ToolSHeD™: The development and evaluation of a decision support tool for health and safety in construction design

摘要

Purpose - The purpose of this paper is to describe an innovative information and decision support tool (ToolSHeD(TM)) developed to help construction designers to integrate the management of OHS risk into the design process. The underlying structure of the prototype web-based system and the process of knowledge acquisition and modelling are described. Design/methodology/approach - The ToolSHeD(TM) research and development project involved the capture of expert reasoning regarding design impacts upon occupational health and safety (OHS) risk. This knowledge was structured using an innovative method well-suited to modelling knowledge in the context of uncertainty and discretionary decision-making. Example "argument trees" are presented, representing the reasoning used by a panel of experts to assess the risk of falling from height during roof maintenance work. The advantage of using this method for modelling OHS knowledge, compared to the use of simplistic rules, is discussed. Findings - The ToolSHeD™ prototype development and testing reveals that argument trees can represent design safety risk knowledge effectively. Practical implications - The translation of argument trees into a web-based decision support tool is described and the potential impact of this tool in providing construction designers (architects and engineers) with easy and inexpensive access to expert OHS knowledge is discussed. Originality/value - The paper describes a new computer application, currently undergoing testing in the Australian building and construction industry. Its originality lies in the fact that ToolSHeD(TM) deploys argument trees to represent expert OHS reasoning, overcoming inherent limitations in rule-based expert systems.