【作者】 余宏亮；

【导师】 丁烈云；

【作者基本信息】 华中科技大学 ， 工程管理， 2011， 博士

【摘要】 地铁工程建设是一项复杂的高风险性建设工程。一方而,国内地铁工程建设规模逐年扩大,另一方面地铁及地下工程施工安全事故频发。总结地铁工程目前安全管理的现状,即有规模大、发展快,技术和管理力量难以保证等客观原因,更重要的是对风险辨识不细致全面、风险控制措施不到位等主观观原因。在地铁车站施工风险识别所需的经验丰富的技术人员十分匮乏地情况下,如何将专家经验和规范中的风险识别知识结构化,通过计算机自动识别风险将具有较大的理论研究和工程实践价值。本文提出研发基于工程图纸的地铁车站施工安全风险自动识别系统(Safety Risk Identification System for Metro Station Construction on the Basis of Construction Drawings, SRIS),通过研究风险致险因素自动提取方法,从标准、规范及专家经验中获取风险识别规则,设计风险自动识别推理机制和算法,实现由工程图纸信息到施工安全风险的自动输出。SRIS系统应用于地铁车站施工准备期风险评估过程,排查重大安全隐患,为风险动态控制与预警提供参考依据,是信息技术改革传统的风险识别过程的具体应用。设计并实现风险致险因素自动提取。首先对地铁施工安全风险及致险因素进行分类,然后建立工程图纸中可识别的项目特征类、结构构件类、地质水文类和施工环境类信息与各类致险因素的关联关系表,最后设计计算机识图策略和专用算法图纸中各类信息的识别和工程语义解析,从而完成工程技术参数及致险因素的自动提取。构建基于可信度的风险识别知识库。总结地铁车站施工安全风险识别领域的相关理论性知识和专家经验性知识,系统地归纳整理地铁年站施工安全风险及其致险因素,阐释了风险识别知识获取过程、风险识别知识的混合表示方法及结构化存储的方法,在此基础上构建基于可信度的风险识别知识库。提出基于规则推理(RBR)和基于CBR-RBR混合模式两种推理机制。针对风险识别规则的构成特点,在基于规则推理(RBR)原理基础上提出基于无规则控制的成组检索匹配推理算法和风险可信度计算方法。总结安全事故案例的多层次属性特征,提出基于案例推理(CBR)和基于规则推理(RBR)混合模式在地铁车站施工安全事故案例库中的应用模型,并指出在CBR主导前提下RBR的具体应用方法,实现从施工安全事故案例库获取风险识别信息。研发并应用基于工程图纸的风险自动识别系统。分析和设计地铁车站施工安全风险自动识别系统的总体结构、功能模块划分、数据库结构。以武汉地铁二号线工程螃蟹甲车站项目为例,给出了风险自动识别的全过程和实例验证。更多还原

【Abstract】 The metro project is a high risk construction project. On the one hand the overall construction scale increases in China year after year, On the other hand metro and underground project construction safety accident occured frequently. Summarizing the current status of safety management in metro construction, there are objective reasons such as huge investment scale, fast development pace, lackage of technical and management strength, the subjective reasons that risk identification is not thorough, risk control measures is not in place are more important. How to make risk identification knowledge in the experts experience and the regulations strutured and identify the metro station construction risk automaticall by computer is a topic of greater theoretical research and engineering practice value in the situation of very scarceful of experienced technical personnel.The primary objective of this paper is to propose Safety Risk Identification System for Metro Station Construction on the Basis of Construction Drawings (SRIS). Through the study on the risk factors automatic extraction method, risk identification rules can be acquired from the standard, specification and expert experience, inference mechanism and algorithm of risk automatic identification can be designed, realizing safety risks in metro station construction can be output automatically by the engineering drawing information. SRIS can identify potential safety hazard for risk dynamic control and warning in the construction preparation period, by applying graphic recognition technology and risk identification automation technology in risk assessment process. It is one of specific application of using information technology (IT) to improve the work efficiency and accurate of the traditional risk identification process.Designing and implementing risk factors automatical acquisition. Firstly, the metro station construction safety risk and risk factors are classified. Secondly, a relation table of risk factors and engineering technical parameters which includes project characteristics information, construction technical information geology hydrological information, construction environment information, was built. At last, computer drawings recognition strategy and special algorithm were designed to capture various types of information recognition and implete engineering semantics analysis, thus completing automatic extraction of the engineering technical parameters and risk factors.Building risk identification knowledge-base based on certainty factor. Theoretical knowledge and expert experiential knowledge of metro station construction safety risk identification was summarized, The metro construction safety risk and the risk factors are structured, the acquisition process for risk identification rules, knowledge representation method and structured storage method of risk identification are interpreted, on the basis of which the knowledge database based the certainty factors has been built.Presenting two kinds of reasoning mechanism of case-based reasoning (CBR) and rule-based reasoning (RBR) hybrid pattern. According to the characteristics of the formation of risk identification rules, the rule based reasoning (RBR) based on the principle of fuzzy control is presented based on the element group retrieval reasoning algorithm and risk credibility calculation method. Summarize safety accident case of multi-level attributes, based on the case-based reasoning (CBR) and rule based reasoning (RBR) mixed mode in metro station construction safety accident database application model, and pointed out that in the premise of CBR leading RBR application method, realizes from the construction safety accident database acquisition risk identification information.Developing and applying the SRIS. The overall framework, function models and database structure were designed and analyzied. A case study of the Pangxiejia Station in Wuhan Metro Line 2 project demonstate the construction safety risk automatic identification process and risk scenario validation.更多还原