Simulation-based optimisation for worker cross-training. (26th August 2021)

• Record Type: Journal Article
• Authors: Karder, Johannes; Beham, Andreas; Hauder, Viktoria A.; Altendorfer, Klaus; Affenzeller, Michael
• Is Part Of: International journal of simulation and process modelling. Volume 16:Number 3(2021)
• Page Start: 185
• Page End: 198
• Publication Date: 2021-08-26
• Subjects: worker cross-training -- workforce qualification -- encoding -- multi-objective optimisation -- NSGA-II -- MOEA/D -- simulation; Management -- Computer simulation -- Periodicals; Mathematical models -- Periodicals; Operations research -- Periodicals; Simulation methods -- Periodicals; 003.05
• Languages: English
• ISSNs: 1740-2123

Abstract

Worker cross-training is a problem arising in many companies that involve human work. To perform certain activities, workers are required to possess certain skills. Cross-trained workers possess even multiple skills, which enables a more flexible deployment, but also incurs higher costs. Thus, companies seek to balance the available skills such that customer deadlines can be met in a cost-efficient way. In this work we compare solution approaches for a simulation-based problem formulation with three objectives. We apply evolutionary multi-objective optimisation to a production system scenario with two lines and six workstations. Their performance is compared for a hard scenario where cross-training is essential to achieve high service levels. Results indicate that the algorithms are able to solve this three-objective formulation quite well using the described encoding and operators. Employing this technology at companies could lead to better qualification strategies and a better contribution of qualification efforts to company goals.