An online prediction method for array antenna assembly performance based on digital twin

Xuepeng Guo (), Linyan Liu (), HuiFen Wang (), Yue Li (), XiaoDong Du (), JianCheng Shi () and Yue Wang ()
Additional contact information
Xuepeng Guo: Nanjing University of Science and Technology
Linyan Liu: Nanjing University of Science and Technology
HuiFen Wang: Nanjing University of Science and Technology
Yue Li: Nanjing University of Science and Technology
XiaoDong Du: China Electronics Technology Group Corporation
JianCheng Shi: China Electronics Technology Group Corporation
Yue Wang: Chongqing University of Posts and Telecommunications

Journal of Intelligent Manufacturing, 2025, vol. 36, issue 4, No 25, 2727-2748

Abstract: Abstract In the actual array antenna assembly process, changes in the assembly process parameters strongly impact the solder joints. Thus, it is always necessary to pay attention to the stress‒strain situation of solder joints to avoid their failure and affecting the overall performance of the resulting antenna products. In this paper, based on digital twin and cloud-edge collaboration technology, an online prediction method for array antenna assembly performance based on digital twinning and cloud-edge collaboration technology is proposed. First, key assembly process parameters such as the tightening torque, tightening sequence and part flatness of the array antenna are used as simulation inputs to carry out the finite element simulation. The mapping relationships between the assembly process parameters and assembly performance are determined, and simulation data samples are constructed. Then, a prediction method that combines ensemble learning and a BP neural network is proposed for assembly performance prediction of array antennas, and an assembly performance prediction model is constructed to realize the online prediction of assembly performance. The results show that the prediction is as expected. Finally, a digital twin-cloud-edge collaborative antenna assembly process performance prediction system is constructed, and real-time monitoring of antenna assembly performance is performed when applied to an array antenna assembly process. The instance validation showed that the developed online prediction model has an average accuracy of 94.35%. This real-time monitoring method can ensure critical solder joint performance and improve the success rate of antenna assembly.

Keywords: Digital twin; Cloud-edge collaboration; Ensemble learning; Online prediction; Array antenna (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-024-02384-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:36:y:2025:i:4:d:10.1007_s10845-024-02384-5

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-024-02384-5

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().