Grant: Alliance Grants

Keeping our infrastructure (bridges, roads, buildings) in safe and operational condition is a major challenge. The sudden pause in engineering and construction sector due to the COVID-19 pandemic can elevate the risk of unwanted accidents and mishaps above normal. When the safety is compromised, the overall infrastructure system becomes ineffective and public safety is under immense threat. To avoid such scenarios, the need for an efficient infrastructure management system cannot be overstated. The proposed research is designed to demonstrate how data analytics and machine learning models can help infrastructure owners and managers predict the condition of existing structures during the lockdown phase of this pandemic, using already available inspection and as-built data. This will aid in identifying safety hazards present during lockdowns at all engineered sites, whether for buildings, bridges or other infrastructure. Using COVID-19 spread and disruption data in a machine learning algorithm, this study will investigate how lockdowns along with revised ongoing-work methods or changed supervision practices could affect structural safety of Canadian infrastructure. This research aims to develop a decision support tool to enable risk-informed critical infrastructure identification based on possible cascade effects for addressing issues pertaining to aging and deteriorating infrastructure during future lockdowns. Combining the expertise of the applicant along with the experienced industry personnel from TBT Engineering Ltd., this project will develop an advanced tool with respect to enhance decision making on critical infrastructure to increase safety and decrease unexpected shutdown and/or failure. This research will also help TBTE to provide specialized services, which will play a significant role in the Canadian infrastructure industry to manage such emergencies during pandemic. The successful completion of the proposed research will pave the way toward resiliency of Canada's infrastructure network against the uncertainty arising from the lockdown.