AI-Enhanced Digital Twin Workflows: Revolutionizing Cloud-Based eCAD Collaboration for Predictive Analytics and Real-Time Optimization
Year: 2025
Type: article
Abstract: Several publications regarding the transformative nature of Artificial Intelligence (AI) and the Digital Twin (DT) technology convergence in cloud-based e-Computer aided designs (eCAD) systems have directly or indirectly been reviewed. AI-Enhanced Digital Twin Workflows (AI-DTWs) The research proposes the techniques of artificial intelligence-based predictive digital modelling, referred to as AI-Enhanced Digital Twin Workflows (AI-DTWs), that combine machine learning with real-time data integration and cloud computing to use dynamic, predictive digital models. AI-DTWs are quite different to the traditional digital twins which are based on a fixed set of data and updated sparsely; in the case of an AI-DTW, it will shift and change with new incoming data giving insightful action to the behaviours of the system, predictive maintenance, and optimization opportunities. The paper contrasts the AI-DTWs to the base models that are in existence and emphasizes that the AI-DTWs has better capabilities in terms of predictiveness, scalability and optimizes the efficiency of operations, limiting downtime and increasing collaboration. The implications of AI-DTWs to the practitioners, policymakers and researchers are described, and some significant challenges, e.g. data interoperability, security and scalability are presented. The review ends with providing suggestions on recommendations of future research that should promote AI-driven digital twins centered around the development of AI algorithms, data integration, and the opportunity of advancing real-time data processing on complex systems.
Author: Ullas Das
Language: English
Subfield: Industrial and Manufacturing Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7083579019