Many bridge structures, one of the most critical components in transportation infrastructure systems, exhibit signs of deteriorations and are approaching or beyond the initial design service life. Therefore, structural health inspections of these bridges are becoming critically important, especially after extreme events. To enhance the efficiency of such an inspection, in recent years, autonomous damage detection based on computer vision has become a research hotspot. This article proposes a threelevel image-based approach for post-disaster inspection of the reinforced concrete bridge using deep learning with novel training strategies. The convolutional neural network for image classification, object detection, and semantic segmentation are, respectively, proposed to conduct system-level failure classification, component-level bridge column detection, and local damage-level damage localization. To enable efficient training and prediction using a small data set, the model robustness is a crucial aspect to be taken into account, generally through its hyperparameters' selection. This article, based on Bayesian optimization, proposes a principled manner of such selection, with which very promising results (well over 90% accuracies) and robustness are observed on all three-level deep learning models. Comput Aided Civ Inf. 2019;34:415-430. wileyonlinelibrary.com/journal/mice 415 How to cite this article: Liang X. Image-based post-disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization. Comput Aided Civ Inf. 2019;34:415-430.

Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In this work, we propose a generic method for self-supervised domain adaptation, using object recognition and semantic segmentation of urban scenes as use cases. Focusing on simple pretext/auxiliary tasks (e.g. image rotation prediction), we assess different learning strategies to improve domain adaptation effectiveness by self-supervision. Additionally, we propose two complementary strategies to further boost the domain adaptation accuracy within our method, consisting of prediction layer alignment and batch normalization calibration. For the experimental work, we focus on the relevant setting of training models using synthetic images, and adapting them to perform on real-world images. The obtained results show adaptation levels comparable to most studied domain adaptation methods, thus, bringing self-supervision as a new alternative for reaching domain adaptation. The code is available at https://github.com/Jiaolong/self-supervised-da.

Toward reduced recovery time after extreme events, near real‐time damage diagnosis of structures is critical to provide reliable information. For this task, a fully convolutional encoder–decoder neural network is developed, which considers the spatial correlation of sensors in the automatic feature extraction process through a grid environment. A cost‐sensitive score function is designed to include the consequences of misclassification in the framework while considering the ground motion uncertainty in training. A 10‐story‐10‐bay reinforced concrete (RC) moment frame is modeled to present the design process of the deep learning architecture. The proposed models achieve global testing accuracies of 96.3% to locate damage and 93.2% to classify 16 damage mechanisms. Moreover, to handle class imbalance, three strategies are investigated enabling an increase of 16.2% regarding the mean damage class accuracy. To evaluate the generalization capacities of the framework, the classifiers are tested on 1,080 different RC frames by varying model properties. With less than a 2% reduction in global accuracy, the data‐driven model is shown to be reliable for the damage diagnosis of different frames. Given the robustness and capabilities of the grid environment, the proposed framework is applicable to different domains of structural health monitoring research and practice to obtain reliable information.

Computer vision leveraging deep learning has achieved significant success in the last decade. Despite the promising performance of the existing deep vision inspection models, the extent of models’ reliability remains unknown. Structural health monitoring (SHM) is a crucial task for the safety and sustainability of structures, and thus, prediction mistakes can have fatal outcomes. In this paper, we use Bayesian inference for deep vision SHM models where uncertainty can be quantified using the Monte Carlo dropout sampling. Three independent case studies for cracks, local damage identification, and bridge component detection are investigated using Bayesian inference. Aside from better prediction results, the two uncertainty metrics, variations in softmax probability and entropy, are shown to have good correlations with misclassifications. However, modifying the decision or triggering human intervention can be challenging based on raw uncertainty outputs. Therefore, the concept of surrogate models is proposed to develop the models for uncertainty‐assisted segmentation and prediction quality tagging. The former refines the segmentation mask and the latter is used to trigger human interventions. The proposed framework can be applied to future deep vision SHM frameworks to incorporate model uncertainty in the inspection processes.

No abstract