Search

This study develops a structural stability monitoring method for an implant structure (i.e., a single-tooth dental implant) through deep learning of local vibrational modes. Firstly, the local vibrations of the implant structure are identified from the conductance spectrum, achieved by driving the structure using a piezoelectric transducer within a pre-defined high-frequency band. Secondly, deep learning models based on a convolutional neural network (CNN) are designed to process the obtained conductance data of local vibrational modes. Thirdly, the CNN models are trained to autonomously extract optimal vibration features for structural stability assessment of the implant structure. We employ a validated predictive 3D numerical modeling approach to demonstrate the feasibility of the proposed approach. The proposed method achieved promising results for predicting material loss surrounding the implant, with the best CNN model demonstrating training and testing errors of 3.7% and 4.0%, respectively. The implementation of deep learning allows optimal feature extraction in a lower frequency band, facilitating the use of low-cost active sensing devices. This research introduces a novel approach for assessing the implant's stability, offering promise for developing future radiation-free stability assessment tools. [ABSTRACT FROM AUTHOR]

Concrete dam deformation prediction plays a crucial role in ensuring dam safety monitoring. Machine learning, especially recurrent neural networks, plays an important role in this, yet its predictive accuracy is not high. This paper first preprocesses time series data using successive variational mode decomposition (SVMD). Then, it combines residual network (ResNet) and gate recurrent unit (GRU), fully leveraging the excellent information extraction capability of the former and the powerful sequential data processing capability of the latter, proposing the ResNet‐GRU model for deformation prediction analysis. During the prediction process, the sanitized gray wolf optimizer (SGWO) algorithm adjusts the parameters, further enhancing the prediction accuracy and performance of the model. The model has also been successfully applied in practical cases, validating its effectiveness. The results indicate that the ResNet‐GRU‐SGWO model can accurately simulate the dynamic deformation process of concrete dams. Compared with various intelligent prediction models, it achieves the highest prediction accuracy and outstanding performance, providing a reference for the prediction of concrete dam deformation. [ABSTRACT FROM AUTHOR]

This study proposes a data‐driven method for predicting the probabilistic response of cable‐stayed bridges. The proposed method is used to construct an optimal prediction model based on a data‐driven machine‐learning method. In addition, the accuracy and efficiency of the prediction model are improved by considering the correlation coefficients between the input sensor data and the output of the target response. The proposed method is comprised of two steps: the selection of meaningful features and the construction of a probabilistic prediction model employing Gaussian process regression. The proposed method is applied to an in‐service cable‐stayed bridge in the Republic of Korea using actual measurement data from various sensors. For comparison purposes, two parametric studies are performed, and the effects of the proposed feature‐selection procedure are investigated based on the normalized correlation coefficients. Consequently, the proposed feature‐selection method is proven to increase the accuracy and efficiency of the prediction. [ABSTRACT FROM AUTHOR]

Structural damage in the steel bridge anchorage, if not diagnosed early, could pose a severe risk of structural collapse. Previous studies have mainly focused on diagnosing prestress loss as a specific type of damage. This study is among the first for the automated identification of multiple types of anchorage damage, including strand damage and bearing plate damage, using deep learning combined with the EMA (electromechanical admittance) technique. The proposed approach employs the 1D CNN (one-dimensional convolutional neural network) algorithm to autonomously learn optimal features from the raw EMA data without complex transformations. The proposed approach is validated using the raw EMA response of a steel bridge anchorage specimen, which contains substantial nonlinearities in damage characteristics. A K-fold cross-validation approach is used to secure a rigorous performance evaluation and generalization across different scenarios. The method demonstrates superior performance compared to established 1D CNN models in assessing multiple damage types in the anchorage specimen, offering a potential alternative paradigm for data-driven damage identification in steel bridge anchorages. [ABSTRACT FROM AUTHOR]

A 1-dimensional convolutional neural network (1D CNN) model is developed to process deep learning of raw impedance signals for smart aggregate (SA)-based concrete stress monitoring. First, the framework of the SA-based stress monitoring using deep learning of raw impedance signals is described. An impedance measurement model is designed for a SA-embedded concrete body under compression. A 1D CNN model is developed for deep learning of raw impedance signals corresponding to various stress levels. Three approaches for concrete stress monitoring are designed to deal with data availability, signal noises, and untrained stress levels. Second, a few SA-embedded concrete cylinders are experimented to measure impedance signals under various stress levels. Finally, the performance of the proposed method is extensively evaluated by investigating the feasibility of the K-fold cross-validation to deal with the data availability and the effects of signal noises and untrained data on the accuracy of stress estimation in the SA-embedded concrete cylinders. [ABSTRACT FROM AUTHOR]