Digital Twin Service

Aims & Scope

Digital Twin technology, as an emerging transformative technology, is profoundly influencing service models across numerous industries. With the growing demand for intelligent services, Digital Twin enables real-time interaction between the virtual and physical worlds, providing significant support for optimizing service processes, improving efficiency, and offering personalized services. This technology creates new opportunities for service upgrades and improvements across various fields. Digital Twin intelligent services focus on high-level application services, relying on the coupling interaction between data and virtual-physical objects. Through prediction and iterative optimization, they approach service task requirements, promote the integration, sharing, and balanced allocation of service elements in the virtual-physical space, thereby providing precise, efficient, and personalized services, driving the intelligent and dynamic adaptation of service systems. This session aims to showcase innovative research from both theoretical and practical perspectives, exploring the challenges and opportunities brought by the integration of Digital Twin technology and intelligent services. 

 

The session will focus on the following aspects:

▪ Digital Twin key technologies and service optimization management methods

▪Service emotional perception and interaction

▪Application of artificial intelligence in Digital Twin Services

▪Service supply chain optimization based on Digital Twin technology

▪Digital Twin-driven service collaboration model innovation and design
▪Design and application of Digital Twin service platforms

------

For session presentation applications, please contact the session chairs below:

Feng Xiang

Email: xiangfeng#wust.edu.cn (replace # with @)

Yuanfa Dong

Email: dongyf#ctgu.edu.cn (replace # with @)


Session Chairs

Presentations

  • Assistant Professor
    Harbin Institute of Technology
    Title: Optimal Sensor Placement for Predicting the Load-Carrying Capacity of Composite Laminates with Delamination
    Abstract A method of optimization of sensor placement (OSP) to predict the load-carrying capacity of composite laminates with delamination is proposed. Due to unknown delamination sizes, OSP becomes an NP-hard problem, solved here using a genetic algorithm (GA). The fitness function of GA incorporates parameter identification error and relative entropy. Numerical and experimental tests on laminates with embedded delamination show that OSP outperforms uniform sensor distributions, improving parameter identification and load prediction with limited data. Meanwhile, experiments confirm strain arrays effectively detect delamination-induced local buckling. This approach provides beneficial support for the implementation of digital twins in composite structures.