GPU-Accelerated Generative Design for Smart Factory Layout Optimization: a Data-Driven Approach to Process Automation and Robotics Integration

EasyChair Preprint 14374

Abstract

The rapid advancement of Industry 4.0 technologies has intensified the need for efficient and adaptive smart factory layouts. This paper explores the application of GPU-accelerated generative design to optimize smart factory layouts, emphasizing the integration of process automation and robotics. Leveraging the computational power of GPUs, the proposed approach employs generative algorithms to explore vast design spaces, producing optimized layouts that balance operational efficiency, cost-effectiveness, and adaptability. By incorporating real-time data and machine learning, the system continuously refines factory layouts in response to changing production demands and environmental factors. This data-driven methodology not only enhances the precision and speed of design iterations but also facilitates seamless integration of robotics and automation systems, resulting in a cohesive and highly responsive manufacturing environment. The findings demonstrate that GPU-accelerated generative design significantly reduces design time, improves layout efficiency, and supports the dynamic needs of modern smart factories, paving the way for more agile and intelligent manufacturing processes.

Keyphrases: Automated Guided Vehicles (AGVs), Central Processing Units (CPUs), Graphics Processing Units (GPUs)

@booklet{EasyChair:14374,
  author    = {Abey Litty},
  title     = {GPU-Accelerated Generative Design for Smart Factory Layout Optimization: a Data-Driven Approach to Process Automation and Robotics Integration},
  howpublished = {EasyChair Preprint 14374},
  year      = {EasyChair, 2024}}