Journal of Infrastructure Intelligence and Resilience最新文献

The fracture surface of high-strength bolt after fatigue fracture contains a lot of information, such as the location of stress concentration and the distribution of fatigue cracks. In this study, a large number of scanning electron microscope (SEM) images of fatigue fracture surface of broken high-strength bolt were identified and classified using the method of deep learning. At the beginning, a data set of SEM images containing 1556 fatigue fractures of high-strength bolts was prepared. Then, three convolutional neural networks, VGG16, ResNets50 and MobileNets, were used to recognize and classify the images in the dataset. In this process, part of the convolution layer of ResNets50 was extracted for visualization. At the same time, the Loss-Epoch curves, accuracy, recall and confusion matrices of the three networks were derived to evaluate the nets. Finally, the network with the highest accuracy was selected to adjust the parameters to further improve the accuracy of the classification. It was found that the three nets can complete the classification of these images. MobileNets had the best performance for this classification task, and the accuracy rate after adjusting the parameters has reached 86.76%. For some images with obvious features, the recall rate of classification had reached 100%. However, images from the same fatigue area were prone to a small amount of confusion. Finally, the feature map of the network would become more abstract with the deepening of the network, and the features of the image concerned by each convolution layer were also different.

Recent advances in computer vision algorithms have transformed the bridge visual inspection process. Those algorithms typically require large amounts of annotated data, which is lacking for generic bridge inspection scenarios. To address this challenge efficiently, this research designs, develops, and demonstrates a platform that can provide synthetic datasets and testing environments, termed Random Bridge Generator (RBG). The RBG produces photo-realistic 3D synthetic environments of six types of bridges randomly, automatically, and procedurally. Following relevant standards and design practice, the RBG creates random cross-sectional shapes, converts those shapes into bridge components, and assembles the components into bridges. The effectiveness of the RBG is demonstrated by producing a dataset (RBG Dataset) containing 10,753 images with pixel-wise annotations, rendered in 250 different synthetic environments. Significant diversity of the photo-realistic bridge inspection environments has been achieved, while all structural components strictly conform to the definitions derived from structural engineering documents. The use of the RBG dataset has been demonstrated by training a deep semantic segmentation algorithm with 101 convolutional layers, showing successful segmentation results for both major and minor structural components. The developed RBG is expected to enhance the level of automation in bridge visual inspection process. The Python code for RBG is made public at: https://github.com/chenghaojia2323/Random-Bridge-Generator.git.

Selecting an efficient structural system during the conceptual design of bridge projects is an essential requirement for the project’s success and fulfilling stakeholders’ expectations. This process involves evaluating a broad range of objective and subjective requirements based on multiple technical criteria. Despite its importance, current literature lacks a structured methodology for assisting designers in the selection process of the bridge structural system. Therefore, this research aims to develop a selection model to facilitate the decision-making process, helping evaluate different bridge structural systems during the conceptual design phase. The primary goal is to choose the most optimal design that aligns with both the client’s needs and technical specifications. The proposed methodology begins by identifying client needs and finding their relative importance using an Analytic Hierarchy Process (AHP) questionnaire, followed by determining the technical requirements in bridge conceptual design. A Quality Function Deployment (QFD) model is developed to evaluate bridge structural systems. The main advantage of integrating QFD and AHP is that it reduces the inconsistency and uncertainty in the QFD inputs. The methodology is implemented in a real case study of a bridge project in the United Arab Emirates (UAE), demonstrating improved results in structural system selection compared to traditional methods. While this research focused on the conceptual design phase of bridge projects, future work could extend to other phases of design.

Under loading and environmental actions, infrastructures undergo continuous aging and deterioration of the constituent materials during their service lifespan. In-situ monitoring the aging and deterioration at material level of infrastructures can provide effective protection and maintenance prior to serious failure, thus enhancing their safety and lifespan as well as resilience. Therefore, self-sensing performance of materials is an important paradigm for updating infrastructures with intelligent digital insights. Concrete, the most widely used engineering material for infrastructure construction, inherently lacks self-sensing property. The incorporation of functional fillers can form a conductive sensory “neural” system inside concrete, thus empowering concrete with the capability to sense stress (or force), strain (or deformation), and damage (e.g., cracking, fatigue) in itself, and also improving (or maintaining) its mechanical properties and durability. The emergence of intrinsic self-sensing concrete has laid a material foundation for realizing in-situ monitoring, contributing to the development of intelligent and resilient infrastructures. This review concisely introduces the significant research progress of research on the composition and preparation, measurement and characterization, performance and control, mechanism and model, and application of intrinsic self-sensing concrete in civil and transportation infrastructures, as well as current challenges and roadmap for its future development.

Deep learning-based object detection methods are utilized for safety management at construction sites, which require large-scale, high-quality, and well-labeled datasets for training. The existing construction datasets are relatively small due to the high expense of labor-intensive annotation, and the varying quality of the construction images also affects the detection performance of the model. To address the limitations of datasets, this study proposes a new method for construction object detection by integrating super-resolution and semi-supervised learning. The proposed method improves the quality of construction images and achieves excellent detection performance with limited labeled data. First, the Real-ESRGAN model is introduced to improve the quality of construction images and make the construction objects visible. The proposed super-resolution method can enhance the texture details of low-resolution images, hence improving the performance of object detection models. Second, the mean-teacher network is adopted to expand the training set, thus avoiding the labor-intensive annotation work. To verify the effectiveness of the proposed method, the method is applied to the state-of-the-art Yolov5 object detection model, and construction images from the Site Object Detection Dataset (SODA) with different labeled data proportions (from 10% to 50% in 10% intervals with an extreme case of 5%) are used as the training set. By comparing with the existing supervised learning method, it is shown that the proposed method can achieve better detection performance. In particular, the method is more effective in enhancing detection performance when the proportion of the labeled data is smaller, which is of great practical value in real-world engineering. The experimental results show the potential of the proposed method in improving image quality and reducing the expense of developing construction datasets.

Structural health monitoring (SHM) systems generate a large amount of sensing data. Data anomalies may occur due to sensor faults and extreme events. Sensor faults can result in low-fidelity measurement data, while data associated with extreme events are crucial for assessing the structural safety condition and should be given special attention. Accurate detection and classification of anomalies can improve the performance of SHM systems. However, most existing classification methods work well only when the number of a-single-class anomalies is sufficient. This study proposes an automatic few-shot classification method for sensor anomalies with limited labeled samples. The most discriminatory shapelet, a new representation of abnormal data, is learned from the standard normal class by maximizing the overall distance, which can locate the prominent abnormal features from 1-h acceleration data. The classification is then learned based on manual feature extraction and deep-learning-based feature extraction by measuring the similarity between the most discriminatory shapelets from the query and support sets. The proposed few-shot classification method is applied to datasets collected from two SHM systems of a long-span bridge and a campus footbridge. Results demonstrate that the proposed method can classify new anomalies with limited samples that differ from the defined anomalies.

This paper presents an approach for structural damage quantification using a long short-term memory (LSTM) auto-encoder and impulse response functions (IRF). Among time domain responses-based methods for structural damage identification, using IRF is advantageous over the original time domain responses, since IRF consists of information of system properties and is loading effect independent. In this study, IRFs are extracted from the acceleration responses measured from different locations of structures under impact force excitations. The obtained IRFs are concatenated. Moving averaging with a suitable window size is performed to reduce random variations in the concatenated responses. Further, principal component analysis is performed for dimensionality reduction. These selected principal components are then fed to the LSTM auto-encoder for structural damage identification. A noise layer is added as an input layer to the LSTM auto-encoder to regularise the model. The proposed model consists of two phases: (1) reconstruction of the selected “principal components” to extract the features; and (2) damage identification of structural elements. Numerical studies are conducted to verify the accuracy of the proposed approach. The results demonstrate that the proposed approach can accurately identify and quantify structural damage for both single- and multiple-element damage cases with noisy measurements, as well as uncertainties in the stiffness parameters. Furthermore, the performance of the proposed approach is evaluated using the limited measurements from a few sensors.

With increasing availability of cost-effective and high-resolution cameras, their use as a non-contact sensing tool has rapidly progressed for structural health monitoring. The cameras offer unique capabilities to provide full-field measurement with high spatial density at low cost. However, extracting high-density temporal data is challenging, as a high-speed camera increases the monitoring cost with high-rate data processing. Recently, motion magnification (MM) has shown significant success in analyzing low-amplitude motion of structural systems. However, previous studies observed that MM methodology performs poorly at low frame rates for modal identifications. In this paper, the influence of low frame rate on phased-based motion magnification (PMM) has been investigated. A novel technique is proposed by combining PMM with zero mean-normalization cross-correlation tracker to determine vibrational responses, and then the spatial Wigner-Ville spectrum-based time-frequency blind source separation method is explored for modal identification using the extracted vibrational responses obtained from the video data. The experimental data of a lumped mass experimental model and a steel bridge is used to test the accuracy of the proposed method. The original and motion-magnified image response data is compared with accelerometer data for modal identification. The proposed method is able to extract the modal parameters with high accuracy for motion-magnified images, even for low frame rates.

Telecommunication infrastructure (TI) is becoming increasingly vital in modern society, where information exchange is needed in almost all aspects of the built environment, business operations, and people's daily lives. The ongoing 5G rollout will lead to a paradigm shift in regional TI deployment landscape, with increased seismic hazard exposure particularly due to the densely deployed small cells. As TI is known to be vulnerable to seismic hazard impacts yet necessary for post-earthquake emergency response, this study carries out a pioneering effort in quantifying the post-earthquake TI failures and functionality to better support risk mitigation decision-making. We propose a novel seismic risk assessment framework for regional 5G TI, by holistically integrating regional seismic hazard analysis, infrastructure seismic exposure data, electric power infrastructure seismic fragility modeling and network connectivity analysis, as well as wireless TI functionality modeling. The proposed framework is evaluated based on a hypothetical regional infrastructure testbed located in Memphis, Tennessee, subjected to several earthquake scenarios. From a reference heterogeneous 5G TI deployment scenario, the results indicate that significant performance degradation of 5G TI is expected especially after major earthquake events. Enabled by the proposed framework, we further compared the efficacy of several risk mitigation strategies and pertinent implications are provided.