An artificial neural network case study: the control of work-in-process inventory in a manufacturing line

In manufacturing systems, the cost of stock, which constitutes a significant portion of the total cost, is one of the important costs that has to be dealt with by the managers. The problem of inventory is encountered in cases where accumulation of physical materials is needed for the purpose of meeting the demand of raw materials, work in process and finished goods in a specific period. Work-in-process, between the stages of manufacturing process comes up because of the high rate of flow of raw materials or finished products and insufficient number of labor-machines at work stations. However, work-in-process can be reduced in a manner that does not hinder the process by determining the optimum number of labor-machine according to the process time. Thus, costs of work-in-process become minimum. In this study, work-in-process at a middle-scale shoe factory is investigated. At the manufacturing center, there are five work departments composed of cutting, sewing, hand-leather working, assembling and quality control-packing. In these departments there are work-in-process because of different processing times and insufficient number of labor-machines. An artificial neural network (ANN) with backpropagation is used for solving this work-in-process problem. In the study, optimum number of labor-machines at work stations were obtained for work-in-process without hindering the production by considering processing times and flow at these work stations