A Simulation-based Genetic Algorithm for a Dispatching Rule in a Flexible Flow Shop with Rework Process
This study investigates a dynamic flexible flow shop scheduling problem under uncertain rework operations for an automobile pipe production line.
Our simulation models investigate the production logistics.
Our machine learning applications optimize them.
The objective of the Simulation & Production Logistics (SimPL) Laboratory is to develop large-scale simulation models, operational algorithms, machine learning models that will improve the operations and productivity of logistics and related production systems. Active research areas include simulation optimization, material handling and self-organizing operations, and OR applications in warehousing, semiconductor, display, and automobile industries.
Business areas: Material handling and production logistics in distribution centers, container terminals, semiconductor and display fabs, and construction equipment assembly line
OR approaches: Large-scale simulations, machine learning models, and optimization models
Operational strategy: Simulation optimization, self-organizing/-balancing operations
This study investigates a dynamic flexible flow shop scheduling problem under uncertain rework operations for an automobile pipe production line.
This study suggests a ML algorithm to determine the efficient yard templates under vehicle congestion.
PNU-Postech-FSU joint workshop was held at Postech on August 2 - 3, 2022.
This study proposes flow time estimation model to optimize the storage location assignment.