School of Civil Engineering, Northeast Forestry University, Harbin 150040, China.
School of Civil Engineering, Harbin Institute of Technology, Harbin 150001, China.
Int J Environ Res Public Health. 2019 Apr 29;16(9):1511. doi: 10.3390/ijerph16091511.
Case-based reasoning (CBR) has been extensively employed in various construction management areas, involving construction cost prediction, duration estimation, risk management, tendering, bidding and procurement. However, there has been a dearth of research integrating CBR with construction safety management for preventing safety accidents. This paper proposes a CBR model which focuses on case retrieval and reuse to provide safety solutions for new problems. It begins with the identification of case problem attribute and solution attribute, the state of hazard is used to describe the problem attribute based on principles of people's unsafe behavior and objective's unsafe state. Frame-based knowledge representation method is adopted to establish the case database from dimensions of slot, facet and facet's value. Besides, cloud graph method is introduced to determine the attribute weight through analyzing the numerical characteristics of expectation value, entropy value and hyper entropy value. Next, thesaurus method is employed to calculate the similarity between cases including word level similarity and sentence level similarity. Principles and procedures have been provided on case revise and case retain. Finally, a real-world case is conducted to illustrate the applicability and effectiveness of the proposed model. Considering the high potential for pre-control and decision-making of construction safety accident, the proposed model is expected to contribute safety managers to take decisions on prevention measures more efficiently.
基于案例推理（CBR）已被广泛应用于建筑管理的各个领域，包括工程造价预测、工期估算、风险管理、投标、招标和采购。然而，将 CBR 与建筑安全管理相结合以防止安全事故的研究却很少。本文提出了一个 CBR 模型，该模型侧重于案例检索和重用，为新问题提供安全解决方案。它首先识别案例问题属性和解决方案属性，基于人的不安全行为和客观的不安全状态原则，使用危险状态来描述问题属性。采用基于框架的知识表示方法，从槽、方面和方面值的维度来建立案例数据库。此外，还引入了云图方法，通过分析期望价值、熵值和超熵值的数值特征来确定属性权重。接下来，采用词法相似度和句法相似度来计算案例之间的相似度。提供了案例修改和案例保留的原则和程序。最后，通过一个实际案例说明了所提出模型的适用性和有效性。考虑到建筑安全事故的预控和决策具有很高的潜力，该模型有望帮助安全管理人员更有效地做出预防措施决策。
