Application of CNN and MLP models for structural health monitoring : A case study on Saigon Bridge

This paper presents an innovative approach to improve the assessment of mechanical responses in short-span bridges, introducing a novel method with significant implications for bridge engineering. The method integrates a convolutional neural network (CNN) and a multilayer perceptron (MLP) model to monitor stiffness degradation in bridge spans over time, representing a significant step forward in SHM techniques. By harnessing the power of neural networks, our approach enables simultaneous monitoring at multiple measurement points across spans or at various time intervals, providing valuable insights into bridge behavior. Through empirical validation, manuscript demonstrates the high accuracy achieved by our combined CNN and MLP model, augmented by power spectral density moments, in evaluating the quality of bridge projects throughout their operational lifespan. Moreover, our method proves highly effective in identifying potential hazardous areas on bridges and detecting structural damage in problematic spans, addressing critical safety concerns in infrastructure management. Furthermore, we propose the integration of data from both non-contact and contact sensors to further enhance the monitoring and assessment of bridge conditions, contributing to the development of more SHM strategies. Additionally, extending the scope of our research to encompass different bridge types and environmental conditions, such as marine environments or high-temperature settings, promises to elucidate the method’s versatility and widespread applicability in practical scenarios. Future directions for research include conducting additional real-world tests on bridge structures to validate the method’s feasibility and accuracy under diverse conditions. In summary, this paper not only presents a cutting-edge methodology for assessing bridge health but also sets the stage for future advancements in structural monitoring technology, with profound implications for the safety and longevity of bridge infrastructure worldwide.

© The Author(s) 2025.

This article is distributed under the terms of the Creative Commons Attribution 4.0 License (https://creativecommons.org/licenses/by/4.0/) which permits any use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).