Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Engage Grants Program

University of Manitoba

$25,000.00

Unsupervised machine learning method for structural damage assessement

FY 2016-17

Summary
Crosier Kilgour & Partners Ltd (CKP) is a national firm that provides precision consulting and structuralengineering services to clients on the application of structural design and inspection analysis. As one of theinspection analysis examples, CKP wants to accurately assess damage of a reinforced concrete (RC) parkadestructure. However, using existing techniques such as visual inspection or simple nondestructive testing, it isdifficult to detect and localize internal damages such as voids and delaminations. In recent years, manymethods have been proposed and developed, using supervised machine learning algorithms, for detection andlocalization of structural damage to prevent sudden collapse of civil structures. These supervised trainingmodes require normal and abnormal data to detect and localize damage; however, abnormal data representingvarious states of damage are quite rare, thereby limiting the applications of supervised methods. In order toaddress these disadvantages of traditional approaches, the applicant developed a new unsupervised method fordetection and localization of structural damages, using an advanced density peaks-based fast clusteringalgorithm (DPFCA), and published this method as a peer-reviewed article. This DPFCA will be applied to theparkade structure to detect and localize internal damages. From extensive experimental studies with variousstructural damage scenarios, the DPFCA will be improved to address environmental effects such astemperature and humidity. From the proposed research project, more accurate damage localization and repair ofcivil infrastructure are possible to improve public safety and avoid the costs (potential business disruption andpersonal injury) associated with catastrophic failure. Moreover, lower damage assessment costs forinfrastructure owners (e.g. municipalities), and potential application to damage-detection and localization incomplicated, multi-story and multi-bay structures will be realized, which can lead the company's ability toexpand its services to a broad client leading to more jobs and direct economic activity.
Program
Engage Grants Program
Location
Manitoba, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
500937-2016
Name nom
Cha, YoungJin
Department département
Civil Engineering
Organization id
19
Institution établissement
University of Manitoba
Province en
Manitoba
Province fr
Manitoba
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1555
Committee name en
Prairie Internal Decision Committee
Committee name fr
Comité de décision interne pour les Prairies
Area of application code
601
Area of application group en
Construction, urban and rural planning
Area of application group fr
Construction, urbanisme et aménagement rural
Area of application en
Structural engineering
Area of application fr
Génie des charpentes
Research subject code
1000
Research subject group en
Civil engineering
Research subject group fr
Génie civil
Research subject en
Civil engineering
Research subject fr
Génie civil
Partie
1
Nb partie
1
Application title
Unsupervised machine learning method for structural damage assessement
Keyword
NSERC
Application summary
Crosier Kilgour & Partners Ltd (CKP) is a national firm that provides precision consulting and structuralengineering services to clients on the application of structural design and inspection analysis. As one of theinspection analysis examples, CKP wants to accurately assess damage of a reinforced concrete (RC) parkadestructure. However, using existing techniques such as visual inspection or simple nondestructive testing, it isdifficult to detect and localize internal damages such as voids and delaminations. In recent years, manymethods have been proposed and developed, using supervised machine learning algorithms, for detection andlocalization of structural damage to prevent sudden collapse of civil structures. These supervised trainingmodes require normal and abnormal data to detect and localize damage; however, abnormal data representingvarious states of damage are quite rare, thereby limiting the applications of supervised methods. In order toaddress these disadvantages of traditional approaches, the applicant developed a new unsupervised method fordetection and localization of structural damages, using an advanced density peaks-based fast clusteringalgorithm (DPFCA), and published this method as a peer-reviewed article. This DPFCA will be applied to theparkade structure to detect and localize internal damages. From extensive experimental studies with variousstructural damage scenarios, the DPFCA will be improved to address environmental effects such astemperature and humidity. From the proposed research project, more accurate damage localization and repair ofcivil infrastructure are possible to improve public safety and avoid the costs (potential business disruption andpersonal injury) associated with catastrophic failure. Moreover, lower damage assessment costs forinfrastructure owners (e.g. municipalities), and potential application to damage-detection and localization incomplicated, multi-story and multi-bay structures will be realized, which can lead the company's ability toexpand its services to a broad client leading to more jobs and direct economic activity.