In the past few years, intelligent structural damage identification algorithms based on machine learning techniques have been developed and obtained considerable attentions worldwide, due to the advantages of reliable analysis and high efficiency. However, the performances of existing machine learning–based damage identification methods are heavily dependent on the selected signatures from raw signals. This will cause the fact that the damage identification method, which is the optimal solution for a specific application, may fail to provide the similar performance on other cases. Besides, the feature extraction is a time-consuming task, which may affect the real-time performance in practical applications. To address these problems, this article proposes a novel method based on deep convolutional neural networks to identify and localise damages of building structures equipped with smart control devices. The proposed deep convolutional neural network is capable of automatically extracting high-level features from raw signals or low-level features and optimally selecting the combination of extracted features via a multi-layer fusion to satisfy any damage identification objective. To evaluate the performance of the proposed deep convolutional neural network method, a five-level benchmark building equipped with adaptive smart isolators subjected to the seismic loading is investigated. The result shows that the proposed method has outstanding generalisation capacity and higher identification accuracy than other commonly used machine learning methods. Accordingly, it is deemed as an ideal and effective method for damage identification of smart structures.

With the rapid increase of ageing infrastructures worldwide, effective and robust inspection techniques are highly demanding to evaluate structural conditions and residual lifetime. The damages on structural surfaces, for example, spalling, crack, rebar buckling and exposure, are important indicators to assess the structural condition. In fact, several state-of-the-art automated inspection techniques using these indicators have been developed to reduce human-conducted onsite inspection activities. However, the efficiency of these techniques is still required to be improved in terms of accuracy and computational cost. In this study, a vision-based crack diagnosis method is developed using deep convolutional neural network (DCNN) and enhanced chicken swarm algorithm (ECSA). A DCNN model is designed with a deep architecture, consisting of six convolutional layers, two pooling layers and three fully connected layers. To enhance the generalisation capacity of trained model, ECSA is introduced to optimize meta-parameters of the DCNN model. The model is trained and tested using image patches cropped from raw images obtained from damaged concrete samples. Finally, a comparative study on different crack detection techniques is conducted to evaluate performance of the proposed method via a group of statistical evaluation indicators.

In the current modern era of information and technology, emerging remote advancements have been widely established for detailed virtual inspections and assessments of infrastructure assets, especially bridges. These technologies are capable of creating an accurate digital representation of the existing assets, commonly known as the digital twins. Digital twins are suitable alternatives to in-person and on-site based assessments that can provide safer, cheaper, more reliable, and less distributive bridge inspections. In the case of bridge monitoring, Unmanned Aerial Vehicle (UAV) photogrammetry and Terrestrial Laser Scanning (TLS) are among the most common advanced technologies that hold the potential to provide qualitative digital models; however, the research is still lacking a reliable methodology to evaluate the generated point clouds in terms of quality and geometric accuracy for a bridge size case study. Therefore, this paper aims to provide a comprehensive methodology along with a thorough bridge case study to evaluate two digital point clouds developed from an existing Australian heritage bridge via both UAV-based photogrammetry and TLS. In this regard, a range of proposed approaches were employed to compare point clouds in terms of points’ distribution, level of outlier noise, data completeness, surface deviation, and geometric accuracy. The comparative results of this case study not only proved the capability and applicability of the proposed methodology and approaches in evaluating these two voluminous point clouds, but they also exhibited a higher level of point density and more acceptable agreements with as-is measurements in TLS-based point clouds subjected to the implementation of a precise data capture and a 3D reconstruction model.

Due to the limitation of sample size in predicting the torsional strength of Reinforced Concrete (RC) beams, this paper aims to discuss the feasibility of employing a novel machine learning approach with K-fold cross-validation in a small sample range, which combines the advantages of a Genetic Algorithm (GA) and a Neural Network (NN) to predict the torsional strength of RC beams. This research study not only utilizes the application of a Back Propagation (BP) neural network and the Gene Algorithm-Back Propagation (GA-BP) neural network in the prediction of the torsional strength of the RC beam, but it also investigates neural network parameter optimization, including connection weights and thresholds, using K-fold cross-validation. The root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE) and correlation coefficient (R²) are among the evaluation metrics used to assess the performance of the trained model. To elaborate on the superiority of the proposed network models in predicting the torsional strength of RC beams, a parametric study is conducted by comparing the proposed model to three commonly used empirical formulae from existing design codes. The comparative findings of this research study demonstrate that the performance of the BP neural network is highly similar to that of design codes; however, its accuracy is inadequate. After improving the weights and thresholds by k-fold cross-validation and GA, the prediction of the BP neural network shows higher consistency with the actual measured values. The outcome of this study can be used as a theoretical reference for the optimal design of RC beams in practical applications.