Advancements and emerging trends in integrating machine learning and deep learning for SHM in mechanical and civil engineering: a comprehensive review

The safety of structures heavily relies on the crucial role of structural health monitoring (SHM), reliability, and longevity of mechanical and civil infrastructure. Traditional methods of SHM often rely on manual inspection and monitoring techniques, which can be time-consuming, expensive, and prone to human error. In recent years, the integration of machine learning (ML) and deep learning (DL) techniques has shown great promise in revolutionizing SHM by enabling automated and accurate monitoring of structural conditions. This review paper provides a comprehensive analysis of the application of ML and DL algorithms, such as artificial neural networks (ANN), convolutional neural networks (CNN), and deep neural networks (DNN), in SHM. It explores the various approaches and methodologies employed in the field, including supervised, unsupervised, and reinforcement learning techniques. The paper discusses the advantages and limitations of ML and DL in SHM, highlighting their ability to handle large volumes of data, extract complex features, and provide real-time monitoring and predictive capabilities. Moreover, it addresses the challenges associated with implementing ML and DL in SHM, including data limitations, model complexity, interpretability, and the integration of domain knowledge. By reviewing a wide range of studies and applications, this paper aims to provide valuable insights into the current state-of-the-art, emerging trends, and future directions in ML and DL-based SHM.