Journal of Infrastructure Intelligence and Resilience最新文献

Exterior wall inspections are critical to ensuring public safety around aging buildings in urban cities. Conventional manual approaches are dangerous, time-consuming and labor-intensive. AI-enabled drone platforms have recently become popular and provide an alternative to serving automated and intelligent inspections. However, current identification only investigates RGB image of visual defects or thermal images of thermal anomalies without considering the continuous monitoring and the conversion between multiple defects. To gain new insights with modality-specific information, this research therefore compares the performance of early, intermediate, and late multimodal RGB-Thermal images fusion techniques for multi-defect detection in facades, especially for detached tiles and missing tiles. Numerous RGB and thermals images from an ageing campus building were collected as a dataset and the classical UNet for image segmentation was modified as a benchmark. The comparative results regarding accuracy (mAP, ROC, and AUC) proved that early fusion model performed well in distinguishing detached tiles and missing tiles from complex and congested facades. Nevertheless, intermediate and late fusion models were proven to be more efficient and effective with an optimal architecture, achieving high mean average accuracy with much less parameters. In addition, the results also showed that multi-modal fusion techniques can significantly improve the performance of multi-defects detection without adding a large number of parameters to single-modal AI models.

The attention given to magnetorheological elastomers (MREs) has been on the rise over the last few decades. MREs feature a remarkable field-controllable modulus or mechanical characteristics that are influenced by an external magnetic field. Compared to its family member magnetorheological fluids (MRF), MREs offer advantages in terms of overcoming sealing and sedimentation issues. This makes them highly promising for the development of smart base isolation systems of buildings and other infrastructures. This review paper attempts to highlight the impactful progress of MRE base isolation in civil engineering over the past decades. It begins with a brief introduction of MREs including its fundamental principles, operation modes, and fabrication process. Then, the recent investigations of MREs and MRE base isolators are reviewed. Finally, discussions are made on the challenges and potential topics for further investigations.

Accurate prediction of roadbed settlement is of great significance to the maintenance of high-speed railway roadbeds and the safe operation of trains. This study proposes a long- and short-term parallel combined prediction (LS-PCP) model based on the prediction characteristics of the LSTM model, GM(1.1) model, and ESP model and applies it to the prediction of roadbed settlement of high-speed railways. First, according to the spatiotemporal characteristics, slow-varying characteristics, and short valid data characteristics of the settlement process of a high-speed railway roadbed, this study designed a combined form of long-term LSTM prediction and short-term GM(1.1) and ESP sliding prediction to overcome the problem of large prediction errors when roadbed settlement enters different stages. Next, the mutual inclusiveness of the member models’ prediction results is tested by the principle of inclusiveness test, and the combination weights are determined by considering the information entropy of the member models through the entropy weighting method. Finally, the combined prediction results of the proposed LS-PCP model are verified from the actual monitoring data of a high-speed railway in Hebei Province and the Guiguang High-speed Railway. The results prove that the proposed LS-PCP combined model has higher prediction accuracy, and the prediction data of this model have important reference significance for the maintenance of high-speed railway roadbeds and safe vehicle operation.

Bridge decks tend to degrade faster than other bridge components due to environment exposure and vehicular loading. Periodic degradation monitoring is needed for timely rehabilitation measures and development of service life models in bridge decks. Surface degradation are identified through visual inspection (VI) and post-processing of high-definition imagery. Although VI is the primary NDE method employed by most transportation authorities, many anomalies (e.g., cracking, corrosion, and delamination) remain hidden under the surface until deteriorations have grown large enough to surface (e.g., spalling). Subsurface degradation is best identified through other forms of non-destructive evaluation (NDE). Inferences can be made between the various NDE methods, as the mechanisms behind the damages sensed by each method are shared. For instance, condition map from an NDE method may infer future visible deterioration, as well as condition maps for other NDE methods. In this paper, a deep learning approach based in a conditional generative adversarial network is presented for modeling of plausible visible deterioration and NDE condition maps. Two applications are explored: (i) visualization of plausible future deterioration based on current NDE condition map, and (ii) visualization of condition maps for NDE methods from other NDE methods. Field and experimental data from the BEAST facility at Rutgers University are used to develop the training databases for each application.

The present study investigates the performance of supplemental inerter and spring with on-off effects (ISWOE) in the mitigation of the seismic response of base-isolated structures. Firstly, the response of the rigid base-isolated structure with ISWOE is investigated to see the response control effects of ISWOE under stationary earthquake excitation. The performance of ISWOE in the response reduction of the isolated structure is compared with the corresponding passive inerter and spring. The equivalent damping that was added to the base-isolated structures by the ISWOE was used to measure its performance in mitigating the seismic response. The equivalent damping of the ISWOE is obtained for different values of the isolation period and damping ratio. Subsequently, equations for the equivalent damping of the ISWOE and displacement responses are proposed, and it is observed that they match well with the obtained numerical results. Secondly, using the non-linear model of the ISWOE, the seismic response of flexible base-isolated structures is determined for actual earthquakes, considering different values of the isolation period and ISWOE parameters. The trends of the results of isolated structures with ISWOE under the actual earthquake motions were in good agreement with those under stochastic excitation. Finally, the seismic response of isolated structures with ISWOE by non-linear analysis is compared with the corresponding linear analysis with equivalent parameters of the ISWOE. The isolator displacement of the structures with the ISWOE by the non-linear analysis was observed to match those achieved using the equivalent parameters and by the linear analysis.

Pipelines subject to ground deformations generated by geohazard loads carry high importance on pipeline analysis, design, and assessment due to risk of structural damage or failure. Additionally, internal pressure and temperature variation within an operating pipe induce additional strains in combination with pipe strains generated by ground displacement. In this study, an enhanced predictive method is proposed founded upon methods employed by Zheng et al. (2022) to assess pipeline behaviour subject to permanent ground displacement, while considering effects of internal operating pressure and temperature variation. The finite difference-based method previously proposed for strain analysis of buried steel pipes subject to ground movement ignores the effects of internal pressure and/or temperature loading, limiting the applicability of this approach to exclude the operating conditions of pipelines. To address this limitation, the proposed enhanced method accounts for the initial thermal strains and biaxial stress state in the pipe due to hoop stress generated by internal pressure. These additional strains are considered within the expressions of internal axial force and bending moment, derived based on the actual stress distribution on the pipe cross-section. The accuracy of the proposed method is validated against the finite element method (FEM) with respect to results of strain and deformation demand using several indicative case studies. This research provides an effective method of incorporating temperature and internal pressure loads of pipelines subject to permanent ground displacements of varying types, magnitudes, and directions.

This study assessed the rheological performance of asphalt binder modified with palm oil clinker fine (POCF) and its influence on the asphalt binder's short-term aging properties. The conventional properties of unaged and short-term aged asphalt binders modified with 0%, 2%, 4%, 6%, and 8% POCF content by binder weight were evaluated. The modified binders were then tested using a dynamic shear rheometer (DSR) in a temperature sweep test at temperatures ranging from 25 ​°C to 55 ​°C. To examine the effect of various POCF contents and temperature ranges on the rheological behavior of asphalt binders, the Central Composite Design (CCD) Response Surface Methodology (RSM) design was used with two input response variables, POCF content and temperature, and two rheological parameters as responses, complex modulus, and phase angle. When compared to the virgin binder, POCF-modified binders had higher complex modulus and lower phase angle values at all temperatures. Furthermore, the stiffness of the aged-modified binder was lower at all temperatures than that of the virgin binder. The analysis shows that complex modulus and phase angle have high correlation coefficients (R²) of <0.98, indicating that the model values are strongly correlated with the experimenttal values. The model also demonstrates that temperature has more influence on the rheological performance of the modified binder. Using the generated quadratic model and numerical optimization, optimal values for POCF and temperature were found to be 5.57% and 41.9 ​°C, respectively. The validation test results show that all responses have a percentage error of <5%, indicating good agreement and the model's effectiveness.

More widespread use of industrialized construction (IC) is hampered by the high capital cost of advanced production facilities paired with low profit margins. A novel service-oriented cloud manufacturing (CMfg) model could in theory increase utilization and profitability of distributed production facilities. However, little research has investigated how IC can benefit from the CMfg model. This paper examines opportunities and challenges of applying CMfg for IC. First, an adapted model of CMfg for construction is developed based on a literature review. Second, four possible scenarios for applying this adapted CMfg model are designed. Finally, an evaluation is performed through a survey among 25 practitioners and 12 in-depth interviews with industry experts. The paper assesses the desirability and categorizes the benefits and barriers of such a CMfg platform for IC. The results suggest that CMfg could enhance the design quality, support IC suitability assessment for project developers and lower financial risks for off-site manufacturers.

One of the key challenges in fully embracing machine learning (ML) in civil and environmental engineering revolves around the need for coding (or programming) experience and for acquiring ML-related infrastructure. This barrier can be overcome through the availability of various platforms that provide automated and coding-free ML services, as well as ML infrastructure (in the form of a cloud service or software). Thus, engineers can now adopt, create, and apply ML to tackle various problems with ease and little coding. From this view, this paper presents a comparison of five automated and coding-free ML platforms: BigML, Dataiku, DataRobot, Exploratory, and RapidMiner on civil and environmental engineering problems. This comparison shows that although these platforms differ in their setup, services, and provided ML algorithms, all platforms performed adequately and comparably well to each other and to coding-based ML analyses. These findings denote the usefulness of coding-free ML platforms, which can lead to a brighter future for ML integration into our domain.