Smart Production and Manufacturing System Using Digital Twin Technology and Machine Learning

Adoption of digital twin (DT) in smart factories, which simulates an actual system that is manufacturing conditions and updates them in real-time, increased the output and decreased the costs and energy use which were some ways that this manifested. Fast-changing consumer demands have caused a sharp increase in factory transition in addition to producing fewer life cycles of a product. Such scenarios cannot be handled by conventional simulation and modeling techniques; we suggest a general framework for automating the creation of simulation models that are data-driven as the foundation for smart factory DTs. Our proposed framework stands out thanks to its data-driven methodology, which takes advantage of recent advances in machine learning and techniques for process mining, constant model validation, and updating. The framework's objective is to completely define and reduce the requirement for specialist knowledge to get the appropriate simulation models. A case study is used to demonstrate our framework. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.