Grant: Alliance Grants
Concordia University
$30,000.00
Physics-informed Neural Network for Structural Digital Twin of bridge infrastructures
FY 2024-25
Summary
Transportation infrastructure is the backbone of modern society and bridges are the bottleneck of the transportation network. Corrosion and cracking in concrete infrastructure are the most common cause of deterioration leading to structural collapses. Structural Digital Twin (SDT) of an infrastructure, brings together "data" and "models" to provide a platform for structural simulation and automatically update itself from multiple sources of sensory data to represent an ever-up-to-date simulation of its physical counterpart. To this date, advanced structural simulations are typically conducted through nonlinear Finite Element Analysis (FEA), which exhibits major drawbacks hindering its application for large-scale SDTs, namely high computational time/power demand, convergence problems, and limitations in model updating based on sensor data. This NSERC Alliance/Mitacs Accelerate joint proposal is a partnership between Concordia University and Timezyx company, based in Vancouver, BC, to address the challenges in digital twinning of critical infrastructure, specifically bridges, from a Structural Health Monitoring (SHM) angle, by implementing a closed-loop and computationally affordable cyber-physical system. Both theoretical foundations and algorithms for such a solution will be developed and deployed in action. The proposed approach is based on real-time prediction of the structural response of a bridge by creating, updating, validating, and maintaining an SDT solution founded on the framework of Physics-Informed Neural Network (PINN). The specific objectives are to develop PINN-based solutions for structural analysis of reinforced concrete beams and to deploy, verify and validate the implemented solution in full-scale real-world structures against conventional structural FEAs and with readily available experimental data. Beyond the immediate scientific objectives, the project exhibits the outstanding prospect of a full-scale demonstration on a real bridge which is very rare in this field. 1 PDF, 1 PhD and 2 MSc students will be recruited by this project as HQP, and besides the Alliance, they will complete 6 Mitacs Internship Units during the 2-year period of the project.
Program
Alliance Grants
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
586343-2023
Name nom
Nik Bakht, Mazdak MN
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
30000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1001
Area of application group en
Northern development
Area of application group fr
Développement du nord
Area of application en
Construction, transportation and communications
Area of application fr
Construction, transports et communications
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
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
Physics-informed Neural Network for Structural Digital Twin of bridge infrastructures
Keywords
applied machine learning; bridge maintenance; defect detection; digital twin; finite elements analysis; infrastructure asset management; infrastructure resilience; physics informed neural networks; smart infrastrucure; structural health monitoring
Application summary
Transportation infrastructure is the backbone of modern society and bridges are the bottleneck of the transportation network. Corrosion and cracking in concrete infrastructure are the most common cause of deterioration leading to structural collapses. Structural Digital Twin (SDT) of an infrastructure, brings together "data" and "models" to provide a platform for structural simulation and automatically update itself from multiple sources of sensory data to represent an ever-up-to-date simulation of its physical counterpart. To this date, advanced structural simulations are typically conducted through nonlinear Finite Element Analysis (FEA), which exhibits major drawbacks hindering its application for large-scale SDTs, namely high computational time/power demand, convergence problems, and limitations in model updating based on sensor data. This NSERC Alliance/Mitacs Accelerate joint proposal is a partnership between Concordia University and Timezyx company, based in Vancouver, BC, to address the challenges in digital twinning of critical infrastructure, specifically bridges, from a Structural Health Monitoring (SHM) angle, by implementing a closed-loop and computationally affordable cyber-physical system. Both theoretical foundations and algorithms for such a solution will be developed and deployed in action. The proposed approach is based on real-time prediction of the structural response of a bridge by creating, updating, validating, and maintaining an SDT solution founded on the framework of Physics-Informed Neural Network (PINN). The specific objectives are to develop PINN-based solutions for structural analysis of reinforced concrete beams and to deploy, verify and validate the implemented solution in full-scale real-world structures against conventional structural FEAs and with readily available experimental data. Beyond the immediate scientific objectives, the project exhibits the outstanding prospect of a full-scale demonstration on a real bridge which is very rare in this field. 1 PDF, 1 PhD and 2 MSc students will be recruited by this project as HQP, and besides the Alliance, they will complete 6 Mitacs Internship Units during the 2-year period of the project.