Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

Concordia University

$32,000.00

Digitalization of Industrial Facilities using Scan-to-BIM

EF 2024-25

Résumé
In the context of the 4th industrial revolution, the concept of digital twin (DT) has been highlighted as a path forward for the industrial sectors. A key element of DT is a highly detailed 3D model of the physical space known as Building Information Model (BIM), on which multidimensional data is integrated to manage the entire project lifecycle. However, a majority of the existing industrial facilities lack BIM or possess an inaccurate outdated version due to substantial effort required in manual development. An active field of research called Scan-to-BIM can alleviate this issue by automating an as-built BIM generation process. Yet, existing Scan-to-BIM technologies are still in pre-mature stage for industrial projects due to lack of available dataset, geometrical complexity, and modeling demand with a high level of detail. The proposed Scan-to-BIM framework has potential to overcome these challenges leveraging computer vision and domain-context knowledge coupled with artificial Intelligence (AI). To resolve the data scarcity issue, a generative design approach will be applied to generate synthetic BIMs with user-specified components, and abundant 3D data will be generated by placing virtual scanners inside the BIM environment. Also, translating the detailed geometry of the physical facility into machine-interpretable information is difficult due to complex design and spatial distribution of the systems. A series of AI models will advance the state of the semantic understanding ability by reducing the gap from category-level to shape-level of detail modeling. Digital model database will be constructed to retrieve the most relevant 3D objects based on the interpreted semantic information. In addition, the practicality of Scan-to-BIM adoption will be investigated through economic feasibility analysis for the industrial decision makers. This automatic BIM modeling will benefit the industries not only by increasing the overall efficiencies through digitalization, but ultimately it will accelerate the transformation of the current practices to fully utilizing digital twin. The research outcomes of this discovery grant program will be: 1) a context-aware generative design framework for industrial sector, 2) design variant industrial BIMs and annotated synthetic point clouds, 3) a single deep learning-based pipeline for reconstructing the physical industrial objects, and 4) an economic feasibility analysis for the decision-makers.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2023-05652
Name nom
Ma, Jong Won
Department département
Building, Civil and Environmental Engineering
Organization id
70
Institution établissement
Concordia University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
32000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1509
Committee name en
Civil, Industrial and Systems Engineering
Committee name fr
Génie civil, industriel et des systèmes
Area of application code
1206
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Engineering
Area of application fr
Génie
Research subject code
1001
Research subject group en
Civil engineering
Research subject group fr
Génie civil
Research subject en
Construction engineering and management
Research subject fr
Génie et gestion du bâtiment
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Digitalization of Industrial Facilities using Scan-to-BIM
Keywords
building information model; scan-to-bim; digitalization; industrial projects; facility management; simulation; artificial intelligence; computer vision; deep learning; knowledge graph
Application summary
In the context of the 4th industrial revolution, the concept of digital twin (DT) has been highlighted as a path forward for the industrial sectors. A key element of DT is a highly detailed 3D model of the physical space known as Building Information Model (BIM), on which multidimensional data is integrated to manage the entire project lifecycle. However, a majority of the existing industrial facilities lack BIM or possess an inaccurate outdated version due to substantial effort required in manual development. An active field of research called Scan-to-BIM can alleviate this issue by automating an as-built BIM generation process. Yet, existing Scan-to-BIM technologies are still in pre-mature stage for industrial projects due to lack of available dataset, geometrical complexity, and modeling demand with a high level of detail. The proposed Scan-to-BIM framework has potential to overcome these challenges leveraging computer vision and domain-context knowledge coupled with artificial Intelligence (AI). To resolve the data scarcity issue, a generative design approach will be applied to generate synthetic BIMs with user-specified components, and abundant 3D data will be generated by placing virtual scanners inside the BIM environment. Also, translating the detailed geometry of the physical facility into machine-interpretable information is difficult due to complex design and spatial distribution of the systems. A series of AI models will advance the state of the semantic understanding ability by reducing the gap from category-level to shape-level of detail modeling. Digital model database will be constructed to retrieve the most relevant 3D objects based on the interpreted semantic information. In addition, the practicality of Scan-to-BIM adoption will be investigated through economic feasibility analysis for the industrial decision makers. This automatic BIM modeling will benefit the industries not only by increasing the overall efficiencies through digitalization, but ultimately it will accelerate the transformation of the current practices to fully utilizing digital twin. The research outcomes of this discovery grant program will be: 1) a context-aware generative design framework for industrial sector, 2) design variant industrial BIMs and annotated synthetic point clouds, 3) a single deep learning-based pipeline for reconstructing the physical industrial objects, and 4) an economic feasibility analysis for the decision-makers.