Sbir phase II: development of an AI-based, IOT enabled system for structural health monitoring

The National Science Foundation (NSF) awarded a Cooperative Agreement under the Technology, Innovation, and Partnerships (CFDA 47.084) program to Canetia Analytics, Inc. for the development of an AI-based, IoT-enabled system for structural health monitoring. The $992,460 award, with a period of performance from May 1, 2025 to April 30, 2027, aims to create a technology solution that enables automated, remote, low-cost, and continuous assessment of the structural health of buildings and infrastructure assets. The project's broader commercial impact is expected to contribute significantly to the safety, sustainability, and resilience of infrastructure, addressing a $7.6 billion global market for structural health monitoring by 2030. The solution comprises an IoT device to record vibration data and a proprietary machine learning-based software to identify structural anomalies, enabling asset operators to lower ownership costs, improve maintenance efficiency, and reduce risks.

Abstract

The broader/commercial impact of this small business innovation research (sbir) phase II project is its significant contribution to safety, sustainability, and resilience of infrastructures and buildings, addressing a structural health monitoring (SHM) market that is expected to reach a value of $7.6 billion globally by 2030. The technology (internet of things (IOT) device + artificial intelligence (AI)-powered software sold as a software-as-a-service) enables fully automated, remote, low-cost, and continuous assessment of the structural health of buildings or infrastructure assets. The technology targets many structures for which current monitoring or risk assessment techniques are not economically viable, while minimizing staff exposure to risk and human errors. Structural failures can lead to an exceedingly high risk of economic loss (for bridge faults >$100 billion/year). Large-scale federal infrastructure investment programs are expected to address these losses and close critical infrastructure gaps (U.S. Bridge repair backlog >$125 billion). However, for these investments to realize their full economic potential, effective infrastructure assessment and maintenance processes are needed. This technology will allow asset operators to lower the costs of ownership, improve maintenance efficiency, and reduce risks, yielding a substantial return on investment (> $10,000/structure) within five years of operation. The intellectual merit of this project is based on its unique, highly scalable, and widely applicable approach. IT comprises an IOT device to record vibration data from structures and a proprietary machine-learning-based software to process the timeseries vibration data to identify anomalies indicative of structural faults or decay. Within the scope of the project, this approach will be evaluated and validated in real-world application domains by deploying IOT devices to five active road and rail bridges across the U.S. To collect a dataset of baseline real-world, vibration signatures from a wide variety of structures. The specific technical objectives of this project include the design of an IOT device, the data acquisition from real world assets and validation of the approach through comparisons with data collected from scale models of these real-world assets. The project addresses three key technical challenges: 1) the use of inherently noisy time series data that may affect the accuracy of the approach, 2) the generalizability of the approach in allowing for applications with a wide range of infrastructure assets and building types, and 3) a potential operational unreliability of the sensors upon their deployment to remote test sites. 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.- subawards are planned for this award.