Evaluating digital twin maturity levels a case study of using large language models
Please login to view abstract download link
Digital Twin (DT) plays a pivotal role for bridging the gap between the reality and simulations, fulfilling a core benchmark of Industry 5.0. Implementing DT solutions require highly skilled professionals form the diverse fields-such as from the design, materials science, manufacturing, data science, software engineering, etc. This level of expertise makes the implementation of DT solutions and setting future goals in an organization challenging. This approach integrates large language models (LLMs) into digital twin maturity assessments. This is demonstrated using a cantilever beam, simulated with Python tools like EXUDYN and PyANSYS, to show progress across maturity levels as seen in Figure 1 [1]. This approach not only advances AI-driven research within the scientific community but also fosters societal innovation by promoting the adoption of cutting-edge tools for digital transformation. This improves decision-making, streamlines evaluations, and supports predictive maintenance.
