Implementing Local Search Algorithms to Multi-series Production Task

The study introduces an innovative approach to address the scheduling challenges encountered in the automotive industry’s multi-variant production processes. It focuses on optimizing task assignments among employees with diverse competencies to minimize the overall production time. Managing employee work effectively becomes crucial due to limited workforce availability, directly impacting production timelines, meeting contractor requirements, and achieving measurable savings. To tackle this, the research employs various local search algorithms, including Tabu Search, Simulated Annealing, and Descending Search. Additionally, the study introduces the integration of a neural network as an augmenting element within Tabu Search algorithm, aimed at alleviating constraints and analyzing potential benefits in production optimization.