Search Results (9)

The complex geological environment in western Sichuan, China, leads to frequent debris flow disasters, posing significant threats to the lives and property of local residents. In this study, debris flow susceptibility models were developed using three machine learning algorithms: Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The models were trained with data in Songpan County and used for debris flow susceptibility prediction in Mao County, using small watersheds as assessment units. Seventeen key feature factors based on multi-source remote sensing data encompassing topography and geomorphology, geological structures, environmental elements, and human activities were selected as input parameters after assessment with Pearson correlation analysis. Model performance was rigorously evaluated through ten-fold cross-validation, and hyperparameter optimization was employed to enhance predictive accuracy. To assess the models’ robustness, the trained models were applied to the neighboring Mao County for cross-regional validation. The results consistently indicate that elevation, seismic nucleation density, population density, and distance to roads are the primary controlling factors influencing susceptibility. Comparative analysis between the Songpan and Mao County reveals that the RF model significantly outperforms SVM and XGBoost in accuracy and robustness. Therefore, the RF model is better suited for debris flow susceptibility assessment in western Sichuan. Although the effectiveness of this model may be limited by the relatively small sample size of debris flow events in the dataset and potential variations in environmental conditions across different regions, it still holds promise for providing a scientific basis and decision-making support for disaster mitigation in comparable areas of western Sichuan. Full article

In order to study the dynamic characteristics of the 660 MW ultra-supercritical circulating fluidized bed (CFB) boiler when the main fuel trip (MFT) and boiler trip (BT) are triggered, a dynamic simulation model of the 660 MW ultra-supercritical circulating fluidized bed boiler was established on the Apros simulation platform. The model dynamically simulated the MFT and BT processes at 100% BMCR, 75% THA, and 50% THA conditions, respectively. The steady-state simulation results showed a high accuracy compared with the designed parameters. The dynamic simulation results showed that after triggering the MFT and BT, owing to the huge thermal inertia, the bed temperature and steam temperature decreased lowly. For 100% BMCR and 75% THA conditions, the moisture separator always worked in dry state during the MFT and BT processes. For the 50% THA condition, the moisture separator quickly switched from dry to wet operation after the boiler triggers MFT and BT and gradually switched from wet to dry operation after MFT and BT were reset. Full article

The lightweight property of helical composite spring (HCS) applied in the transportation field has attracted more and more attention recently. However, it is difficult to maintain stiffness and fatigue resistance at the same time. Herein, inspired by collagen fibers in bone, a bionic basalt fiber/epoxy resin helical composite spring is manufactured. The collagen fibers consist of nanoscale hydroxyapatite (increases stiffness) and collagen molecules composed of helical amino acid chains (can increase fatigue resistance). Such a helical structure of intercalated crystals ensures that bone has good resistance to fracture. Specifically, we first investigated the effect of adding different contents of NS to basalt fibers on the stiffness and fatigue properties of an HCS. The results show that the optimal NS content of 0.4 wt% resulted in 52.1% and 43.5% higher stiffness and fatigue properties of an HCS than those without NS, respectively. Then, two braided fiber bundles (TS-BFB) and four braided fiber bundles (FS-BFB) were designed based on the helical structure of amino acid chains, and the compression tests revealed that the maximum load resistance of TS-BFB and FS-BFB was increased by 29.2% and 44%, respectively, compared with the conventional single fiber bundle (U-BFB). The superior mechanical performance of TS-BFB and FS-BFB is attributed to the more adequate bonding of 0.4 wt% NS to the epoxy resin and the multi-fiber bundles that increase the transverse fiber content of the spring. The findings in this work introduce the bionic collagen fiber structure into the design for an HCS and provide a new idea to improve the spring performance. Full article

In today’s diversified development model, the combination of modeling and business decision development is particularly important. The advanced theoretical business model established by modeling enables more efficient and accurate financial analysis. In the original enterprise profit evaluation model, the DuPont analysis method cannot take into account the development capability of the enterprise very well. This article takes Tencent Music as an example, and improves it on the basis of DuPont analysis. The Enterprise Capital Profit Model was proposed. At the same time, the LASSO regression based on cluster analysis is used to screen, analyze, and diagnose the financial data of Tencent Music in recent years, which verifies the validity and feasibility of the model. This paper uses the report data combined with statistical modeling to optimize the traditional financial evaluation method of enterprises, better find problems, and provide strategies for the further development of enterprises. Likewise, the method can be extended to other businesses to help them analyze their financial situation and provide a reference for future development. Full article

For large and medium-sized cities, the planning and development of urban road networks may not keep pace with the growth of urban vehicles, resulting in traffic congestion on urban roads during peak hours. Take Jinan, a mid-sized city in China’s Shandong Province, for example. In view of the daily traffic jam of the city’s road traffic, through investigation and analysis, the existing problems of the road traffic are found out. Based on real-time, daily road traffic data, combined with the existing road network and the planned road network, the application of a road intelligent transportation system is proposed. Combined with the application of a road intelligent transportation system, this paper discusses the future development of urban road traffic and puts forward improvement suggestions for road traffic planning. This paper has reference value for city development, road network construction, the application of intelligent transportation systems, and road traffic planning. Full article

The purpose of this study is to explore the influence of different swimming strokes on the performance of swimmers and the resistance of each part from the perspective of hydrodynamics. In this paper, the influence of internal and external factors on the swimming speed is analyzed comprehensively and meticulously from the macro and micro perspectives. In the macroscopic part, the swimming speed representation model is established, and the validity of the model is further verified by the analysis of experimental data and hydrodynamic equations. In the microscopic part, we carefully analyzed details such as the opening angle of the palm, the timing of the arm and leg and the angular velocity of each link of the human body. Combined with computer simulation, stereo modeling and numerical analysis are carried out, and the best scheme FOR how to cooperate with each part of the body in swimming is given. Full article

Semantic segmentation has been widely used in the basic task of extracting information from images. Despite this progress, there are still two challenges: (1) it is difficult for a single-size receptive field to acquire sufficiently strong representational features, and (2) the traditional encoder-decoder structure directly integrates the shallow features with the deep features. However, due to the small number of network layers that shallow features pass through, the feature representation ability is weak, and noise information will be introduced to affect the segmentation performance. In this paper, an Adaptive Multi-Scale Module (AMSM) and Adaptive Fuse Module (AFM) are proposed to solve these two problems. AMSM adopts the idea of channel and spatial attention and adaptively fuses three-channel branches by setting branching structures with different void rates, and flexibly generates weights according to the content of the image. AFM uses deep feature maps to filter shallow feature maps and obtains the weight of deep and shallow feature maps to filter noise information in shallow feature maps effectively. Based on these two symmetrical modules, we have carried out extensive experiments. On the ISPRS Vaihingen dataset, the F1-score and Overall Accuracy (OA) reached 86.79% and 88.35%, respectively. Full article

Hyperspectral remote sensing is widely used to detect petroleum hydrocarbon pollution in soil monitoring. Different spectral pretreatment methods seriously affect the prediction and analysis of petroleum hydrocarbon contents (PHCs). This study adopted a combined spectral data preprocessing technique that improves the prediction accuracy of petroleum hydrocarbons in soil. We combined continuum removal and wavelet packet decomposition (CR–Daubechies 3 (db3)) to process the hyperspectral reflectance data of 26 soil samples in the oil production work area in China and judged the correlation between spectral reflectance and petroleum hydrocarbons in soil. Partial least squares regression was used to construct an optimal model for the inversion of PHCs in soil and the leave-one-out cross-validation was used to select the best factor number. The best model of soil petroleum hydrocarbon inversion was determined by comprehensively comparing the initial spectrum, db3 to high-frequency spectrum, db3 to low-frequency spectrum, after-continuum removal spectrum, CR-db3 to high-frequency spectrum, and CR-db3 to low-frequency spectrum comprehensively. The main contributions of this study are as follows: (1) three-layer decomposition with CR-db3 can improve the correlation between spectral reflectance and PHCs and effectively improve the sensitivity of the spectrum to PHCs; (2) the prediction accuracy of the high-frequency spectrum of wavelet packet decomposition for PHCs in soil is higher than that of low-frequency information; (3) the proposed petroleum hydrocarbon prediction model based on CR-db3 processed spectra to obtain high-frequency information is optimal (coefficient of determination = 0.977, root mean square error of calibration = 3.078, root mean square error of cross-validation = 4.727, root mean square error of prediction = 4.498, ratio of performance to deviation = 6.12). Full article

A turbulent horseshoe vortex (HV) system around a wall-mounted cylinder in open channel is characterized by random variations in vortex features and an abundance of vortex interactions. The turbulent HV system is responsible for initiating the local scour process in front of the cylinder. The evolution of the turbulent HV system is investigated statistically and quantitatively with time-resolved particle image velocimetry. The cylinder Reynolds numbers of the flow are 8600, 10,200, and 13,600, respectively. A novel vortex tracking method was proposed to obtain the variations in position, size, and strength of the primary HV (PHV) which dominates the system most of the time. Relationships between the various features of the PHV during its evolutionary process were obtained through correlation analyses. Results show that the dimensionless mean lifespan of the PHV is about 5.0. Statistically, the downstream movement of the PHV toward the cylinder is accompanied with its bed-approaching movement and decreasing in size, and the opposite is true. The circulation strength of the PHV decreases and increases dramatically in the region downstream of its time-averaged position when the PHV approaches and departs from the cylinder, respectively. Meanwhile, mechanisms responsible for the generation, movement, variation, and disappearance of the PHV are re-investigated and enriched based on its interactions with vortices in the separation region and structures in the incoming flow. The obtained change trends of the features of the PHV and the underlying mechanisms for its evolution are valuable for predicting and controlling the initial stage of the local scour in front of cylinders. Full article