Corrosion, construction flaws and overloading adversely impact structural health, and can lead to catastrophic failures. Continuous monitoring is the key to preventing such outcomes. We monitor our personal health with fitness trackers, keeping tabs on heart rate, activity, sleep patterns etc. for early warning of disease. Structural health monitoring (SHM) does the same for critical infrastructure, helping asset managers detect early warning signs of deterioration and damage. For managing data across hundreds or thousands of assets spread over several kilometers, it is critical to have scalable SHM solutions.

Despite the promise of permanently deployed long-term SHM systems, their industrial adoption as a replacement for periodic non-destructive testing (NDT) has been limited. This is usually due to a mix of organizational, business, and technical challenges, well laid out by Cawley et al. [1] Streaming raw data to centralized servers has large bandwidth and data costs, especially for distributed assets like bridges, pipelines, and wind farms. A key barrier lies in embedding data processing directly on edge devices, enabling on-site damage assessment and delivering clear, actionable insights to operators.

Recent research by our research group at IIT Bombay [2] introduces a novel, explainable unsupervised artificial intelligence (AI) framework for scalable machine fault detection in Industry 4.0. The framework was field-validated using data from 18 machines installed at three factories in India, monitored for several months. This approach addresses many challenges that resonate deeply with asset health monitoring. Using lightweight, explainable artificial intelligence (AI) models within the sensor node (edge), it is possible to directly detect early faults, even in changing operating conditions, without the need of large labeled datasets or heavy computational infrastructure.

Instead of relying on large datasets for training, Asutkar et al. showed how AI models can learn what “healthy” looks like post-deployment. For SHM, this means we can spot early changes in structural behavior, without having to invest in training large AI models.

The lightweight approach runs directly on edge devices, making it ideal for distributed networks of sensors. For SHM, this enables:

• Real-time detection at the asset
• Minimal data transfer: only critical alerts
• Scalable monitoring across many sites

Our team is adapting these principles to deliver SHM systems optimized for modern IoT infrastructure.

Cutting through noise: One challenge in SHM is telling real damage apart from changes caused by weather or usage or operating conditions. The trend-based classifier approach presented by Asutkar et al. only flags issues that persist, reducing false alarms.This makes monitoring more reliable and actionable for engineers and asset managers.

Making AI explainable: By using explainable AI, the system shows why an alert was raised, helping teams understand what changed. In SHM, this means faster decisions and more targeted inspections.

Scaling for real-world infrastructure: Proven across multiple datasets, this approach is highly scalable, just like SHM needs to be. Our solutions are:

• Data-efficient: work with limited damage history
• Scalable: fit for large infrastructure networks
• Explainable: insights, not just alarms
• Edge-ready: ideal for remote assets

As infrastructure ages, smarter, scalable SHM is vital. We’re creating edge-AI systems that detect problems early and explain their causes, helping you stay ahead of risks. From bridges to pipelines, we are helping keep critical infrastructure safe and future-ready.

1. Cawley, P. A development strategy for structural health monitoring applications. Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems 4, 041012 (2021).
2. Asutkar S. and Tallur S. An explainable unsupervised learning framework for scalable machine fault detection in Industry 4.0. Measurement Science and Technology, 34(10) 105123 (2023).

© 2025 Nirixense Technologies Pvt. Ltd. All rights reserved. email: connect@nirixense.com

About the Author: Dr. Siddharth Tallur is Co-founder & Director at Nirixense Technologies, and Associate Professor at Department of Electrical Engineering, IIT Bombay. His experience includes development of high resolution and low-cost sensors, high-speed instrumentation and embedded smart sensing systems. He obtained MS-Ph.D. degree from Cornell University (ECE, 2013), and B.Tech. from IIT Bombay (EE, 2008).

Note: This article presents the author’s personal views and insights drawn from publicly shareable aspects of research projects conducted as a faculty member at IIT Bombay. The content is intended solely for thought leadership and knowledge sharing. The views expressed do not necessarily represent those of IIT Bombay.