Integrating digital twins and data-driven predictive models to enhance infrastructure assets safety

This research project aims to improve the safety and maintenance of bridges by using advanced technology and methods to predict how bridges will respond to stress due to temperature fluctuations over time. Several sensors are installed on different elements of the bridge to measure strain and temperature values every second. The data is then analyzed using machine learning models to predict extreme strain values before they become serious problems. This proactive approach allows the partner organization to maintain the bridge more efficiently and cost-effectively, ensuring it remains safe for public use and extends its lifespan. Ultimately, this project helps create safer, more reliable infrastructure while reducing maintenance costs and preventing unexpected bridge closures.

Faculty Supervisor:

Ali Motamedi;Érik Andrew Poirier

Student:

Partner:

CIMA+ (Montreal, QC)

Discipline:

Engineering

Sector:

Professional, scientific and technical services

University:

École de technologie supérieure

Program: