Journal of Infrastructure Intelligence and Resilience最新文献

Bridge condition rating is a challenging task as it largely depends on the experience-level of the manual inspection and therefore is prone to human errors. The inspection report often consists of a collection of images and sequences of sentences (text) explaining the condition of the considered bridge. In a routine manual bridge inspection, an inspector collects a set of images and textual descriptions of bridge components and assigns an overall condition rating (ranging between 0 and 9) based on the collected information. Unfortunately, this method of bridge inspection has been shown to yield inconsistent condition ratings that correlate with inspector experience. To improve the consistency among image-text inspection data and further predict the accordant condition ratings, this study first provides a collective image-text dataset, extracted from the collection of bridge inspection reports from the Virginia Department of Transportation. Using this dataset, we have developed novel deep learning-base methods for an automatic bridge condition rating prediction based on data fusion between the textual and visual data from the collected report sets.

Our proposed multi modal deep fusion approach constructs visual and textual representations for images and sentences separately using appropriate encoding functions, and then fuses representations of images and text to enhance the multi-modal prediction performance of the assigned condition ratings. Moreover, we study interpretations of the deployed deep models using saliency maps to identify parts of the image-text inputs that are essential in condition rating predictions. The findings of this study point to potential improvements by leveraging consistent image-text inspection data collection as well as leveraging the proposed deep fusion model to improve the bridge condition prediction rating from both visual and textual reports.

This scientific study aims to automatically identify potentially dangerous areas of frost heaving and surfacing of a buried oil pipeline using the geological description of soil profile. The geological description of soil profile along the proposed route of a pipeline entails the study and identification of various layers of soil to determine the soil's suitability for pipeline installation and support. Enriching the geological description of soils in the first stage was achieved by creating a family of parameters that characterize the presence of water in two states and the interaction of the buried oil pipeline with soil layers. In the second stage, missed and erroneous soil parameters were restored by searching for similar patterns along the route of the pipeline using the enriched geological description of soil profile. Afterward, the selected areas of frost heaving and surfacing were ranked by potential danger in the third stage. The algorithm developed was shown to reduce the risk of damage to the oil pipeline and enrich the geological description of soil profile without additional field works. The results of the study allowed for the allocation of potentially dangerous areas where frost heaving and surfacing occur. The methodology described in the study can be applied in the midstream segment of the oil and gas industry to minimize the risk of pipeline damage.

It is important to assess, monitor, and control civil infrastructure displacements, and extensive work has been done to develop structural displacement sensing techniques. This paper presents a comprehensive review of structural displacement sensing techniques, with particular focus on those for civil infrastructures. The working principles of structural displacement sensing techniques using thirteen different sensors are first reviewed, and the advantages and disadvantages of each sensor are briefly discussed. The disadvantages of single-mode sensor-based structural displacement estimation have been partially addressed by the use of multi-mode sensors. Thus, the studies on multi-mode sensor-based structural displacement estimation are reviewed. After that, field applications of these techniques to building structures, bridge structures, and other structures are briefly reviewed. The remaining challenges for the real application of these techniques are summarized, and future research directions are provided.

Data acquisition systems, such as Wireless Smart Sensor Networks (WSSNs) can increase the resilience of infrastructure by providing real-time monitoring and data collection of environmental parameters. Yet, sustainable energy supplies for sensor networks established in remote and inaccessible areas still present a challenge. Previously, researchers have attempted to address this difficulty by proposing different energy systems including solar energy harvesting, however, significant prolonged experimental data for the operation of extensive networks powered by solar energy has not been reported. This paper presents an original design and implementation of an energy system for a large WSSN and provides the sensors' power status data over a significant duration. A network of low-cost flood monitoring sensors, including twenty-six water level sensors, twenty rain gauges, and eight communication nodes were deployed and tested on summer and fall 2022 at six remote locations at the northern New Mexico Pueblo, Ohkay Owingeh. A thermometer and a humidity sensor were added to each communication node to record temperature and air's moisture level. In addition, a networked voltage monitoring system was deployed to observe the sensors energy status in real-time. The items of the WSSN are composed of two differing energy circuits suited for their energy demands. The sensors' energy circuits contain a photovoltaic panel, a lithium-polymer battery, a control device, and a DC-to-DC converter. Whereas the communication nodes contain another photovoltaic panel, a lead-acid battery, and a solar charging controller. The findings provide a perspective on the long-term field deployment of WSSNs consisting of low-cost sensors.

This paper presents the improvement of a widely used burst capacity model for steel oil and gas pipelines that contain longitudinal external surface cracks, namely the CorLAS model, through the addition of a correction factor that is quantified by the Gaussian process regression (GPR). The correction factor is assumed to depend on four non-dimensional input features that characterize both the crack geometry and pipe material properties. A database consisting of 212 full-scale burst tests of pipe specimens that contain longitudinal surface cracks is established based on the open literature, which is employed to train the GPR model and evaluate its performance. It is shown that GPR is highly effective in improving the accuracy of the CorLAS model predictions. The improvement is further shown to have a marked effect on the time-dependent probability of burst of pipelines containing growing surface cracks through two hypothetical pipeline examples: when employing the CorLAS model, the probabilities of burst are significantly higher, exceeding those obtained using the improved CorLAS model by more than one order of magnitude.

Structural Health Monitoring (SHM) has become a paramount necessity in civil engineering for improving the operational performance of aging infrastructure. Recent monitoring techniques have utilized emerging technologies in Industry 4.0, such as the Internet of Things, Big Data analytics, cloud computing, and cybersecurity, to automate SHM methodologies. However, they have found challenges in linking these technologies and developing an autonomous, well-established digital framework for applications of SHM. Visualizing processed SHM data in a real-time digital interface generates multiple obstacles, such as witnessing delays in data transfer and resorting to offline tools for manual data processing. This paper, therefore, explores the integration of Building Information Modeling (BIM) and the Internet of Things (IoT) through an Arduino micro-processing unit for tracking and visualizing the data from the time and frequency domains. Strategies for enabling data monitoring and processing are developed while continuously acquiring structural responses. The query of data is established in a web-based database instead of storing the data in offline resources that await manual intervention. The proposed real-time SHM methodology is validated experimentally using two practical applications: a dynamically moving vehicle over a simply-supported bridge prototype and a randomly excited three-story model with real-time visualization of both time- and frequency-domain information under undamaged and damaged conditions. The proposed research develops an early-phase Digital Twin (DT) to present static and real-time dynamic data in a rich-fed BIM database.

The resilience of water main networks highly depends on the capacity for identifying and fixing structural failures in the system as fast as possible. Given the buried nature of such systems, this will be hard and costly through manual or semi-automated inspections. In this paper, a data-driven method is applied to predict the failure of water mains in the City of Kitchener. Six machine learning prediction models were developed under two scenarios: global models, which consider the three dominant material types in the network; and the homogenous model, which considers only cast-iron pipes. The water main’s condition score, length, and criticality score were the most influential factors on the pipe failure. The random forest models outperformed the other machine learning models with an accuracy of 97.3% and an F1-score of 80.4%; the homogenous modeling showed superior performance than the global one with an F1-score of 86.0%. The results showed that more than 72% of breaks could have been potentially prevented by monitoring and upgrading only 8% of the network. The superiority of the developed models lies in their ability to predict pipe failures with the least number of false alarms.

Currently, there are numerous drawbacks associated with infrastructure health monitoring and management, such as inefficiency, subpar real-time functionality, demanding data requirements, and high cost. Digital twin (DT), a hybrid of a computational simulation and an actual physical system, has been proposed to overcome these challenges and become increasingly popular for modeling civil infrastructure systems. This literature review summarized different methods to build digital twins in civil infrastructure. In addition, this review also introduced the current progress of digital twins in different infrastructure sectors, including smart cities and urban spaces, transport systems, and energy systems, along with detailed examples of their various applications. Finally, the current challenges in digital twin technologies for civil infrastructure are also highlighted.

A significant number of research papers focusing on the risk analysis of oil and gas pipelines have been published. The present study includes a bibliometric analysis and literature review, considering publications from 1982 to 2022, to provide a comprehensive overview of research contributions in the field of risk assessment for oil and gas pipelines. Various techniques, such as trend analysis, bibliographic coupling, co-occurrence analysis, network analysis, and citation analysis are used to study the published papers related to the subject topic. Based on the research's keywords, the co-occurrence analysis reveals the strong and weak connections between various topics in this domain, and as a result, future research areas can be identified.

With the rapid advance in camera sensor technology, the acquisition of high-resolution images or videos has become extremely convenient and cost-effective. Computer vision that extracts semantic knowledge directly from digital images or videos, offers a promising solution for non-contact and full-field structural vibration measurement and condition assessment. Unmanned aerial vehicles (UAVs), also known as flying robots or drones, are being actively developed to suit a wide range of applications. Taking advantage of its excellent mobility and flexibility, camera-equipped UAV systems can facilitate the use of computer vision, thus enhancing the capacity of the structural condition assessment. The current article aims to provide a concise survey of the recent progress and applications of UAV-based computer vision in the field of structural dynamics. The different aspects to be discussed include the UAV system design and algorithmic development in computer vision. The main challenges, future trends, and opportunities to advance the technology and close the gap between research and practice will also be stated.