Automated Positioning of Anchors for Personal Fall Arrest Systems for Steep-Sloped Roofs

Falls account for about one-third of all construction fatalities with most fatalities in the roofing trade. Even though a personal fall arrest system (PFAS) is required for fall protection, proper placement of PFAS anchor points is an issue evidenced by the high number of fatalities caused by incorrect anchor positioning. The research goal was to proof the concept of optimizing the location of the PFAS anchor points on steep-sloped roofs. This goal was achieved by: (1) Developing an algorithm for converting the required local jurisdiction construction regulations and standards for PFAS anchor positioning into machine-readable rules; and (2) Developing and validating an algorithm for optimizing the location of PFAS anchor points. The K-Nearest Neighbor Search (KNNS) optimization algorithm was selected in this research and was implemented into a standalone computer tool using Python programming language. The tool calculates the potential anchor locations that satisfy the fall clearance and swing hazard requirements and then displays the anchor locations both graphically and numerically. The optimization algorithm was validated using the K-fold Cross-Validation method, which proved the algorithm was adequately accurate and consistent. The research contribution is the proof of the concept that the development of an optimization algorithm and automated field-level tool for optimal selection of PFAS anchor points is possible, further research and refinement could help steep-sloped roofing companies improve their safety practices.

Dieses Werk wurde unter der Creative-Commons-Lizenz Namensnennung 4.0 International (CC-BY 4.0) veröffentlicht und darf unter den Lizenzbedinungen vervielfältigt, verbreitet, öffentlich zugänglich gemacht, sowie abgewandelt und bearbeitet werden. Dabei muss der Urheber bzw. Rechteinhaber genannt und die Lizenzbedingungen eingehalten werden.