Abstracts – Browse Results
Click on the titles below to expand the information about each abstract.
Viewing 1 results ...
Mahamedi, E, Wonders, M, Kassem, M, Woo, W L and Greenwood, D (2022) Digital Twin and Building Performance: A Review and Proposed Framework. In: Tutesigensi, A and Neilson, C J (Eds.), Proceedings 38th Annual ARCOM Conference, 5-7 September 2022, Glasgow Caledonian University, Glasgow, UK. Association of Researchers in Construction Management, 581-690.
- Type: Conference Proceedings
- Keywords: Digital twins, Machine learning, Artificial intelligence, Building performance, Predictive models.
- ISBN/ISSN: 978-0-9955463-6-3
- URL: http://www.arcom.ac.uk/-docs/proceedings/dee14e2cd85e2a748c9dc9ce93bb6ee8.pdf
- Abstract:
<p>The use of Digital Twin (DT) as an emerging technology-led development encompasses data-driven methods which bring the benefit of enhancing better understanding of building performance and providing relevant information for decision making. Extensive reviews intersecting the DT concept with building performance are lacking. The aim of this paper is to present such a review and propose a framework for using DTs to develop predictive models to improve the performance of buildings. The review analyses recent studies on energy prediction performance and fault detection in building maintenance using data-driven models, and further identifies the remaining gaps in the literature. The framework incorporates artificial intelligence (AI), machine-learning (ML), and cloud computing technology in a scalable prototype solution to efficiently capture, process, and integrate real-time building data in a timely manner. The framework is expected to help decision-makers gain valuable insights into the building performance, which will then inform interventions for improving the energy efficiency.</p>