Exploring the Adoption and Application of Transformer Models in Manufacturing Scheduling

This paper investigates the application of Transformer-based learning algorithms within the domain of manufacturing scheduling, prompted by the architecture's foundational role in advancements like Chat-GPT. As Transformer models gain prominence in various fields due to their sophisticated handling of sequential data and long-range dependencies, their potential in manufacturing processes remains largely uncharted. Our research aims to identify the industries and specific types of scheduling where these models are being implemented and to understand the nature of these applications. Through a detailed analysis of relevant literature, we assess the current landscape of Transformer applications in manufacturing, highlighting both the methodologies used for data extraction and the insights gained from these studies. Preliminary findings suggest that while the use of Transformer models in manufacturing scheduling is emergent, it presents substantial opportunities for future research. The study reveals a promising but underexplored area ripe for innovation and practical application, suggesting a critical avenue for future technological developments in industrial operations management.