Search

This paper first proposes a novel framework for combining deep learning approach and Synthetic Aperture Radar (SAR) technique to evaluate and predict the condition of bridge displacement. The Long short-term memory (LSTM) neural network and the Small Baseline Subsets InSAR (SBAS-InSAR) are used to predict the longitudinal deformation of the bridge. Firstly, the proposed framework based on LSTM is established to obtain the relationship between the longitudinal deformation of the bridge and the influence parameters (such as temperature, temporal baseline, and others). In particular, the residual connection (RC) module is adapted to form the residual long short-term memory (Res-LSTM) neural network to improve prediction accuracy and robustness. A case study in Nanjing is analyzed to verify the performance of the proposed framework. The extracted datasets obtained from Sentienl-1 are divided into the training, validation, and testing dataset, which can satisfy the requirements in the engineering field. The R 2 and MSE of the testing datasets utilizing the proposed model are 93.17% and 15.62. Furthermore, the results indicated that the proposed framework based on Res-LSTM could predict and warn the abnormal structural deformation, extend the lifespan of structures, and minimize structural damage due to excessive deformation. [ABSTRACT FROM AUTHOR]

Graph convolutional networks (GCNs) have been shown to be effective for hyperspectral image (HSI) classification due to their capacity to learn representations of spatial–spectral features. However, the existing GCN-based models heavily rely on predefined receptive fields to capture and aggregate neighbor information for each node, which limits the ability to adaptively selecting the most significant receptive field from graph data. To address the aforementioned problem, in this article, we propose a novel dynamic adaptive sampling GCN (DAS-GCN) algorithm that captures neighbor information through adaptive sampling to allow the receptive field to be dynamically obtained. The basic underlying idea is that the most meaningful receptive field for each target node can be adaptively discovered, and the edge adjacency weights can be adjusted simultaneously after each adaptive sampling operation. Thus, we enable the graph to be dynamically updated and refined. Specifically, the adaptive sampling operation consists of two complementary components; in the first step, the importance of different remote nodes in a large-scale neighborhood is learned, while in the second step, rich underlying spatial–spectral information is extracted from local neighbors and filtered. The proposed model has the ability to learn how to extensively exploit spectral–spatial correlations from both local and remote nodes. Moreover, the proposed DAS-GCN model has a superior ability to leverage node feature information to naturally generalize and efficiently generate node embeddings for unseen data. The experimental results with overall accuracy on four real HSI datasets, i.e., Indian Pines, Pavia university, Houston 2013, and Salinas are 95.63%, 96.40%, 94.70%, and 99.08%, respectively, which clearly demonstrate the advantages of the proposed method compared with other state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

While semisupervised methods based on graph convolutional networks (GCNs) can achieve good results in hyperspectral image (HSI) classification, their performance is limited as they rely only on spatial–spectral similarity when constructing local adjacency graphs. Moreover, relying on local adjacency graphs can limit the ability of the methods to ensure the consistency of global feature in complex hyperspectral remote sensing environments. Using the spatial–spectral information is typically not sufficient for providing a reliable similarity measurement to construct a global graph when the spectral variability is large and the spatial distance is long in intraclass pixels. To address this issue, this article presents a novel globally consistent GCN (GCGCN) for HSI classification. According to the proposed method, a local reliable initial graph is first built from inherent spatial–spectral information by considering this graph as a variable to optimize. Then, adaptive global high-order neighbors are explored to capture the underlying rich spatial contextual information by utilizing the graph topological consistent connectivity instead of the common strategy of using only the spatial–spectral similarity measurement. Finally, the adaptive global high-order graph structure and two-layer networks are combined to achieve the global feature smoothing of the same class samples and maintain high global feature consistency. The proposed GCGCN method is evaluated on three real HSI data sets to demonstrate its superiority compared to ten different classification methods. Moreover, the proposed GCGCN method achieves state-of-the-art classification results on three data sets in terms of four classification evaluation metrics, including overall accuracy (OA), kappa coefficient (KC), average accuracy (AA), and class accuracy (CA). [ABSTRACT FROM AUTHOR]

The thermal insulating performance of expanded vermiculite is closely related to expansibility. A novel method of Mg2+ modification was proposed to improve the vermiculite expansion ratio. The modification process was characterised by energy dispersive X-Ray spectroscopy, X-ray diffraction, Fourier-transform infrared spectroscopy, thermogravimetric-differential scanning calorimeter and scanning electron microscopy. Moreover, the thermal expansion experiment was performed to investigate the expansion behaviours of Raw-V and Mg–V samples at various temperatures. The result indicated that the introduction of Mg2+ could increase the vermiculite interlayer water content through hydration interaction, and the expansion ratio increased 13.7% under the heating temperature of 900 °C after modification. To explain the interaction of magnesium ion and water molecules, a molecular dynamics model was developed, and the simulation results were validated using the binding energy calculation. The results of this study can provide a new perspective and theoretical guidance for the commercial process of vermiculite expansion. [ABSTRACT FROM AUTHOR]

We present results of density functional theory (DFT) study on the mechanism of photo-organocatalytic β-functionalization of aldehydes with Michael acceptors. The plausible mechanism afforded involves three distinct steps: radical generation, radical addition, oxidative hydrogen atom transfer. The region-determining step is the radical addition step which affords α- or β-radical addition adduct through α-/β-transition states with different barrier. In the reduction step of radical addition adduct, the calculation results support our proposal that oxidative hydrogen atom transfers (HAT) from enamine to the radical addition adduct, generates a neutral intermediate and β-enaminylradical, the latter of which thereafter participates in the previous step of radical addition to form β- intermediate. Our result is in satisfactory accordance with the experimental observation. [ABSTRACT FROM AUTHOR]

[Display omitted] • A novel expanded vermiculite/xonotlite insulation composite was prepared via the hydrothermal method. • Vermiculite thermal expansion and nano xonotlite fiber synthesis were comprehensively studied. • The effect of intercalation on thermal insulating performance was systematically investigated. Natural disasters caused by global warming are threatening the survival of mankind. Reducing carbon emissions is an effective way to prevent global warming. In recent years, the construction industry is playing a dominant role in global energy consumption. Aimed to solve the problem of high energy consumption in the construction industry, a novel expanded vermiculite/xonotlite thermal insulation composite was successfully prepared via the hydrothermal method. The microstructure and thermal performance of the composite were systematically analyzed using field emission scanning electron microscopy (FESEM), energy dispersive spectroscopy (EDS), X-ray diffraction (XRD), thermogravimetric analysis (TGA), laser flash analysis (LFA), and infrared thermal imaging. The test results indicated that xonotlite fibers could be inserted well into the interlayers of expanded vermiculite. And the intercalation of xonotlite greatly improved the thermal insulation performance of expanded vermiculite at high temperature. The thermal conductivity of this composite decreased with intercalation rate increasing. The composite with intercalation rate of 51.43 % had the lowest thermal conductivity of 0.2116 W/mK at 800 °C which was 55.36 % lower than the expanded vermiculite sample. Meanwhile, this composite had good thermal stability and high temperature resistance. In addition, the thermal expansion of vermiculite and the synthesis of nano-xonotlite fibers were comprehensively studied and discussed. This study will provide a new perspective and ideas for developing vermiculite-based thermal insulating materials. [ABSTRACT FROM AUTHOR]

• This study proposed the surrogate model to predict recycled aggregate concrete (RAC) creep behavior utilizing machine learning (ML). • Both grid search algorithm and k-fold cross-validation were utilized to find the optimal hyperparameters. • The XGBoost, was shown to have a higher efficiency and accuracy for predicting RAC creep over other methods. • The results are helpful to comprehend the performance of RAC structures and promote the application of RAC in buildings. This paper comprehensively investigated the surrogate model of recycled aggregate concrete (RAC) creep behavior prediction for the first time utilizing five typical machine learning (ML) algorithms trained with the RAC_Creep_v1 database. The grid search algorithm and k -fold cross-validation are performed to find the optimal hyperparameters. Then, attribute importance analysis and correlation analysis were conducted to evaluate the effect of various input variables on the results. By retraining the XGBoost model after feature selection, the results revealed that loading age has the greatest impact on RAC creep performance. The XGBoost, the optimal model via evaluation and comparison, was shown to have a higher efficiency and accuracy for predicting RAC creep subjected to different variables. Furthermore, the result of this paper can assist designers in comprehending the performance of RAC structures, promoting the application of RAC in buildings and the study for reducing carbon emissions. [ABSTRACT FROM AUTHOR]

[Display omitted] • A novel humidity self-regulating interior wall coating composite based on red mud was prepared. • The hygroscopicity of HRCRM were systematically investigated and analyzed. • Various properties of HRCRM were tested and the moisture absorption mechanism was analyzed. Aimed to resolve the problem of excessively high indoor humidity in subtropical areas and develop a new resource disposal technique for red mud, a novel humidity self-regulating interior wall coating composite based on red mud (HRCRM) was successfully prepared using red mud as a matrix material and vermiculite as a humidity regulator. The effects of component proportion, ambient humidity, exposure time on hygroscopicity of this composite were systematically investigated. This composite exhibited good humidity regulating ability with the largest water absorption rate of 16.38% under experimental conditions. Moreover, various properties were tested including surface drying time, hardness, adhesion, coating appearance, water resistance and reusability, meeting the national standard requirements well. The mechanism was comprehensively analyzed by XRD, TG-DTG, FESEM, and FTIR, indicating that the humidity self-adjusting function of HRCRM was realized by regulating the interlayer water storage of vermiculite. This study can provide theoretical and technical guidance for residential environment improvement in subtropical areas and comprehensive utilization of red mud. [ABSTRACT FROM AUTHOR]

Developing nanoporous thermal insulation materials is an effective method for solving energy consumption problems. In this study, fumed silica based thermal insulating composite was prepared using a novel dry molding method. Thermal conductivity was measured using a guarded hot plate method in the steady state. The results indicated that this composite exhibited excellent thermal insulating performance, achieving an ultra-low thermal conductivity of 0.0205 W/mK at 100 °C. By analyzing the microstructure using field emission scanning electron microscopy (FESEM), we found that the fiber surface was modified by a 12 μm-thick layer of fumed silica particles that reduced solid heat transfer. However, at high temperatures, thermal insulating performance decreased rapidly, and thermal conductivity reached up to 0.119 W/mK at 500 °C. Based on this problem, a heat transfer model was constructed to explain micro-nano scale heat transfer mechanisms of this composite. The results indicated that gas-solid coupled thermal conductivity occupied a large proportion of 78.3% at 100 °C, but the value was only 0.015 W/mK. As the serving temperature increased, radiative heat transfer gradually occupied the dominant position in total heat transfer. Radiative thermal conductivity reached up to 0.101 W/mK at 500 °C, which was approximately 93.3% of total thermal conductivity. Therefore, it was apparent that the increase in radiative heat transfer was the main cause of the decline in thermal insulating performance at high temperatures. Additionally, the effect of the fiber mass ratio on thermal conductivity was investigated at various temperatures. Empirical and simulated data were compared, and the results revealed that the heat transfer model was basically consistent with experimental findings, achieving a mean error of only 4.78%. [ABSTRACT FROM AUTHOR]