Modelling bridge deterioration using long short-term memory neural networks: a deep learning-based approach
Abstract
Purpose
Bridge deterioration is a critical risk to public safety, which mandates regular inspection and maintenance to ensure sustainable transport services. Many models have been developed to aid in understanding deterioration patterns and in planning maintenance actions and fund allocation. This study aims at developing a deep-learning model to predict the deterioration of concrete bridge decks.
Design/methodology/approach
Three long short-term memory (LSTM) models are formulated to predict the condition rating of bridge decks, namely vanilla LSTM (vLSTM), stacked LSTM (sLSTM), and convolutional neural networks combined with LSTM (CNN-LSTM). The models are developed by utilising the National Bridge Inventory (NBI) datasets spanning from 2001 to 2019 to predict the deck condition ratings in 2021.
Findings
Results reveal that all three models have accuracies of 90% and above, with mean squared errors (MSE) between 0.81 and 0.103. Moreover, CNN-LSTM has the best performance, achieving an accuracy of 93%, coefficient of correlation of 0.91, R2 value of 0.83, and MSE of 0.081.
Research limitations/implications
The study used the NBI bridge inventory databases to develop the bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.
Originality/value
This study provides a detailed and extensive data cleansing process to address the shortcomings in the NBI database. This research presents a framework for implementing artificial intelligence-based models to enhance maintenance planning and a guideline for utilising the NBI or other bridge inventory databases to develop accurate bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.
Keywords
Acknowledgements
The authors would like to thank the Office of Vice Chancellor for Research and Graduate Studies at the University of Sharjah for supporting this research study under project number: 23020401266.
Citation
Abu Dabous, S., Ibrahim, F. and Alzghoul, A. (2024), "Modelling bridge deterioration using long short-term memory neural networks: a deep learning-based approach", Smart and Sustainable Built Environment, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/SASBE-10-2023-0295
Publisher
:Emerald Publishing Limited
Copyright © 2024, Emerald Publishing Limited