SBIR Phase I: Development of an artificial iIntelligence (AI)-based, internet of things (IoT)-enabled system for structural health monitoring

Canetia Analytics, Inc., San Diego CA

Investigators

Abstract

The broader impact of this Small Business Innovation Research (SBIR) Phase I project is the low-cost assessment of the health of structures or buildings. Often property-owners and infrastructure managers do not have a true and fair view of the actual state of their building assets. Building health is assessed from infrequent inspections or monitoring that is often uneconomical for smaller structures. This project seeks to develop a technology that is able to discern structural anomalies to facilitate risk assessment and proper management. This technology seeks to disrupt the growing market of structural health monitoring, providing an affordable solution for the assessment of the current state of buildings and structures with benefit to cost ratios over 10, installation costs ranging between $10 to $1,000 per control point and Software as a Service (SaaS) costs ranging between $10 and $500 per month. Once on the market, the technology may help to avoid dramatic human, environmental, and economic losses caused by damaged or collapsed buildings and structures. This Small Business Innovation Research (SBIR) Phase I project seeks to develop a proof of concept solution featuring Internet of Things (IoT) sensors and Artificial Intelligence (AI) to provide insights into the conditions of buildings remotely and automatically by analyzing natural structural vibrations. The solution targets structureal assets that currently are rarely assessed but entail risk of failure. The technology takes advantages of the fact that each structure has its own natural vibration signature, which depends on its design and materials, purpose, and environment. Hidden signals of anomalies, which can be associated with degradation, flaws, or failures, can be found encoded within this vibration signature. This novel technology uses AI to provide insight into these signals and translate them into valuable information about the health of structures. The project seeks to validate the degree to which anomalous data clusters obtained from buildings or structures can be associated with damage or defects and may help to establish the precision and accuracy in anomaly detection. The project comprises the monitoring of real buildings or structures and the manufacturing of the necessary IoT devices, the structural analyses through numerical modelling, laboratory experiments with physical models, and the use of AI to control hazard risk. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.