Simulation–Validated Genetic algorithm scheduling for industrial production systems

• Developed a Genetic Algorithm based scheduling framework for configuration-dependent industrial job-shop systems. • Integrated discrete-event simulation as an iterative, feasibility-oriented validation layer for scheduling optimization. • Demonstrated substantial makespan reduction and utilization improvements in an industrial commissioning-stage case study. • Showed how strengthening simulation-based validation enhances the practical credibility of GA-based scheduling results. In industrial production systems with high product variety and complex routing logic, schedules that are optimal in computation can become infeasible when executed under real operating constraints. This study proposes a simulation–optimization framework that integrates a Genetic Algorithm (GA)–based scheduler with discrete-event simulation (DES) via a structured validation loop. Instead of utilizing simulation just as a post-hoc evaluator, the DES model is embedded as an iterative feasibility environment that tests GA-generated schedules against routing logic, capacity limits, and flow dependencies. The framework is demonstrated using an industrial job-shop production line characterized by multiple product types, heterogeneous processing steps, and alternative flow paths. Compared to the initial-commissioning phase baseline sequence, the proposed approach reduced makespan from 3,119 min to 1,111 min (about a 64% reduction) and machine utilization increased from 6.53% to 18.7% (about 2.9 × ), and subsequent DES validation confirmed that these gains remain feasible under detailed system logic and operational constraints. The improvements were achieved without modifying physical resources, highlighting the leverage of sequencing logic alone. The main contributions of this work are threefold, (1) A GA-based scheduling model for configuration-dependent job-shop production lines, capturing sequence- and routing-induced complexity, (2) The use of discrete-event simulation as an iterative, analyst-driven mechanism for validating the feasibility and performance of GA-generated schedules under realistic production constraints, (3) Empirical evidence showing that strengthening DES-based validation, rather than increasing algorithmic complexity, can significantly enhance the industrial credibility of GA-based scheduling outcomes. Therefore, the study shows how validation fidelity in DES environment can bridge the gap between optimization outputs and deployable industrial decision support.