综合运用,构建省级流域突发性危险废物污染事故预警系统方案,为政府应急决策提供快速服务.     

中国安全生产科学研究院“十三·五”系列科研成果典型危险化学品爆炸事故现场应急处置辅助决策系统

依托项目:基于实际情景动态风险分析的事故应急处置辅助决策系统(2017YFC0804706),研究内容:中国安全生产科学研究院、中共中央党校(国家行政学院)、中国人民警察大学、北京优错科技有限公司开展合作研究,从危险化学品爆炸事故应急决策特征及流程分析入手,开展相关事故应急辅助决策支持系统的业务与功能需求分析,设计并实现了1套能够应用于危险化学品爆炸事故现场应急处置辅助决策的专业化信息系统。     

地铁施工风险应急管理研究

针对近年来地铁施工事故频发,难以快速、有针对性地进行应急处置的问题,通过对近年来地铁施工事故案例的统计,分析导致地铁施工事故的相关因素,用Protege软件对以往地铁施工事故应急案例建立知识本体模型。通过目标案例与本体库中的源案例进行相似度计算与匹配,检索出案例库中相似度超过阈值的源案例,然后再对比筛选后的源案例与目标案例之间的关键属性相似度,从而决定进行规则推理或直接参考该案例的应急措施,以此提高应急处置的速度与针对性。     

基于案例推理的化工园区应急资源需求预测

为确定化工园区突发事故的应急资源需求,提出了一种基于案例推理的化工园区应急资源需求预测方法。该方法主要由三部分组成:(1)基于案例推理的模型构建;(2)化工园区事故的案例描述;(3)基于人工神经网络的案例适应。最后,以石化园区火灾爆炸事故的应急资源需求预测验证该方法的有效性。研究表明,该方法可以实时地对化工园区应急资源需求进行预测,为化工园区的应急资源储备和配置提供支持。     

煤矿应急管理集成信息系统设计

针对目前煤矿企业在应急管理中存在的问题,通过对国内外应急管理技术的研究成果的学习和总结,进行煤矿应急管理信息系统的需求分析,在对应急管理的理论流程、基于案例推理（CBR）等理论进行深入研究的基础上,将人工智能、关键链方法和计划调度相关理论应用到人员管理和应急计划的制定和实施过程中,结合J2EE、SOA、GIS和GPS等技术,实现煤矿应急管理信息系统功能设计与集成设计,并借此推进煤矿企业在应急管理方面的发展,将事前预警与事后响应相结合,降低煤矿突发事件的危害程度。     

An expert system for the quantification of fault rates in construction fall accidents

Introduction. Expert witness reports, prepared with the aim of quantifying fault rates among parties, play an important role in a court's final decision. However, conflicting fault rates assigned by different expert witness boards lead to iterative objections raised by the related parties. This unfavorable situation mainly originates due to the subjectivity of expert judgments and unavailability of objective information about the causes of accidents. As a solution to this shortcoming, an expert system based on a rule-based system was developed for the quantification of fault rates in construction fall accidents. The aim of developing DsSafe is decreasing the subjectivity inherent in expert witness reports. Methodology. Eighty-four inspection reports prepared by the official and authorized inspectors were examined and root causes of construction fall accidents in Turkey were identified. Using this information, an evaluation form was designed and submitted to the experts. Experts were asked to evaluate the importance level of the factors that govern fall accidents and determine the fault rates under different scenarios. Based on expert judgments, a rule-based expert system was developed. The accuracy and reliability of DsSafe were tested with real data as obtained from finalized court cases. Result. DsSafe gives satisfactory results.     

基于BP神经网络在森林防火专家系统不确定推理中的应用研究

提出将改进的BP神经网络应用于森林防火专家系统的不确定性推理中,其良好的自学习和泛化能力,可以解决基于可信度规则的知识表示在实际应用中导致的规则激增,推理速度缓慢的问题。该方法将不确定的知识用可信度区间表示,通过知识编码,设计并训练BP网络,最后用MATLAB进行仿真。实验结果表明:BP神经网络可以自动学习专家的典型经验,并且能将之准确的推广,隐含层神经元个数的确定和典型样本的选取决定了准确精度。在实际的专家系统不确定推理应用中具有应用价值。     

基于贝叶斯网络的化工园区地震次生灾害情景分析

为了研究化工园区内发生地震灾害后的事故演化过程,利用事故链模型对地震次生灾害演化过程进行分析,并将其转化为贝叶斯网络,确定各节点的变量与状态取值范围;通过相关文献及专家经验判断分析,获得贝叶斯网络中各节点的条件概率;依据贝叶斯网络的推理策略,比较不同地震烈度下,各化工事故发生的后验概率值,并探讨应急救援的及时性对地震次生灾害发生概率的影响,从关键要素遏制化工事故的发生,采取针对性的应对措施,尽可能的降低化工事故,有效的降低人员伤亡及财产损失。     

A novel knowledge database construction method for operation guidance expert system based on HAZOP analysis and accident analysis

An expert system for operation guidance will contribute to identifying the operatoration problems and indicating the resolutions thereof, because the information stored in the expert system can be utilized to resolve the corresponding technical problems. However, there are several problems that should be solved in the practical application of the expert system, such as lack of corresponding knowledge or resolutions utilized to cope with the problems, inapplicable resolutions, too many resolutions for the operators to choose from to obtain the best one in the first time, etc. Obtaining and storing as much as information in the database of the expert system are important issues in the construction process of the expert system. The accident analysis results contain a limited number of accident cases and the HAZOP analysis only refers to a single deviation analysis. This paper has presented a novel knowledge database construction method for an operation guidance expert system based on the HAZOP analysis and the accident analysis, which can be used to resolve the above problems. The HAZOP analysis results are combined with the accident analysis results and the combination information can be stored in the database of the expert system, and can be employed to forecast accidents or identify accident causes. The structures of the operation guidance table and the accident investigation table have been illustrated. The residuum hydrotreating process expert system is taken as an example to illustrate the knowledge database construction method. With the aid of this expert system, the operators will well understand the operations and adopt the best resolutions to deal with the abnormal situations. Also the operators can identify potential risks existing in the plant which will result in accidents according to the accident analysis results associated with the HAZOP analysis results.     

道路交通事故BP神经网络预测研究

在分析道路交通事故影响因素的基础上,确定道路交通事故评价指标体系。该体系包含交通事故次数、死亡人数、受伤人数3个输出指标及12个影响因素。利用人工神经网络具的强非线性逼近、模糊推理、自学习的优点,建立道路交通事故BP神经网络预测模型。模型对我国2006年、2007年、2008年的交通事故情况进行预测,其中,2006年、2007年预测精度较高,2008年预测误差稍大,可能的原因为2007年12月修订的《中华人民共和国道路交通安全法》对减少交通事故起到较大作用。     

A methodology for enhancing the reliability of expert system applications in probabilistic risk assessment

In highly complex industries, capturing and employing expert systems is significantly important to an organization's success considering the advantages of knowledge-based systems. The two most important issues within the expert system applications in risk and reliability analysis are the acquisition of domain experts' professional knowledge and the reasoning and representation of the knowledge that might be expressed. The first issue can be correctly handled by employing a heterogeneous group of experts during the expert knowledge acquisition processes. The members of an expert panel regularly represent different experiences and knowledge. Subsequently, this diversity produces various sorts of information which may be known or unknown, accurate or inaccurate, and complete or incomplete based on its cross-functional and multidisciplinary nature. The second issue, as a promising tool for knowledge reasoning, still suffers from lack of deficiencies such as weight and certainty factor, and are insufficient to accurately represent complex rule-based expert systems. The outputs in current expert system applications in probabilistic risk assessment could not accurately represent the increasingly complex knowledge-based systems. The reason is the lack of certainty and self-assurance of experts when they are expressing their opinions. In this paper, a novel methodology is presented based on the concept of Z-numbers to overcome this issue. A case study in a high-tech process industry is provided in detail to demonstrate the application and feasibility of the proposed methodology.     

Emergency resources demand prediction using case-based reasoning

The demand prediction on emergency resources is the premise and basis of optimal allocation of emergency resources. Nowadays, there are only few researches on this aspect in China and abroad. For this reason, the paper aims at the characteristics of emergency resource demand prediction and presents a method for emergency resource demand prediction using case-based reasoning (CBR), which is also a method based on risk analysis. This prediction method cannot only provide a basis for emergency resource reserve and allocation in future, but also provide a method and model support for the emergency resources allocation decision-making system to be constructed in future.