Computer-Aided Civil and Infrastructure Engineering

A number of image processing techniques (IPTs) have been implemented for detecting civil infrastructure defects to partially replace human‐conducted onsite inspections. These IPTs are primarily used to manipulate images to extract defect features, such as cracks in concrete and steel surfaces. However, the extensively varying real‐world situations (e.g., lighting and shadow changes) can lead to challenges to the wide adoption of IPTs. To overcome these challenges, this article proposes a vision‐based method using a deep architecture of convolutional neural networks (CNNs) for detecting concrete cracks without calculating the defect features. As CNNs are capable of learning image features automatically, the proposed method works without the conjugation of IPTs for extracting features. The designed CNN is trained on 40 K images of 256 × 256 pixel resolutions and, consequently, records with about 98% accuracy. The trained CNN is combined with a sliding window technique to scan any image size larger than 256 × 256 pixel resolutions. The robustness and adaptability of the proposed approach are tested on 55 images of 5,888 × 3,584 pixel resolutions taken from a different structure which is not used for training and validation processes under various conditions (e.g., strong light spot, shadows, and very thin cracks). Comparative studies are conducted to examine the performance of the proposed CNN using traditional Canny and Sobel edge detection methods. The results show that the proposed method shows quite better performances and can indeed find concrete cracks in realistic situations.

Computer vision‐based techniques were developed to overcome the limitations of visual inspection by trained human resources and to detect structural damage in images remotely, but most methods detect only specific types of damage, such as concrete or steel cracks. To provide quasi real‐time simultaneous detection of multiple types of damages, a Faster Region‐based Convolutional Neural Network (Faster R‐CNN)‐based structural visual inspection method is proposed. To realize this, a database including 2,366 images (with 500 × 375 pixels) labeled for five types of damages—concrete crack, steel corrosion with two levels (medium and high), bolt corrosion, and steel delamination—is developed. Then, the architecture of the Faster R‐CNN is modified, trained, validated, and tested using this database. Results show 90.6%, 83.4%, 82.1%, 98.1%, and 84.7% average precision (AP) ratings for the five damage types, respectively, with a mean AP of 87.8%. The robustness of the trained Faster R‐CNN is evaluated and demonstrated using 11 new 6,000 × 4,000‐pixel images taken of different structures. Its performance is also compared to that of the traditional CNN‐based method. Considering that the proposed method provides a remarkably fast test speed (0.03 seconds per image with 500 × 375 resolution), a framework for quasi real‐time damage detection on video using the trained networks is developed.

A multicriteria model is developed for analyzing the planning strategies for reducing the future social and economic costs in the area with potential natural hazard. The developed multicriteria decision‐making procedure consists of generating alternatives, establishing criteria, assessment of criteria weights, and application of the compromise ranking method (VIKOR). The alternatives are the scenarios of sustainable hazard effects mitigation, generated in the form of comprehensive reconstruction plans, including the redevelopment of urban areas and infrastructures, multipurpose land use, and restrictions on building in hazardous areas. The plans have to be evaluated according to the criteria representing public safety, sustainability, social environment, natural environment, economy, culture, and politics. The multicriteria model can treat all relevant conflicting effects and impacts in their representative units. The evaluation of alternatives is implicated with imprecision (or uncertainty) of established criteria, and the fuzzy multicriteria model is developed to deal with “qualitative” (unquantifiable or linguistic) or incomplete information. The application of this model is illustrated with the post‐earthquake reconstruction problem in Central Taiwan, including the restoration concerning the safe and serviceable operation of “lifeline” systems, such as electricity, water, and transportation networks, immediately after a severe earthquake.

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 three‐level 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.

Abstract:  The time‐frequency character of wavelet transforms allows adaptation of both traditional time and frequency domain system identification approaches to examine nonlinear and non‐stationary data. Although challenges did not surface in prior applications concerned with mechanical systems, which are characterized by higher frequency and broader‐band signals, the transition to the time‐frequency domain for the analysis of civil engineering structures highlighted the need to understand more fully various processing concerns, particularly for the popular Morlet wavelet. In particular, as these systems may possess longer period motions and thus require finer frequency resolutions, the particular impacts of end effects become increasingly apparent. This study discusses these considerations in the context of the wavelet's multi‐resolution character and includes guidelines for selection of wavelet central frequencies, highlights their role in complete modal separation, and quantifies their contributions to end‐effect errors, which may be minimized through a simple padding scheme.

Abstract:  Traditional documentation capabilities of laser scanning technology can be further exploited for urban modeling through the transformation of resulting point clouds into solid models compatible for computational analysis. This article introduces such a technique through the combination of an angle criterion and voxelization. As part of that, a k‐nearest neighbor (kNN) searching algorithm is implemented using a predefined number of kNN points combined with a maximum radius of the neighborhood, something not previously implemented. From this sample, points are categorized as boundary or interior points based on an angle criterion. Façade features are determined based on underlying vertical and horizontal grid voxels of the feature boundaries by a grid clustering technique. The complete building model involving all full voxels is generated by employing the Flying Voxel method to relabel voxels that are inside openings or outside the façade as empty voxels. Experimental results on three different buildings, using four distinct sampling densities showed successful detection of all openings, reconstruction of all building façades, and automatic filling of all improper holes. The maximum nodal displacement divergence was 1.6% compared to manually generated meshes from measured drawings. This fully automated approach rivals processing times of other techniques with the distinct advantage of extracting more boundary points, especially in less dense data sets (<175 points/m²), which may enable its more rapid exploitation of aerial laser scanning data and ultimately preclude needing a priori knowledge.

Wavelet neural network (WNN) has been widely used in the field of civil engineering. However, WNN can only effectively handle problems of small dimensions as the computational cost for constructing wavelets of large dimensions is prohibitive. To expand the application of WNN to higher dimensions, this article develops a new wavelet support vector machine (SVM)‐based neural network metamodel for reliability analysis. The method first develops an autocorrelation wavelet kernel SVM and then uses a set of wavelet SVMs with different resolution as the activation function of WNN. The output of network is obtained through aggregating outputs of different wavelet SVMs. The method takes advantage of the excellent capacities of SVM to handle high‐dimensional problems and of the attractive properties of wavelet to represent complex functions. Four examples are given to demonstrate the application and effectiveness of the proposed method.