A Machine Learning-Based Approach for BIM Object Localization

Jing Wang (), Weisheng Lu, Fan Xue and Meng Ye
Additional contact information
Jing Wang: The University of Hong Kong
Weisheng Lu: The University of Hong Kong
Fan Xue: The University of Hong Kong
Meng Ye: The University of Hong Kong

A chapter in Proceedings of the 24th International Symposium on Advancement of Construction Management and Real Estate, 2021, pp 1391-1399 from Springer

Abstract: Abstract This research is positioned in the growing need for Building Information Modelling (BIM) localization to effectively use global BIM resources in a locality. It focuses on BIM objects, which are not only the primary ‘building blocks’ of modelling but also the fundamental elements conveying the BIM information. The problem here is that BIM objects from global libraries may contain general, ambiguous, inconsistent, and missing information, thus incurring considerable manual adjustment efforts to use BIM objects of this kind in local projects. This paper aims to propose a machine learning (ML)-based approach to automatically localize (i.e., enrich and modify) BIM objects and their associated information to suit the local needs. The approach comprises of three steps: (1) characterizing a BIM object; (2) developing a local object configurator (LOC) based on ML; and (3) training, calibrating, and applying the LOC for bulk BIM objects localization. This study contributes a methodological framework to develop the ML approach for BIM object localization. The outcomes of the study can also boost the development of local BIM object libraries at both industry and company level.

Keywords: Building information modelling (BIM); BIM objects; Semantic enrichment; Machine learning (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (1)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:sprchp:978-981-15-8892-1_97

Ordering information: This item can be ordered from
http://www.springer.com/9789811588921

DOI: 10.1007/978-981-15-8892-1_97

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().