Knowledge acquisition and knowledge structure for the safety first expert system.
Proceedings of the 31st Annual Conference of the Associated Schools of Construction, Tempe, Arizona, April 6-8, 1995 1995 Apr:227-236
The development and design of an expert system (SAFETY FIRST) to assist in determining the causes of fall accidents in the construction industry and to provide recommendations for prevention were described. This system was composed of five main components, the knowledge base, the inference engine, the user interface, the external files interface, and the external files; the first four components were contained in a level 5 object shell. This report described the construction of the knowledge base. The knowledge base was constructed based on knowledge acquisition and representation tasks. For knowledge acquisition, experts were interviewed and this data was converted into computer compatible codes by software engineers. Fault tree structures were then developed to represent the knowledge gained. The tree structure of the SAFETY FIRST system was structured to study falls caused by seven different types of elevated surfaces as well as same level falls, and slips. The authors conclude that the expert system described is useful for the representation of knowledge regarding construction falls.
NIOSH-Grant; Traumatic-injuries; Computer-models; Accident-analysis; Construction-workers; Walking-surfaces
Civil Engineering Ohio State University 2070 Neil Ave Columbus, OH 43210
Proceedings of the 31st Annual Conference of the Associated Schools of Construction, Tempe, Arizona, April 6-8, 1995
Ohio State University, Columbus, Ohio