Factory Layout Design and Optimization using Production Simulation and Reinforcement Learning

Designing the factory layout is important process that has a significant impact on productivity, logistics and manufacturing costs. The design of the factory layout requires careful consideration of the various factors mentioned above, and the relationships between them become more complex as the scale of the factory. It demands considerable investment of time and resources when implementing a new production line or making layout changes due to process redesign such as adjustments in equipment count, process, and logistics. However, it is essential to find methods to reduce the costs and discover the optimal layout due to the difficulty in decision-making optimized factory layout. This study explores the method of determining optimal factory layouts, considering productivity and logistics, using production simulation and reinforcement learning algorithms. Through this methodology, the research deviates from conventional rules traditionally considered optimal in existing layouts. The study focuses on finding an optimal layout that maximizes key performance indicators such as productivity and logistics, while satisfying given conditions. Utilizing design data containing equipment information, an automatically generated simulation model analyzes and predicts the mentioned key performance indicators. The predicted results are evaluated and updated by the reinforcement learning algorithm, iterating the process of creating a simulation model and predicting results based on the updated design data. Through this iterative process, the study gradually identifies layout with key performance indicators. This study demonstrates the possibility of deriving optimal layouts under complex layout design conditions. The proposed methodology is expected to identify optimal layouts for the varying conditions.