The CrackNet, an efficient architecture based on the Convolutional Neural Network (CNN), is proposed in this article for automated pavement crack detection on 3D asphalt surfaces with explicit ...objective of pixel‐perfect accuracy. Unlike the commonly used CNN, CrackNet does not have any pooling layers which downsize the outputs of previous layers. CrackNet fundamentally ensures pixel‐perfect accuracy using the newly developed technique of invariant image width and height through all layers. CrackNet consists of five layers and includes more than one million parameters that are trained in the learning process. The input data of the CrackNet are feature maps generated by the feature extractor using the proposed line filters with various orientations, widths, and lengths. The output of CrackNet is the set of predicted class scores for all pixels. The hidden layers of CrackNet are convolutional layers and fully connected layers. CrackNet is trained with 1,800 3D pavement images and is then demonstrated to be successful in detecting cracks under various conditions using another set of 200 3D pavement images. The experiment using the 200 testing 3D images showed that CrackNet can achieve high Precision (90.13%), Recall (87.63%) and F‐measure (88.86%) simultaneously. Compared with recently developed crack detection methods based on traditional machine learning and imaging algorithms, the CrackNet significantly outperforms the traditional approaches in terms of F‐measure. Using parallel computing techniques, CrackNet is programmed to be efficiently used in conjunction with the data collection software.
The nonlinear effects exhibited by structures under the action of wind loads have gradually stepped into the vision of wind-resistant researchers. By summarizing the prominent wind-induced nonlinear ...problems of four types of wind-sensitive structures, namely tall buildings, high-rise structures, flexible bridges, and transmission lines, the occurrence mechanism of their nonlinear effects is revealed, providing cutting-edge research progress in theoretical studies, experimental methods and vibration control. Aerodynamic admittance provides insights into the aerodynamic nonlinearity (AN) between the wind pressure spectrum and wind speed spectrum of tall building surfaces. The equivalent nonlinear equation method is used to solve nonlinear vibration equations with generalized van-der-Pol-type aerodynamic damping terms. The elastic–plastic finite element method and multiscale modeling method are widely employed to analyze the effects of geometric nonlinearity (GN) and material nonlinearity (MN) at local nodes on the wind-induced response of latticed tall structures. The AN in blunt sections of bridges arises from the amplitude dependence of the aerodynamic derivative and the higher-order term of the self-excited force. Volterra series aerodynamic models are more suitable for the nonlinear aerodynamic modeling of bridges than the polynomial models studied more in the past. The improved Lindstedt–Poincare perturbation method, which considers the strong GN in the response of ice-covered transmission lines, offers high accuracy. The complex numerical calculations and nonlinear analyses involved in wind-induced nonlinear effects continue to consume significant computational resources and time, especially for complex wind field conditions and flexible and variable structural forms. It is necessary to further develop analytical, modeling and identification tools to facilitate the modeling of nonlinear features in the future.
Reliable short-term wind speed prediction is critical for ensuring the rational exploitation and utilization of wind energy. However, due to complex characteristics (e.g., nonstationarity, ...nonlinearity, uncertainty, etc.) of natural winds, the realization of this task usually confronts a great challenge. For this purpose, an innovative method for forecasting short-term wind speeds is developed based on the principle of “decomposition-prediction-ensemble”. Concretely, a new pretreatment technique, including boxplot figure based abnormal data diagnosis and correction, multivariate fast iterative filtering based time-frequency decomposition, and improved amplitude and frequency modulation based subseries reconstruction, is first developed to perform the high-quality data preprocessing. Then, three different algorithms in conjunction with the correntropy loss and consideration of model diversity are designed as high-performance predictors to capture more data characteristics. Further, a hybrid ensemble strategy combining stacking ensemble and hierarchical ensemble is developed to learn the potential interaction or nonlinear correlation among decomposed subseries as well as some uncertain information for high-reliability prediction. The eventual predictions are given in the form of deterministic point-value, interval, and real-time probability density function. Numerical examples based on four sets of multi-height wind speed data prove the effectiveness and superiority of the proposed method. For example, the average promotion obtained by this method compared with univariate conditional kernel density estimation in terms of mean absolute error is 33.87%, while the improvement in terms of coverage width criterion is 29.64%.
•A new pretreatment technique is designed for high-quality data processing.•Three predictors with high robustness and strong generalization are developed.•Hybrid ensemble strategy can yield deterministic and probabilistic predictions.
Walnuts exhibit a higher resistance to diseases, though they are not completely immune. This study focuses on the Pectin methylesterase (PME) gene family to investigate whether it is involved in ...disease resistance in walnuts. These 21 genes are distributed across 12 chromosomes, with four pairs demonstrating homology. Variations in conserved motifs and gene structures suggest diverse functions within the gene family. Phylogenetic and collinear gene pairs of the PME family indicate that the gene family has evolved in a relatively stable way. The cis-acting elements and gene ontology enrichment of these genes, underscores their potential role in bolstering walnuts' defense mechanisms. Transcriptomic analyses were conducted under conditions of Cryptosphaeria pullmanensis infestation and verified by RT-qPCR. The results showed that certain JrPME family genes were activated in response, leading to the hypothesis that some members may confer resistance to the disease.
•Twenty-one JrPME genes were identified in Juglans regia and grouped into five subfamilies.•The JrPME gene family has direct and indirect disease resistance roles in Juglans regia.•The JrPME gene family responds to the pathogenic fungus Cryptosphaeria pullmanensis when it infects walnut trees.
This study develops a three-dimensional (3D) Laser Railway Detection System for automated railway fastener defect detection on 3D ballastless track. The 3D laser imaging system overcomes the ...shortcomings of shadows and illumination variations, thereby providing 3D information of the ballastless track with high reproducibility and accuracy. RailNet, an efficient architecture based on a Convolutional Neural Network (CNN), is proposed in this paper for detecting high-speed railway fastener defects on 3D ballastless track. RailNet consists of 10 layers and includes more than 120,000 parameters. RailNet is trained using 80,000 3D fastener images with 1-mm resolution and is then demonstrated to be successful at identifying damaged and missing fasteners. The testing results show that the system described in this paper can inspect the defective hook-shaped fasteners notably well. The proposed RailNet significantly outperforms the other approaches with a prediction accuracy of 100%, and the number of testing samples is 16,000.
when the ballast track stretch with the bridge, ballast which is near expansion joint will move confusedly. As a result, rail produced vertical deformation. The deformation will affect the running ...safety and comfortability of train. At present, there are two kinds of treatments which are cover board structure and baffle structure to deal ballast’s movement. Aiming at the different modes of stretching when the two kinds of structures and different arrangement condition of bridge plate are applied, the rail-sleeper-ballast discrete element model is developed by the method of two-dimensional granular flow. The relationship between rail deformation and bridge expansion is analyzed on the foundation of the model. Results show as flows: when bridge extends or shortens, rail always produced upwarp deformation. Bridge plate should arrange asymmetrically. Like this, the rail deformation decrease by 40%. And adopting the baffle structure can effectively reduce the influence of bridge expansion in ballast truck.
Considering the common application of the 20m simply supported beam in modern urban rail transit, an integrative rail-bridge-pier finite element model is developed. The force imposed on the pier, ...abutment and rail are calculated in different conditions, including the bridge stretching, bending and braking. In addition, the displacement of pier top and the maximum rapid relative displacement between girder and track are also calculated. The results are shown as follows: in terms of multiple span simply supported beams, the most harmful bending mode is when the load distributes on two adjacent simply supported beams. According to the additional braking tension force, as well as the additional braking pressure and the rapid relative displacement between girder and track, the most harmful breaking mode can be confirmed respectively. In the paper, the minimum value of the longitudinal horizontal linear stiffness of 20m simply supported beam piers is 120 kN/cm (double-line).
Environmental pollution caused by tetracycline antibiotics is a major concern of global public health. Here, a novel and portable molecularly imprinted electrochemiluminescence (MIECL) sensor based ...on smartphones for highly sensitive detection of chlortetracycline (CTC) has been successfully established. The high-performance ECL emitter of biomass carbon (BC) encapsulated CdZnTeS (CdZnTeS@BC) was successfully synthesized by hydrothermal. The enhanced ECL performance was ascribed to the introduction of the BC and increased the overall electrical conductivity of the nanoemitter, as well as increased the number of sulfur vacancies and doping on the surface of the emitter based on density functional theory calculations. An aniline-CTC molecular imprinted polymer was synthesized on the surface of the CdZnTeS@BC modified electrode by in-situ electropolymerization. The decrease in MIECL signal was attributed to the increase in impedance effect. The MIECL nanoplatform enabled a wide linear relationship in the range of 0.05-100 μmol/L with a detection limit of 0.029 μmol/L for spectrometer sensors. Interestingly, the light emitted during the MIECL reaction can be captured by a smartphone. Thus, machine learning was used to screen the photos that were taken, and color analysis was carried out on the screened photos by self-developed software, thus achieving a portable, convenient, and intelligent sensing mode. Finally, the sensor obtains satisfactory results in the detection of actual samples, with no significant differences from those of liquid chromatography.
A new type of porous carbon is prepared by cost-effective pyrolysis carbonization and subsequent alkali activation of an easily available biomass, magnolia leaf (ML). The as-prepared ML porous ...carbons (MPCs) show high specific surface areas and suitable pore size distributions. Surface characterization of ML and MPC-1 were investigated by N 2 adsorption, FT-IR, SEM and TEM. Two anionic azo dyes were used, namely, orange II (OII) and methyl orange (MO), to simulate the textile effluent. Batch experiments of OII and MO in a single dye system (SDS) and a binary dye system (BDS) onto MPC-1 were investigated as a function of pH, contact time and species concentration. The adsorption process followed the Langmuir isotherm model with high coefficients of correlation ( R 2 > 0.999). The pseudo-second order kinetic model fitted well to the experimental results. This study indicates that MPCs demonstrated superior OII and MO adsorption capabilities and could be employed as a low cost alternative to commercially available porous carbon for the removal of dyes from wastewater.