A NEURAL ALGORITHM FOR FINDING THE SHORTEST FLOW PATH FOR AN AUTOMATED GUIDED VEHICLE SYSTEM

The automated guided vehicle (AGV) system is emerging as the dominant technology to maximize the flexibility of material handling, while inc reasing the overall productivity of manufacturing operations. This pap er presents a new way of finding the shortest flow path for an AGV sys tem on a specific routing structure. An optimal solution of the system is determined by using an approach based on the Hopfield neural netwo rk with the simulated annealing (SA) procedure. In other words, the pr oposed approach reduces the total cost of an AGV delivery path from on e workstation to another on the shop floor. By changing the temperatur e of the two-stage SA, a solution can be found that avoids potential c ollisions between AGVs. Both the flow path and the potential collision , which are major problems in AGV systems, may be solved simultaneousl y by the proposed neural network approach. Other advantages offered by the proposed method are its simplicity compared with operations resea rch (OR) methods and a decreased number of needed AGVs. The performanc e of the approach is also investigated.