DDD-GenDT: Dynamic Data-driven Generative Digital Twin Framework

2024-12-28

AI Summary

Digital twins (DTs) face challenges in complex dynamic systems—such as CNC machining—including modeling lag, heavy reliance on labeled data, and limited capacity for autonomous evolution. Method: This paper proposes a dynamic data-driven generative digital twin framework that, for the first time, directly employs large language models (LLMs, e.g., GPT-4) as interactive and evolvable digital twin entities. Integrating the Dynamic Data-Driven Applications Systems (DDDAS) paradigm, the framework enables zero-shot, real-time state inference and behavioral prediction without fixed model architectures or manual annotations. Results: Evaluated on the NASA milling wear dataset, the approach achieves zero-shot tool wear state prediction using only minimal instructions and historical time-series data (e.g., spindle current). It attains an average RMSE of 0.479 A—4.79% of the full-scale range (10 A)—demonstrating substantial improvements in DT generalizability and deployment efficiency.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Digital twin (DT) technology has emerged as a transformative approach to simulate, predict, and optimize the behavior of physical systems, with applications that span manufacturing, healthcare, climate science, and more. However, the development of DT models often faces challenges such as high data requirements, integration complexity, and limited adaptability to dynamic changes in physical systems. This paper presents a new method inspired by dynamic data-driven applications systems (DDDAS), called the dynamic data-driven generative of digital twins framework (DDD-GenDT), which combines the physical system with LLM, allowing LLM to act as DT to interact with the physical system operating status and generate the corresponding physical behaviors. We apply DDD-GenDT to the computer numerical control (CNC) machining process, and we use the spindle current measurement data in the NASA milling wear data set as an example to enable LLMs to forecast the physical behavior from historical data and interact with current observations. Experimental results show that in the zero-shot prediction setting, the LLM-based DT can adapt to the change in the system, and the average RMSE of the GPT-4 prediction is 0.479A, which is 4.79% of the maximum spindle motor current measurement of 10A, with little training data and instructions required. Furthermore, we analyze the performance of DDD-GenDT in this specific application and their potential to construct digital twins. We also discuss the limitations and challenges that may arise in practical implementations.

Problem

• Digital Twin
• Modeling and Updating
• Complex System Adaptability

Innovation

• Dynamic Data-Driven
• Digital Twin Framework
• Adaptive Prediction