Buildings (Aug 2024)

Digital Twins in Construction: Architecture, Applications, Trends and Challenges

  • Zhou Yang,
  • Chao Tang,
  • Tongrui Zhang,
  • Zhongjian Zhang,
  • Dat Tien Doan

DOI
https://doi.org/10.3390/buildings14092616
Journal volume & issue
Vol. 14, no. 9
p. 2616

Abstract

Read online

The construction field currently suffers from low productivity, a lack of expertise among practitioners, weak innovation, and lack of predictability. The digital twin, an advanced digital technology, empowers the construction sector to advance towards intelligent construction and digital transformation. It ultimately aims for highly accurate digital simulation to achieve comprehensive optimization of all phases of a construction project. Currently, the process of digital twin applications is facing challenges such as poor data quality, the inability to harmonize types that are difficult to integrate, and insufficient data security. Further research on the application of digital twins in the construction domain is still needed to accelerate the development of digital twins and promote their practical application. This paper analyzes the commonly used architectures for digital twins in the construction domain in the literature and summarizes the commonly used technologies to implement the architectures, including artificial intelligence, machine learning, data mining, cyber–physical systems, internet of things, virtual reality, augmented reality applications, and considers their advantages and limitations. The focus of this paper is centered on the application of digital twins in the entire lifecycle of a construction project, which includes the design, construction, operation, maintenance, demolition and restoration phases. Digital twins are mainly moving towards the integration of data and information, model automation, intelligent system control, and data security and privacy. Digital twins present data management and integration challenges, privacy and security protection, technical manpower development, and transformation needs. Future research should address these challenges by improving data quality, developing robust integration methodologies, and strengthening data security measures.

Keywords