Management of production systems requires making immediate decisions based on the data generated in bulk by IT systems. In this case, it can be helpful to use models of artificial neural networks (ANN) that, on the grounds of accessible data, will determine results of the made decision. One of the key problems in production companies is determination of execution time and cost of a production order. The problem is especially important in a company manufacturing a variable product line with a big part of manual operations. In the article, the way of building an ANN model for efficiency forecasting of the assembly process of electric bundles is presented. With regard to the very wide and variable product line, the products with different complexity degree are manufactured on three types of assembly lines. The assembly processes are performed on the assembly lines manually by groups of workers, so efficiency of the process is influenced mostly by skills and experience of these workers. Therefore, numbers of new assembly workers assigned to individual assembly lines and quantities of new products in the production schedule are selected as explanatory variables in the ANN model. The explained variable in the ANN model is production volume of the manufactured electric bundles.
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.