We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
A modelling and updating approach of digital twin based on surrogate model to rapidly evaluate product performance.
- Authors
Liu, Xinyu; Han, Xu; Wang, Honghui; Liu, Guijie
- Abstract
As a technology for the interaction and integration of products and simulation models, the digital twin can achieve accurate prediction and evaluation of product performance. However, the accurate model base is computationally complex, has a long iteration time, and is unable to perceive changes in the operating state in time. This leads to poor adaptability of the model and low efficiency of performance evaluation. The surrogate model can simplify the above model and improve computational efficiency. Based on this, this paper proposes a digital twin modelling and updating approach. The surrogate model is applied to the digital twin modelling process, which can accurately describe the physical mechanism and achieve interaction with the physical world. Then, this paper defines the consistency metric function, which achieves the rapid perception of the operation state and follows the physical world. Meanwhile, an improved LHS-Adam model update algorithm is used to adaptively update the model structure, improving the efficiency of the model parameters adjustment. Finally, experiments are conducted on the bogie suspension system to verify the feasibility and effectiveness of the update method in practical applications. The experimental results show that the established digital twin model has good updating performance and more efficient performance evaluation capability.
- Publication
International Journal of Advanced Manufacturing Technology, 2023, Vol 129, Issue 11/12, p5059
- ISSN
0268-3768
- Publication type
Article
- DOI
10.1007/s00170-023-12646-w