A combined methodology for selection of part feeding system based on part features

Most of the industrial products are produced by assembling different parts. In internal logistics activities, the delivery of a product's parts to their relevant assembly line and then to workstations is of great importance and also parts feeding system directly affects the time required to produce the product. This time varies depending on the various features of the parts. In the first stage of this study, a Multiple Linear Regression model is proposed for the analysis of the relationship between the various characteristics of parts and the daily time spent for the parts feeding system. As a result of the analysis, the factors affecting the daily time spent were determined and statistical inferences were made. Taking into account the results obtained in the first stage, a Two-Step Clustering method has been applied to solve the problem of how parts will be delivered to the assembly line. The parts were separated into two clusters by line stocking and kitting according to the results, the quality of these clusters was found to be at a good level, and it was shown that it is applicable to the design of the part feeding system when a few exceptional parts are removed.