Simultaneous scheduling optimization for machines and multiple-load AGVs in a digital-twin-based environment

Industrial automation has become crucial with the rise of Industry 4.0, and automatic material handling system (AMHS) plays an important role in the development of smart manufacturing facilities. Within AMHS, automated guided vehicles (AGVs) are widely used in flexible manufacturing systems (FMS) owing to their high efficiency and flexibility. Moreover, multiple-load AGVs further improve the system throughput. In addition, with advancements in artificial intelligence (AI), big data, sensor technology, and the Internet of Things (IoT), digital twin technology has emerged as a valuable tool for improving production efficiency and reducing costs by creating a virtual replica of the system. This study aims to integrate scheduling optimization techniques with digital twin technology for the simultaneous scheduling of machines and multiple-load AGVs. Initially, a genetic algorithm-based optimization method generates optimal job scheduling without considering the AGV material handling time. This optimal scheduling solution is then implemented in simulation software to simulate the operation of AGVs in a real production environment. Through simulations, the utilization rate of AGVs and the overall makespan are evaluated. More precise results could be obtained by combining digital twin technology with genetic algorithms. The experimental results indicate that the digital twin-based scheduling method effectively optimizes job scheduling and enhances AGV utilization, leading to a more efficient production process.