Leveraging AI And Sensor Technologies For Real-Time Structural Health Monitoring Of In-Service Bridges
Open Access
- 6 January 2025
- journal article
- Published by AIM International Journal in Frontiers in Applied Engineering and Technology
- Vol. 2 (1) , 135-163
Abstract
The increasing demand for efficient and proactive bridge maintenance solutions has led to the rapid adoption of Artificial Intelligence (AI)-driven Structural Health Monitoring (SHM) systems, integrating machine learning, IoT-enabled sensor networks, computer vision, predictive maintenance models, drone-assisted inspections, and blockchain-based security frameworks. Traditional bridge inspection methods, which rely on manual evaluations and periodic assessments, often fail to detect early-stage structural damage, are labor-intensive, and incur high operational costs. This study systematically reviewed 75 high-quality peer-reviewed articles published between 2015 and 2024, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, to assess the efficacy, scalability, and economic feasibility of AI-based SHM technologies. The findings indicate that machine learning algorithms outperform traditional inspection techniques, achieving over 90% accuracy in crack and fatigue detection, while predictive maintenance models reduce maintenance costs by 30–50% by optimizing intervention strategies and minimizing emergency repairs. The study further highlights the role of IoT-enabled wireless sensor networks and fiber optic sensors, which have improved real-time monitoring capabilities, reducing data acquisition time by 65% and enabling continuous structural assessments without disrupting bridge operations. AI-assisted drone inspections have significantly improved damage detection efficiency by 85%, reducing inspection time by up to 60%, proving the viability of autonomous UAV-based SHM applications. Additionally, blockchain-secured sensor networks have been found to enhance data integrity and cybersecurity, reducing data breaches by 65% and ensuring tamper-proof sensor-generated records, addressing one of the critical security concerns in modern infrastructure monitoring. Despite these advancements, the study identifies key implementation challenges, including computational costs, data interoperability issues, scalability constraints, and regulatory barriers, that must be addressed for wider adoption of AI-driven SHM frameworks. The review underscores the transformative impact of AI-powered SHM technologies, highlighting their potential to enhance bridge safety, optimize maintenance efficiency, and extend infrastructure lifespan, making them an essential component of next-generation smart infrastructure management.Keywords
This publication has 135 references indexed in Scilit:
- Impacts of Modern AI and ML Trends2023
- Identifying issues in adoption of AI practices in construction supply chains: towards managing sustainabilityOperations Management Research, 2023
- Machine learning‐based automatic operational modal analysis: A structural health monitoring application to masonry arch bridgesStructural Control and Health Monitoring, 2022
- Bridge damage detection via improved completed ensemble empirical mode decomposition with adaptive noise and machine learning algorithmsStructural Control and Health Monitoring, 2022
- Convolutional neural network and its pretrained models for image classification and object detection: A surveyConcurrency and Computation: Practice and Experience, 2021
- Bayesian Deep Learning for Vibration-Based Bridge Damage Detection2021
- A Forward Model Driven Structural Health Monitoring Paradigm: Damage Detection2021
- Security, Privacy and Risks Within Smart Cities: Literature Review and Development of a Smart City Interaction FrameworkInformation Systems Frontiers, 2020
- Structural Health Monitoring (SHM)2018
- Developing a pattern-based method for detecting defective sensors in an instrumented bridgeJournal of Civil Structural Health Monitoring, 2013