IIT Mandi develops AI-based structural health monitoring

15 Sep 2023 CW Team

The application of these AI-based algorithms extends well beyond bridges and can be adapted for assessing the health of various structures, including ropeways, buildings, aerospace structures, transmission towers, and other components of essential infrastructure that require regular health assessments and protective measures.

Structures like bridges are subjected to natural ageing processes due to environmental factors such as temperature fluctuations, exposure to water and air, and the added stress of heavy road traffic. Traditionally, assessing the condition of bridges has heavily relied on visual inspections, which are often deemed inadequate by experts in the field. Visual inspections are subjective, time-consuming, and involve manual analysis of numerous photographs. As such, they fall short of detecting all structural issues, which can be detrimental to ensuring the safety and reliability of these vital structures.

The recent breakthrough achieved by the researchers at IIT Mandi and INRIA leverages recent advances in instrumentation, data analysis, and AI tools like deep learning to enhance structural health monitoring. These technologies facilitate the detection, measurement, understanding, and prediction of defects in structures over time. Consequently, they enable more effective planning for renovation or repair work, ultimately reducing maintenance costs and extending the lifespan and availability of bridges and other infrastructure.

The team at IIT Mandi has developed a Deep Learning-based SHM approach that relies on AI algorithms to identify and isolate structural damages by analyzing recorded ambient dynamic responses without requiring human intervention. This innovative method is based on data-driven techniques such as Machine Learning, AI, and Bayesian statistical inference, which estimate a bridge's health and predict its remaining usable life. This outcome has the potential to reduce risks to infrastructure, particularly under operational and adverse loading conditions.

One critical aspect considered in the AI-based SHM approach is the impact of temperature fluctuations on a bridge's dynamic traits, especially in structures like prestressed concrete and cable-stayed bridges. The algorithm developed by IIT Mandi was rigorously tested on a real bridge located in a cold region with extreme annual and daily temperature swings. The results demonstrated its effectiveness in identifying structural damage caused by various factors, including temperature fluctuations.

In another related study, the researchers employed advanced filtering techniques to assess the condition of different structural components without the need for direct measurement of their connections. This technique allows for the separate assessment of each component's health, aiding in the evaluation of overall structural integrity. Through computer simulations and extensive testing, the researchers verified the method's robust performance, even in the presence of background noise and varying levels of damage severity.

This groundbreaking research not only advances the field of structural health monitoring but also paves the way for safer, more efficient, and cost-effective maintenance and repair of critical infrastructure, benefiting society as a whole.

Researchers at the Indian Institute of Technology (IIT) in Mandi, in collaboration with France's National Institute for Research in Digital Science and Technology (INRIA), have made significant strides in the field of structural health monitoring (SHM) by harnessing the power of artificial intelligence (AI) and advanced signal processing techniques. Their innovative approach utilizes AI algorithms to accurately predict the structural health of bridges and other critical infrastructure, marking a substantial departure from traditional, manual inspection methods.The application of these AI-based algorithms extends well beyond bridges and can be adapted for assessing the health of various structures, including ropeways, buildings, aerospace structures, transmission towers, and other components of essential infrastructure that require regular health assessments and protective measures.Structures like bridges are subjected to natural ageing processes due to environmental factors such as temperature fluctuations, exposure to water and air, and the added stress of heavy road traffic. Traditionally, assessing the condition of bridges has heavily relied on visual inspections, which are often deemed inadequate by experts in the field. Visual inspections are subjective, time-consuming, and involve manual analysis of numerous photographs. As such, they fall short of detecting all structural issues, which can be detrimental to ensuring the safety and reliability of these vital structures.The recent breakthrough achieved by the researchers at IIT Mandi and INRIA leverages recent advances in instrumentation, data analysis, and AI tools like deep learning to enhance structural health monitoring. These technologies facilitate the detection, measurement, understanding, and prediction of defects in structures over time. Consequently, they enable more effective planning for renovation or repair work, ultimately reducing maintenance costs and extending the lifespan and availability of bridges and other infrastructure.The team at IIT Mandi has developed a Deep Learning-based SHM approach that relies on AI algorithms to identify and isolate structural damages by analyzing recorded ambient dynamic responses without requiring human intervention. This innovative method is based on data-driven techniques such as Machine Learning, AI, and Bayesian statistical inference, which estimate a bridge's health and predict its remaining usable life. This outcome has the potential to reduce risks to infrastructure, particularly under operational and adverse loading conditions.One critical aspect considered in the AI-based SHM approach is the impact of temperature fluctuations on a bridge's dynamic traits, especially in structures like prestressed concrete and cable-stayed bridges. The algorithm developed by IIT Mandi was rigorously tested on a real bridge located in a cold region with extreme annual and daily temperature swings. The results demonstrated its effectiveness in identifying structural damage caused by various factors, including temperature fluctuations.In another related study, the researchers employed advanced filtering techniques to assess the condition of different structural components without the need for direct measurement of their connections. This technique allows for the separate assessment of each component's health, aiding in the evaluation of overall structural integrity. Through computer simulations and extensive testing, the researchers verified the method's robust performance, even in the presence of background noise and varying levels of damage severity.This groundbreaking research not only advances the field of structural health monitoring but also paves the way for safer, more efficient, and cost-effective maintenance and repair of critical infrastructure, benefiting society as a whole.