检索结果-南通市图书馆

Drogue detection for autonomous aerial refueling based on convolutional neural networks

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2017年第1期30卷 380-390页

作者： wang xufeng Dong Xinmin Kong Xingwei Li Jianmin Zhang Bo School of Aeronautics and Astronautics Engineering Air Force Engineering University State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University

Drogue detection is a fundamental issue during the close docking phase of autonomous aerial refueling（AAR）. To cope with this issue, a novel and effective method based on deep learning with convolutional neural networks（CNNs） is proposed. In order to ensure its robustness and wide application, a deep learning dataset of images was prepared by utilizing real data of ‘‘Probe and Drogue＂ aerial refueling, which contains diverse drogues in various environmental conditions without artificial features placed on the drogues. By employing deep learning ideas and graphics processing units（GPUs）, a model for drogue detection using a Caffe deep learning framework with CNNs was designed to ensure the method＇s accuracy and real-time performance. Experiments were conducted to demonstrate the effectiveness of the proposed method, and results based on real AAR data compare its performance to other methods, validating the accuracy, speed, and robustness of its drogue detection ability.

关键词： Autonomous aerial refueling Computer vision Convolutional neural net-works Deep learning Drogue detection

Characteristics and stability of slope movement response to underground mining of shallow coal seams away from gullies

在线全文

学校读者我要写书评

暂无评论

International Journal of Mining Science and Technology 2012年第1期22卷 47-50页

作者： Zhang Dongsheng Fan Gangwei wang xufeng College of Geology and Exploration Engineering Xinjiang UniversityUrumchi 830046China School of Mines China University of Mining&TechnologyXuzhou 221116China State Key Laboratory of Coal Resource and Mine Safety China University of Mining&TechnologyXuzhou 221008China

Underground pressure is abnormal during mining of shallow coal seams under gullies. We studied gully slope movements, subject to underground mining, with physical simulation and theoretical analysis. The rules disclose that the slope rock slides horizontally in response to mining in the direction of gullies and rotates reversely with the appearance of a polygon block in mining away from gullies. We focused our attention on the case of mining away from a gully. We built a mechanical model in terms of a polygon block hinged structure and investigated the variation of horizontal thrust and shear force at the hinged point in relation to the rotation angle under different fragmentations. The Sliding-Rotation instability conditions of the polygon block hinged structure are presented based on the analyses of sliding instability and rotation instability. These results can serve as a theoretical guide for roof control during mining away from gullies in a coalfield defined by gullies.

关键词： Shallow coal seam Mining away from gullies Polygon block hinged structure Sliding instability Rotation instability

The uncertainty analysis of the MODIS GPP product in global maize croplands

在线全文

学校读者我要写书评

暂无评论

Frontiers of Earth Science 2018年第4期12卷 739-749页

作者： Xiaojuan HUANG Mingguo MA xufeng wang Xuguang TANG Hong YANG Chongqing Engineering Research Center for Remote Sensing Big Data Application Southwest UniversityChongqing 400715China Research Base of Karst Eco-environments at Nanchuan in Chongqing Ministry of Natural ResourcesSchool of Geographical SciencesSouthwest UniversityChongqing 400715China Northwest Institute of Eco-environment and Resources Chinese Academy of SciencesLanzhou 730000China Department of Geography and Environmental Science University of ReadingReading RG66ABUK

Gross primary productivity (GPP) is very important in the global carbon cycle. Currently, the newly released estimates of 8-day GPP at 500 m spatial resolution (Collection 6) are provided by the Moderate Resolution Imaging Spectroradiometer (MODIS) Land Science Team for the global land surface via the improved light use efficiency (LUE) model. However, few studies have evaluated its performance. In this study, the MODIS GPP products (GPP(MOD)) were compared with the observed GPP (GPP(EC)) values from site-level eddy covariance measurements over seven maize flux sites in different areas around the world. The results indicate that the annual GPP(MOD) was underestimated by 6%aEuro'58% across sites. Nevertheless, after incorporating the parameters of the calibrated LUE, the measurements of meteorological variables and the reconstructed Fractional Photosynthetic Active Radiation (FPAR) into the GPP(MOD) algorithm in steps, the accuracies of GPP(MOD) estimates were improved greatly, albeit to varying degrees. The differences between the GPP(MOD) and the GPP(EC) were primarily due to the magnitude of LUE and FPAR. The underestimate of maize cropland LUE was a widespread problem which exerted the largest impact on the GPP(MOD) algorithm. In American and European sites, the performance of the FPAR exhibited distinct differences in capturing vegetation GPP during the growing season due to the canopy heterogeneity. In addition, at the DE-Kli site, the GPP(MOD) abruptly produced extreme low values during the growing season because of the contaminated FPAR from a continuous rainy season. After correcting the noise of the FPAR, the accuracy of the GPP(MOD) was improved by approximately 14%. Therefore, it is crucial to further improve the accuracy of global GPP(MOD), especially for the maize crop ecosystem, to maintain food security and better understand global carbon cycle.

关键词： MODIS GPP eddy covariance maize cropland validation improvement

Roof filling control technology and application to mine roadway damage in small pit goaf

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Mining Science and Technology 2019年第3期29卷 477-482页

作者： Weiyi Cai Zechao Chang Dongsheng Zhang xufeng wang Wenhao Cao Yazhou Zhou School of Mines China University of Mining & TechnologyXuzhou 221116China State Key Laboratory of Coal Resources and Safe Mining China University of Mining & TechnologyXuzhou 221116China Key Laboratory of Deep Coal Re-source Mining Ministry of Education of ChinaChina University of Mining & TechnologyXuzhou 221116China

To recover coal resources that have been damaged by traditional mining methods and ensure stability of the lower roadway in a small pit goaf,the goaf area must be filled and *** this research,the 1202 working face of the Hanzui mine is considered as an example for classifying the roof of the mining tunnel under the small kiln destruction zone,the effect of the goaf on the roadway is determined based on the radio tunnel penetration method,a mechanical model to determine the roof filling control mechanism was established,and the duct foaming system and roof filling process were *** results show that the scope and degree of influence of the goaf on the mining lane are large,but safe tunneling can be ensured through the use of a steel shed and advanced grouting *** the roof conditions are not similar,materials with different filling heights and filling strengths can be used to control the roof filling of the *** combining field experience and laboratory tests,it was determined that a high-foaming material with a water-cement ratio of 1:0.6,a suitable high-foaming additive,and a water volume ratio of 1:30 is cost-efficient for filling and meets the filling strength ***,the reliability of the proposed technology was verified by field experiments,which provide a reference for filling operations in similar mines.

关键词： Repeated mining Roadway roof control High foam material Filling mining

Detection and threshold-adaptive segmentation of farmland residual plastic film images based on CBAM-DBNet

在线全文

学校读者我要写书评

暂无评论

International Journal of Agricultural and Biological Engineering 2024年第5期17卷 231-238页

作者： Lijian Xiong Can Hu xufeng wang Hongbiao wang Xiuying Tang Xingwang wang College of Engineering China Agricultural UniversityBeijing 100083China Modern Agricultural Engineering Key Laboratory at the Universities of Education Department of Xinjiang Uygur Autonomous Region Tarim UniversityAlaer 843300China College of Mechanical and Electrical Engineering Tarim UniversityAlaer 843300China

Robust, accurate, and fast monitoring of residual plastic film (RPF) pollution in farmlands has great significance. Based on CBAM-DBNet, this study proposed a threshold-adaptive joint framework for identifying the RPF on farmland surfaces and estimating its coverage rate. UAV imaging was used to gather images of the RPF from several locations with various soil backgrounds. RPFs were manually labeled, and the degree of RPF pollution was defined based on the RPF coverage rate. Combining differentiable binarization network (DBNet) with the convolutional block attention module (CBAM), whose feature extraction module was improved. A dynamic adaptive binarization threshold formula was defined for segmenting the RPF’s approximate binary map. Regarding the RPF image detection branch, the CBAM-DBNet exhibited a precision (P) value of 85.81%, a recall (R) value of 82.69%, and an F1-score (F1) value of 84.22%, which was 1.09 percentage points higher than the DBNet in the comprehensive index F1 value. For the RPF image segmentation branch, using CBAM-DBNet to segment the RPF image combined with an adaptive binarization threshold formula. Subsequently, the mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE) of the prediction of RPF’s coverage rate were 0.276, 0.366, and 0.605, respectively, outperforming the DBNet and the Iterative Threshold method. This study provides a theoretical reference for the further development of evaluation technology for RPF pollution based on UAV imaging.

关键词： binarization threshold adaptive residual plastic film object detection image segmentation UAV remote sensing

Underground pressure characteristics analysis in back-gully mining of shallow coal seam under a bedrock gully slope

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Mining Science and Technology 2011年第1期21卷 23-27页

作者： wang xufeng Zhang Dongsheng Fan Gangwei Zhang Chengguo School of Mines Chino University of Mining ＆ Technology Xuzhou 221116 China Stote Key Laboratory of Coal Resource and Mine Safety Chino University of Mining ＆ Technology Xuzhou 221008 China

We studied underground pressure and its mechanism during back-gully mining in a shallow coal seam under a bedrock gully slope,by means of physical simulation,numerical modeling and field *** results show that the intensity of underground pressure is related to its relative position at the *** underground pressure is intensive and the support resistance reaches a maximum when the coalface is at the bottom of the gully,whereas the underground pressure is moderate and decreases gradually when the coalface passes the *** mechanism of these changes is analyzed when the slope rotated in a reversed direction to the slope dip during back-gully mining and form an unstable,multilateral block hinged structure,due to *** subsidence of multilateral blocks is considerable when the block fragmentation is small,resulting in enormous changes in the underground *** an increase in the mass of the block body,the block displacement will be reduced in conjunction with an increased clamp effect by both the unbroken rocks and broken rocks in the goaf,resulting in a decrease of the underground pressure.

关键词： Shallow coal seam Gully slope Back-gully mining Underground pressure

Feature Recognition and Tracking of Aircraft Tanker and Refueling Drogue for UAV Aerial Refueling

在线全文

学校读者我要写书评

暂无评论

Feature Recognition and Tracking of Aircraft Tanker and Refu...

Unveiling evapotranspiration patterns and energy balance in a subalpine forest of the Qinghai-Tibet Plateau:observations and analysis from an eddy covariance system

第25届中国控制与决策会议

作者： wang xufeng DONG Xinmin KONG Xingwei School of Aeronautics and Astronautics Engineering Air Force Engineering University

ISBN: (纸本)9781467355339

This paper describes the results of the analysis of specific ’feature detection and recognition’ algorithms within a Machine Vision approach for the problem of aerial refueling for unmanned aerial vehicles. In order to precisely obtain the center of the features of the aircraft tanker and refueling drogue in the images of vision-based navigation during automated aerial refueling docking, a feature extraction method based on the HSV color space information of images is proposed. The HSV color space is introduced and the features of the aircraft tanker and refueling drogue are made based on the principle of choosing features. By using of least square ellipse fitting, after making color converted, color phase filter, binary and edge detection on images. The feature locations of the aircraft tanker and refueling drogue are precisely obtained and tracked. The experiment shows that the method proposed can not only extract the features accurately but can also calculate their locations in real-time, which provides a more reliable feature extraction and tracking method for vision-based navigation for automated aerial refueling.

关键词： UAV Aerial Refueling Feature Recognition and Tracking Aircraft Tanker Refueling Drogue

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Forestry Research 2024年第3期35卷 175-188页

作者： Niu Zhu Jinniu wang Dongliang Luo xufeng wang Cheng Shen Ning Wu Ning Zhang Binghui Tian Aihong Gai Chengdu Institute of Biology Chinese Academy of SciencesChengdu 610041People's Republic of China College of Resources and Environmental Sciences Gansu Agricultural UniversityLanzhou 730070People's Republic of China Mangkang Ecological Monitoring Station Tibet Ecological Security Barrier Ecological Monitoring NetworkQamdo 854500People's Republic of China Northwest Institute of Eco Environmental Resources Chinese Academy of SciencesLanzhou 730000People's Republic of China

Evapotranspiration is an important parameter used to characterize the water cycle of *** under-stand the properties of the evapotranspiration and energy balance of a subalpine forest in the southeastern Qinghai-Tibet Plateau,an open-path eddy covariance system was set up to monitor the forest from November 2020 to October 2021 in a core area of the Three Parallel Rivers in the Qing-hai-Tibet *** results show that the evapotranspira-tion peaked daily,the maximum occurring between 11:00 and 15:*** factors had significant effects on evapotranspiration,among them,net radiation the greatest(R^(2)=0.487),and relative humidity the least(R^(2)=0.001).The energy flux varied considerably in different seasons and sensible heat flux accounted for the main part of turbulent *** energy balance ratio in the dormant season was less than that in the growing season,and there is an energy imbalance at the site on an annual time scale.

关键词： Evapotranspiration Energy balance Subalpine forest Three Parallel Rivers region Southeast Qinghai-Tibet Plateau

Construction of virtual mulch film model based on discrete element method and simulation of its physical mechanical properties

在线全文

学校读者我要写书评

暂无评论

International Journal of Agricultural and Biological Engineering 2020年第4期13卷 211-218页

作者： Wensong Guo Can Hu Xiaowei He Long wang Shulin Hou xufeng wang College of Mechanical and Electrical Engineering Tarim UniversityAlar 843300XinjiangChina College of Engineering China Agricultural UniversityBeijing 100083China

In China,especially in Xinjiang Region,mulch film remaining in the soil has severely jeopardized the safety of soil *** numerically simulate the residual film-soil-recovery implementation system,a virtual mulch film model with consistent physical and mechanical properties with real mulch film needs to be *** this study,a flexible deformable virtual mulch film model was constructed using YADE software based on the Minkowski Sum principle and the ball-ball force-displacement constitutive rule,as well as the contact failure rule were *** deformation behaviors of cylinders and PFacet elements,such as stretching,bending,and torsion,were *** splicing the basic PFacet elements,a virtual mulch model was *** mechanical model of a virtual mulch film under tension was established and the axial tensile stiffness coefficient kn was determined to be 43.30 N·*** verify the physical and mechanical properties of this virtual mulch film,both real and virtual stretching and tearing tests were *** experimental results showed that:in the process of stretching and tearing of real and virtual films,the properties of morphological features of both are basically identical;however,they clearly differ in *** viscoelastic constitutive model between balls and yield judgment conditions requires further study.

关键词： discrete element method mulching film physical and mechanical properties virtual test