| Popis: |
Operations in clustering and racking systems (CRS) are labor intensive warehouse management. Operators have been looking for an automated approach to escalate zoning efficiency. Since space management affects the efficiency of inter-warehouse operation, this article proposes similarity algorithms upon trained image data from machine learning (ML) to categorize products. This eases product placement and space planning to automate the smart warehouse. First, upon the request of new placements, this study manipulates the analysis of image similarity to identify the products’ cluster. In accordance with the ML based training among the image lists, the similarity based on distance vector analysis is applied for the choices of storage location in the warehouse. Lastly, the proposed method was determined by using the simulation with the use-case images. The results confirm that it can sort out the decision in clustering and racking operations. |
