Scholarlink

<p>Structural Health Monitoring (SHM) of bridges plays a pivotal role in sustaining infrastructure reliability and public safety. However, conventional vibration-based approaches encounter significant challenges such as susceptibility to environmental variability and heavy dependence on baseline data, which limit their effectiveness in complex operational environments. This systematic review aims to critically evaluate recent advancements in vibration-based SHM methodologies, with a focus on the integration of Artificial Intelligence (AI) and Machine Learning (ML) techniques from 2014 to 2025. A systematic literature review was conducted using Scopus as the primary database, guided by the PRISMA framework, encompassing 51 peer-reviewed journal articles published between 2014 and 2025. The findings highlight significant methodological advancements, including the application of supervised neural networks, unsupervised learning algorithms such as autoencoders, hybrid AI models integrating physics-informed neural networks (PINNs), and Bayesian approaches for uncertainty quantification. AI-driven methods demonstrated enhanced accuracy, robustness, and scalability, addressing critical limitations of conventional SHM systems. However, challenges persist, particularly in terms of computational complexity, the requirement for large labelled datasets, generalization across bridge types, and limited field-based validation. This study underscores the potential of hybrid AI approaches and identifies several research gaps. Future directions include enhanced field-based validations, integration of optimal sensor placement techniques, development of interpretable models, and predictive maintenance strategies incorporating Remaining Useful Life (RUL) estimation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Emerging trends in machine learning applications for structural health monitoring of bridges

  • 期刊论文

  • 发表日期：

    2025年8月19日

查看全文
  • Ahmad Kamil Aminuddin,
  • Sakhiah Abdul Kudus,
  • Adiza Jamadin,
  • Mohamad Farid Misnan,
  • Zainorizuan Mohd Jaini,
  • Akihiko Sato

摘要

Structural Health Monitoring (SHM) of bridges plays a pivotal role in sustaining infrastructure reliability and public safety. However, conventional vibration-based approaches encounter significant challenges such as susceptibility to environmental variability and heavy dependence on baseline data, which limit their effectiveness in complex operational environments. This systematic review aims to critically evaluate recent advancements in vibration-based SHM methodologies, with a focus on the integration of Artificial Intelligence (AI) and Machine Learning (ML) techniques from 2014 to 2025. A systematic literature review was conducted using Scopus as the primary database, guided by the PRISMA framework, encompassing 51 peer-reviewed journal articles published between 2014 and 2025. The findings highlight significant methodological advancements, including the application of supervised neural networks, unsupervised learning algorithms such as autoencoders, hybrid AI models integrating physics-informed neural networks (PINNs), and Bayesian approaches for uncertainty quantification. AI-driven methods demonstrated enhanced accuracy, robustness, and scalability, addressing critical limitations of conventional SHM systems. However, challenges persist, particularly in terms of computational complexity, the requirement for large labelled datasets, generalization across bridge types, and limited field-based validation. This study underscores the potential of hybrid AI approaches and identifies several research gaps. Future directions include enhanced field-based validations, integration of optimal sensor placement techniques, development of interpretable models, and predictive maintenance strategies incorporating Remaining Useful Life (RUL) estimation.