Adaptive Control for Safe and Quality Rebar Fabrication

Abstract

Rebar fabrication is a labor intensive operation that uses scrap or “trash” steel for raw materials and therefore can benefit greatly from improvements in safety, productivity, and quality. Shared control through a human-machine interface may be the best alternative for achieving highest quality standards and improving worker performance in safety and productivity. This paper develops a control scheme for automated rebar bending within the framework of computer integrated construction and presents research focused on the task level control to compensate for springback in the bent rebar. Three major problems are addressed: (1) Conception of a hierarchical computer integrated construction control structure that links rebar fabrication to the other construction project functions: (2) comparative evaluation of alternative algorithms for prediction of springback; and (3) portability of a springback control model that uses real-time electronic sensing. Bending tests were conducted with both a laboratory prototype and an actual shop table bender to experiment with alternative models for in-process springback prediction including a neural network model. Limitations in control system portability were realized in the transfer from the laboratory prototype bender to the shop bender. Springback model evaluations revealed that empirical statistical models, neural networks, and in-process relaxation performed equally well.