Flow-Shop Scheduling Optimization through Discrete-Event Simulation and Neural Networks.

Schedule optimization of manufacturing systems is critical to improve operational efficiency. Typically, these scheduling problems become challenging because they involve coordinating various production tasks, resource management, and makespan minimization. These challenges are particularly evident in flow-shop manufacturing systems, where the operation sequencing significantly impacts overall performance. The main objective of this manuscript is to present the methodology followed to optimize the schedule of a flow-shop manufacturing system through the combination of discrete-event simulation and neural networks. With a specific focus on enhancing operational efficiency, the study aimed to employ the built-in neural network capabilities of Simio simulation software to optimize the makespan, consequently reducing the overall production time required for processing manufacturing orders. By exploring the integration of advanced simulation techniques with neural network functionalities, this research highlights the advantages of this powerful tool to model and optimize complex manufacturing processes. Moreover, the study compared the Simio with neural networks approach and Palmer Heuristic method to assess their respective advantages and disadvantages and emphasized the potential benefits for the manufacturing industry by implementing these methodologies to facilitate informed decision-making and drive improvements in productivity and resource utilization within the context of manufacturing operations.