检索结果-南通市图书馆

Science China Technological Sciences 2024年第6期67卷 1923-1932页

作者： ZHAO Tao SHI Yan LU Kun XI Xiang WU XueZhong XIAO DingBang college of Intelligence Science and engineering National University of defense Technology

The quality factor(Q factor) is a crucial performance parameter for resonators. In this paper, a novel release method for highquality micro fused silica shell resonators with teeth-like tines with good surface morphology is proposed. This method is based on femtosecond laser-assisted chemical etching. First, the optimal energy range of femtosecond laser modification is obtained through mechanism analysis. Second, the optimal parameters for a straight line and arc pattern are determined by optimizing the average output power, processing speed, and processing spacing. The results demonstrate why edge breakage in rounded corners is easy under different parameters. Finally, according to these conclusions, the processing is performed on a micro fused silica shell resonator with a Q factor exceeding 6 million. In addition, subsurface damage is rare throughout the fabrication process, and the surface roughness of the released cross section reaches the nanometer level. The improved Q factor helps suppress mechanical thermal noise and reduce zero bias and zero bias drift, constituting the primary method for enhancing the performance of the resonant gyroscope.

关键词： micro hemispherical resonator fused silica laser-assisted chemical etching quality factor

Operational requirements analysis method based on question answering of WEKG

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems engineering and Electronics 2024年第2期35卷 386-395页

作者： ZHANG Zhiwei DOU Yajie XU Xiangqian MA Yufeng JIANG Jiang TAN Yuejin college of Systems engineering National University of Defense TechnologyChangsha 410073China

The weapon and equipment operational requirement analysis(WEORA) is a necessary condition to win a future war,among which the acquisition of knowledge about weapons and equipment is a great challenge. The main challenge is that the existing weapons and equipment data fails to carry out structured knowledge representation, and knowledge navigation based on natural language cannot efficiently support the WEORA. To solve above problem, this research proposes a method based on question answering(QA) of weapons and equipment knowledge graph(WEKG) to construct and navigate the knowledge related to weapons and equipment in the WEORA. This method firstly constructs the WEKG, and builds a neutral network-based QA system over the WEKG by means of semantic parsing for knowledge navigation. Finally, the method is evaluated and a chatbot on the QA system is developed for the WEORA. Our proposed method has good performance in the accuracy and efficiency of searching target knowledge, and can well assist the WEORA.

关键词： operational requirement analysis weapons and equipment knowledge graph(WEKG) question answering(QA) neutral network

Requirements ranking based on crowd-sourcing high-end product USs

在线全文

学校读者我要写书评

暂无评论

Journal of Systems engineering and Electronics 2024年第1期35卷 94-104页

作者： MA Yufeng DOU Yajie XU Xiangqian JIA Qingyang TAN Yuejin college of Systems engineering National University of Defense TechnologyChangsha 410003China

Based on the characteristics of high-end products,crowd-sourcing user stories can be seen as an effective means of gathering requirements,involving a large user base and generating a substantial amount of unstructured feedback.The key challenge lies in transforming abstract user needs into specific ones,requiring integration and analysis.Therefore,we propose a topic mining-based approach to categorize,summarize,and rank product requirements from user stories.Specifically,after determining the number of story categories based on py LDAvis,we initially classify“I want to”phrases within user stories.Subsequently,classic topic models are applied to each category to generate their names,defining each post-classification user story category as a requirement.Furthermore,a weighted ranking function is devised to calculate the importance of each requirement.Finally,we validate the effectiveness and feasibility of the proposed method using 2966 crowd-sourced user stories related to smart home systems.

关键词： high-end product complex system crowd-sourcing user stories topic mining requirements ranking

Accurately tracking hypersonic gliding vehicles via an LEO mega-constellation in relay tracking mode

在线全文

学校读者我要写书评

暂无评论

Journal of Systems engineering and Electronics 2024年第1期35卷 211-221页

作者： LI Zhao WANG Yidi ZHENG Wei college of Aerospace Science and engineering National University of Defense TechnologyChangsha 410073China

In order to effectively defend against the threats of the hypersonic gliding vehicles(HGVs),HGVs should be tracked as early as possible,which is beyond the capability of the ground-based radars.Being benefited by the developing megaconstellations in low-Earth orbit,this paper proposes a relay tracking mode to track HGVs to overcome the above problem.The whole tracking mission is composed of several tracking intervals with the same duration.Within each tracking interval,several appropriate satellites are dispatched to track the HGV.Satellites that are planned to take part in the tracking mission are selected by a new derived observability criterion.The tracking performances of the proposed tracking mode and the other two traditional tracking modes,including the stare and track-rate modes,are compared by simulation.The results show that the relay tracking mode can track the whole trajectory of a HGV,while the stare mode can only provide a very short tracking arc.Moreover,the relay tracking mode achieve higher tracking accuracy with fewer attitude controls than the track-rate mode.

关键词： target tracking mega-constellation hypersonic gliding vehicle(HGV) sensor selection observability analysis

Semi-supervised remote sensing image scene classification with prototype-based consistency

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第2期37卷 459-470页

作者： Yang LI Zhang LI Zi WANG Kun WANG Qifeng YU college of Aerospace Science and engineering National University of Defense TechnologyChangsha 410073China

Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.

关键词： Semi-supervised learning Remote sensing Scene classification Prototype network Deep learning

Adaptive and augmented active anomaly detection on dynamic network traffic streams

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic engineering 2024年第3期25卷 446-460页

作者： Bin LI Yijie WANG Li CHENG National Key Laboratory of Parallel and Distributed Computing College of ComputerNational University of Defense TechnologyChangsha 410073China college of System engineering National University of Defense TechnologyChangsha 410073China

Active anomaly detection queries labels of sampled instances and uses them to incrementally update the detection model,and has been widely adopted in detecting network attacks.However,existing methods cannot achieve desirable performance on dynamic network traffic streams because(1)their query strategies cannot sample informative instances to make the detection model adapt to the evolving stream and(2)their model updating relies on limited query instances only and fails to leverage the enormous unlabeled instances on streams.To address these issues,we propose an active tree based model,adaptive and augmented active prior-knowledge forest(A3PF),for anomaly detection on network trafic streams.A prior-knowledge forest is constructed using prior knowledge of network attacks to find feature subspaces that better distinguish network anomalies from normal traffic.On one hand,to make the model adapt to the evolving stream,a novel adaptive query strategy is designed to sample informative instances from two aspects:the changes in dynamic data distribution and the uncertainty of anomalies.On the other hand,based on the similarity of instances in the neighborhood,we devise an augmented update method to generate pseudo labels for the unlabeled neighbors of query instances,which enables usage of the enormous unlabeled instances during model updating.Extensive experiments on two benchmarks,CIC-IDS2017 and UNSW-NB15,demonstrate that A3PF achieves significant improvements over previous active methods in terms of the area under the receiver operating characteristic curve(AUC-ROC)(20.9%and 21.5%)and the area under the precision-recall curve(AUC-PR)(44.6%and 64.1%).

关键词： Active anomaly detection Network traffic streams Pseudo labels Prior knowledge of network attacks

A physics-informed deep learning framework for spacecraft pursuit-evasion task assessment

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第5期37卷 363-376页

作者： Fuyunxiang YANG Leping YANG Yanwei ZHU college of Aerospace Science and engineering National University of Defense TechnologyChangsha 410073China

Qualitative spacecraft pursuit-evasion problem which focuses on feasibility is rarely studied because of high-dimensional dynamics,intractable terminal constraints and heavy computational cost.In this paper,A physics-informed framework is proposed for the problem,providing an intuitive method for spacecraft threat relationship determination,situation assessment,mission feasibility analysis and orbital game rules summarization.For the first time,situation adjustment suggestions can be provided for the weak player in orbital game.First,a dimension-reduction dynamics is derived in the line-of-sight rotation coordinate system and the qualitative model is determined,reducing complexity and avoiding the difficulty of target set presentation caused by individual modeling.Second,the Backwards Reachable Set(BRS)of the target set is used for state space partition and capture zone presentation.Reverse-time analysis can eliminate the influence of changeable initial state and enable the proposed framework to analyze plural situations simultaneously.Third,a time-dependent Hamilton-Jacobi-Isaacs(HJI)Partial Differential Equation(PDE)is established to describe BRS evolution driven by dimension-reduction dynamics,based on level set method.Then,Physics-Informed Neural Networks(PINNs)are extended to HJI PDE final value problem,supporting orbital game rules summarization through capture zone evolution analysis.Finally,numerical results demonstrate the feasibility and efficiency of the proposed framework.

关键词： Spacecraft pursuit-evasion Qualitative differential game Physics-Informed Neural Networks(PINNs) Reachability analysis Hamilton-Jacobi-Isaacs(HJI) Partial Differential Equations(PDEs)

Span-based joint entity and relation extraction augmented with sequence tagging mechanism

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

Science China(Information Sciences) 2024年第5期67卷 84-98页

作者： Bin JI Shasha LI Hao XU Jie YU Jun MA Huijun LIU Jing YANG college of Computer National University of Defense Technology

Span-based joint extraction simultaneously conducts named entity recognition(NER) and relation extraction(RE) in a text span form. However, since previous span-based models rely on span-level classifications, they cannot benefit from token-level label information, which has been proven advantageous for the task. In this paper, we propose a sequence tagging augmented span-based network(STSN), a spanbased joint model that can make use of token-level label information. In STSN, we construct a core neural architecture by deep stacking multiple attention layers, each of which consists of three basic attention units.On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE. Experimental results on three benchmark datasets show that STSN consistently outperforms the strongest baselines in terms of F1,creating new state-of-the-art results.

关键词： joint extraction named entity recognition relation extraction span sequence tagging mechanism

AstroPose: Astronaut pose estimation using a monocular camera during extravehicular activities

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China Technological Sciences 2024年第6期67卷 1933-1945页

作者： LIU ZiBin LI You WANG ChunHui LIU Liang GUAN BangLei SHANG Yang YU QiFeng college of Aerospace Science and engineering National University of Defense Technology Key Laboratory of Human Factors engineering China Astronaut Research and Training Center

With the completion of the Chinese space station, an increasing number of extravehicular activities will be executed by astronauts,which is regarded as one of the most dangerous activities in human space exploration. To guarantee the safety of astronauts and the successful accomplishment of missions, it is vital to determine the pose of astronauts during extravehicular activities. This article presents a monocular vision-based pose estimation method of astronauts during extravehicular activities, making full use of the available observation resources. First, the camera is calibrated using objects of known structures, such as the spacesuit backpack or the circular handrail outside the space station. Subsequently, the pose estimation is performed utilizing the feature points on the spacesuit. The proposed methods are validated both on synthetic and semi-physical simulation experiments, demonstrating the high precision of the camera calibration and pose estimation. To further evaluate the performance of the methods in real-world scenarios, we utilize image sequences of Shenzhou-13 astronauts during extravehicular activities. The experiments validate that camera calibration and pose estimation can be accomplished solely with the existing observation resources, without requiring additional complicated equipment. The motion parameters of astronauts lay the technological foundation for subsequent applications such as mechanical analysis, task planning, and ground training of astronauts.

关键词： monocular camera astronaut pose estimation camera calibration

Effect of kerosene injection states on mixing and combustion characteristics in a cavity-based supersonic combustor

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第4期37卷 308-320页

作者： Xu LIU Peibo LI Fei LI Hongbo WANG Mingbo SUN Chao WANG Yixin YANG Dapeng XIONG Yanan WANG Science and Technology on Scramjet Laboratory College of Aerospace Science and EngineeringNational University of Defense TechnologyChangsha 410073China

It has been found that the static pressure distribution along the axial direction of liquid kerosene is lower than that of the gaseous kerosene under the same flow condition and overall equivalent ratio from previous studies.To further investigate this phenomenon,a compressible two-phase parallel simulation method is utilized to analyze the mixing and combustion characteristics of gaseous and liquid kerosene jets in a cavity-based supersonic combustor.The numerical results are consistent with the experiments and demonstrate that gaseous injection leads to a cavity shear layer that dives deeper into the cavity,forming two recirculation zones in the front and rear of the cavity.In contrast,the cavity shear layer is closer to the mainstream during liquid injection,and only a large recirculation zone is formed in the rear of the cavity.As a result of the cavity shear layer and the recirculating flow,the fuel vapor of gaseous injection accumulates in the front of the cavity,while for the liquid injection,the fuel vapor disperses in the cavity,cavity shear layer,and the region above,and the rear of the cavity has a higher fuel vapor concentration than the front.This unique fuel distribution causes the combustion area to be concentrated in the cavity during the gaseous injection but dispersed inside and downstream of the cavity during the liquid injection.As a result,forming a thermal throat under the same conditions is more challenging during liquid injection,and the generated static pressure distribution is lower than that during the gaseous injection.

关键词： Gaseous injection Liquid injection Mixing process Combustion Supersonic flow