Determination of vehicle requirements in automated guided vehicle systems: A statistical approach

Interest in automated material handling systems has been increasing in manufacturing and assembly facilities. Automated guided vehicle system (AGVS) is one such material handling system. One of the decisions in implementing an AGVS is to determine the number of vehicles required for a facility at the early planning stage. This paper undertakes the development of an analytical model using a regression technique to estimate the number of vehicles required by a facility. The model attempts to use characteristics of a facility for which an automated guided vehicle system is under consideration to determine the number of vehicles required. Although several facility characteristics were investigated, only a few were finally included in the model based on the statistical significance of their contributions to predicting vehicle requirements. The predictive abilities of several models hypothesized were compared with results obtained through simulation on some test facilities. Based on the results of the comparisons, a final model was adopted. The vehicle requirements predicted by the model differed from the results obtained from the simulation model only slightly. The results show that regression analysis provides an alternative and promising approach for estimating vehicle requirements for an AGVS, especially during the initial phase of a system design.