Abstract:In this paper, we propose a neuro-genetic artificial neural network framework to achieve certain targeted productivity measures/ performance values in a flow shop with parallel processors (resources) at each stage. The performance measures that we consider are flow time, number of tardy jobs, total tardiness and machine utilizations. In order to achieve these goals, the management has to make decisions on the availability of resources, in our setting, the number of identical machines in each work station and the dispatching rule to be utilized in the shop floor to achieve performance values as close as to the targeted ones.
Introduction:In the current competitive global market, demand for a certain product might change based on several factors. For example, seasonality of demand, a new competitor or lower than expected sales due to an economic crisis in the market might force an under utilization of the capacity. In this case, the management might consider not to run all of the available resources such as machines and workers. However, a goal in this case might be keeping the level of certain performance measures at a certain level to accommodate a certain level of unexpected demand. In this study, we assume that the management has decided on the targeted values of the performance measures. We optimize the number of machines (resources) and the due dates of the incoming orders in order to achieve performance values as close to the targeted values as possible.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.