Hybrid neural network method for damage localization in structural health monitoring.

The detection of cracks in large structures is of critical importance, as such damage can result not only in significant financial costs but also pose serious risks to public safety. Many existing methods for crack detection rely on deep learning algorithms or traditional approaches that typically use image data. In this study, however, we explore an innovative approach based on numerical data, which is characterized by greater cost efficiency and offers intriguing research implications. This study emphasizes the evaluation of hybrid RNN-CNN models in comparison to the pure CNN models previously utilized in related research. Our proposed model incorporates a single RNN layer, complemented by essential supporting layers, which contributes to a reduction in complexity and a decrease in the number of parameters. This design choice results in a more streamlined and efficient architecture. Our experimental results reveal an accuracy of 78.9%, which, while slightly lower than the performance of conventional CNN models, underscores the potential of RNN layers in crack detection tasks. Importantly, this work demonstrates that integrating additional RNN layers can effectively enhance crack detection capabilities, particularly given the significance of preserving spatial information for accurate crack segmentation. These findings open avenues for further exploration and optimization of RNN-based methods in structural damage analysis, suggesting that the strategic use of RNNs can complement CNN models to achieve robust performance in this domain.