检索结果-内蒙古大学图书馆

3rd World Symposium on Artificial Intelligence, WSAI 2021

作者： Ma, Yunfei Chen, Huimin Huo, Jian Beijing Institute of Technology Science and Technology on Electromechanical Dynamic Control Laboratory Beijing China

ISBN: (纸本)9780738143033

In modern war, armies from different countries have different weapons for infantry. Therefore, identifying the weapons held by infantry helps to determine their affiliations. In this paper, we have built our dataset of different types of assault rifles from photos. The dataset was trained using the convolutional neural network YOLOv3. Several different real videos were used to verify the YOLOv3 training results. The experiments show that the model can detect and identify assault rifles in different scenes. It proves to work with a good accuracy and can be used in real time on battlefield. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Blind frequency estimation of pseudo-code phase and linear frequency modulation composited fuze by Duffing oscillator 55

Blind frequency estimation of pseudo-code phase and linear f...

引用

55th International Conference on Vibroengineering

作者： Guan, Enming Yan, Xiaopeng Lv, Minghui Wan, Yi Chen, Yanjun Science and Technology on Electromechanical Dynamic Control Laboratory Beijing Institute of Technology Beijing China

In order to blind estimate pseudo-code (PN) code phase modulation and linear frequency modulation composited fuzecarrier frequency. By improving the traditional Duffing oscillator detection model of strong reference signal, an approximate carrier frequency blind estimation method by small-scale periodic Duffing oscillator is proposed in this paper. In this method, the internal dynamic frequency is used to approximate the changes of the output time domain and phase diagram of the chaotic system during the frequency to be measured. Then calculate the different frequency to blind estimate the carrier frequency of the signal. This method widens the range of frequency detection and can realize blind frequency estimation with less prior knowledge. The parameter estimation effect of the approximate carrier frequency estimation method based on small cycle Duffing oscillator under different signal to noise ration (SNR) is simulated and analyzed in this paper. The results show that this method has better parameter estimation performance than the traditional composited fuze frequency estimation method, especially in the environment of low SNR. © 2022 JVE International. All rights reserved.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Research on detection performance of millimeter wave fuze under rainfall condition 4

Research on detection performance of millimeter wave fuze un...

引用

4th International Conference on Defence technology, ICDT 2024

作者： Tong, Ao Zhang, Yao Pan, Liwen Pan, Xi Science and Technology on Electromechanical Dynamic Control Laboratory Beijing Institute of Technology Beijing China

Aiming at the characteristics that the performance of millimeter wave fuze is easily affected by the natural environment, this paper studies the performance of millimeter wave fuze under rainfall conditions. By analyzing the theory of rain attenuation effect and backscattering effect, it is concluded that the rain attenuation effect reduces the received power of the signal, and the backscattering effect reduces the signal to interference plus noise ratio (SINR) of the receiving end. Based on this, the signal propagation path model under rainfall conditions is established. Finally, the variation of the maximum reliable detection range with signal wavelength and rainfall rate is simulated under different SINR requirements, and the variation of signal to noise ratio (SNR) and SINR with rainfall rate is compared under different distances. The simulation results show that both the rain attenuation effect and the backscattering effect lead to the decrease of the maximum reliable detection distance of millimeter wave fuze. With the increase of rainfall rate, the detection performance of millimeter wave fuze decreases, and the detection distance decreases by about 23.2 % under extreme conditions. The rain backscattering effect on millimeter wave fuze is higher than its attenuation effect, and the influence of rain backscattering effect on millimeter wave fuze increases with the increase of detection distance. When the detection distance increases from 15 m to 30 m, the difference between SNR and SINR at the receiving end of millimeter wave fuze increases by about 3 times. This study has important reference significance for the application of millimeter wave fuze in precision guided weapons. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Fuze Intermediate Frequency Echo Simulator System 4

Design and Implementation of a Fuze Intermediate Frequency E...

引用

4th International Conference on Defence technology, ICDT 2024

作者： Guo, Yao He, Shuhuan Yu, Wenheng Pan, Xi Science and Technology on Electromechanical Dynamic Control Laboratory Beijing Institute of Technology Beijing China

The fuse echo simulator plays a crucial role in fuse testing. This paper introduces a combined hardware and software solution for a fuze intermediate frequency (IF) echo simulation system. The system utilizes Direct Digital Synthesis (DDS) technology to generate controllable IF echo *** prestoring classic target and environmental characteristic information data, the system is capable of incorporating diverse target and environmental parameters during the simulation of projectile-target encounter process, thereby enhancing the fidelity of the simulated echo signals. Experimental simulations and engineering validations have confirmed that the proposed system can accurately simulate various characteristics of echo signals, while exhibiting low temporal complexity and high real-time performance. These attributes render it effective for evaluating the dynamic performance of Frequency Modulated Continuous Wave (FMCW) fuse systems. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Calculation model for kinetic energy and rock burst risk evaluation method during roadway excavation

引用

International Journal of Mining science and technology 2025年

作者： Tan, Yunliang Tan, Yan Guo, Weiyao Li, Bo He, Shudong Zhang, Lei Zhang, Yujiang College of Energy and Mining Engineering Shandong University of Science and Technology Qingdao266590 China Shandong Key Laboratory of Intelligent Prevention and Control of Dynamic Disaster in Deep Mines Shandong University of Science and Technology Qingdao266590 China School of Civil Engineering Tongji University Shanghai200092 China China Coal Technology & Engineering Group Chongqing Research Institute Chongqing400039 China College of Coal Engineering Shanxi Datong University Datong037003 China College of Mining Engineering Taiyuan University of Technology Taiyuan030024 China

The accumulation and release of deformation energy within the rock mass of a roadway are primary contributors to the occurrence of rock bursts. This study introduces a calculation model for the kinetic energy generated during roadway excavation, which is based on the fracture and energy states of the rock mass. The relationships among the mining depth, width of the plastic zone, rebound range of the roof and floor, stress concentration factor, and the induced kinetic energy are systematically explored. Furthermore, a rock burst risk evaluation method is proposed. The findings indicate that the energy evolution of the rock mass can be categorized into four stages: energy accumulation due to in-situ stress, energy accumulation resulting from coal compression, energy dissipation through coal plastic deformation, and energy consumption due to coal failure. The energy release from the rock mass is influenced by several factors, including mining depth, stress concentration factor, the width of the plastic zone, and the rebound range of the roof and floor. Within the plastic zone of coal, the energy released per unit volume of coal and the induced kinetic energy exhibit a nonlinear increase with mining depth and stress concentration factor, while they decrease linearly as the width of the plastic zone increases. Similarly, the driving energy per unit volume of the roof and floor shows a nonlinear increase with mining depth and stress concentration factor, a linear increase with the rebound range of the roof and floor, and a linear decrease with the width of the plastic zone. A rock burst risk evaluation method is developed based on the kinetic energy model. Field observations demonstrate that this method aligns with the drilling cuttings rock burst risk assessment method, thereby confirming its validity. © 2025

关键词： Roofs

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Enrichment and Fidelity Preservation Learning Framework for Skeleton-based Action Recognition

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Li, Chuankun Li, Shuai Gao, Yanbo Gao, Xingyu Chen, Ping Li, Jian Li, Wanqing North University of China State Key Laboratory of Dynamic Testing Technology School of Information and Communication Engineering Taiyuan030051 China Shandong University School of Control Science and Engineering School of Software Jinan250100 China Chinese Academy of Sciences Institute of Microelectronics Beijing100029 China University of Wollongong Advanced Multimedia Research Lab WollongongNSW2522 Australia

Unsupervised skeleton-based action recognition has achieved remarkable progress recently. Existing unsupervised learning methods suffer from severe overfitting problem, and thus small networks are used, significantly reducing the representation capability. To address this problem, the overfitting mechanism behind the unsupervised learning for skeleton-based action recognition is first investigated. It is observed that skeleton is already a relatively high-level and low-dimension feature, but not in the same manifold as the features for action recognition. Simply applying the existing unsupervised learning method tends to produce features that discriminate the different samples rather than action classes, resulting in the overfitting problem. To address this problem, this paper proposes an Unsupervised spatial-temporal Feature Enrichment and Fidelity Preservation (U-FEFP) learning framework to generate rich distributed features that contain all the information of a skeleton sample. A spatial-temporal feature transformation subnetwork is developed using channel-wise topology refinement graph convolutional block and graph convolutional gated recurrent unit block as the basic feature extraction network. The unsupervised Bootstrap Your Own Latent-based learning is utilized to generate rich distributed features, and the unsupervised pretext task-based learning is employed to preserve the information contained in the skeleton. The two unsupervised learning ways are collaborated as U-FEFP to produce robust and discriminative representations. Experimental results on four widely used benchmarks, namely NTU-RGB+D-60, PKU-MMD, NTU-RGB+D-120 and UAV-Human dataset, demonstrate that the proposed U-FEFP obtains the best result compared with the state-of-the-art unsupervised learning methods. © 1991-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Design on Silicon-Based Millimeter-Wave Low Noise Amplifier Circuits 7

A Design on Silicon-Based Millimeter-Wave Low Noise Amplifie...

引用

7th IEEE International Conference on Electronic Information and Communication technology, ICEICT 2024

作者： Xing, Zikang Liang, Qiuyan Xu, Rui Science and Technology on Electromechanical Dynamic Control Laboratory China Xi'an Institute of Electromechanical Information Technology Xi'an710065 China

ISBN: (纸本)9798350384437

This paper investigates the technology of silicon-based millimeter-wave low noise amplifiers (LNA). The LNA consist of two stages of amplifiers connected in cascade. The first stage circuit achieves low noise performance by utilizing minimum noise input matching. The second stage achieves high gain performance by utilizing high gain output matching.. The LNA in this paper achieves a gain S21 of 16 dB at a center frequency of 36 GHz with a noise figure (NF) as small as 5 dB. © 2024 IEEE.

关键词： Low noise amplifiers

来源：评论

学校读者我要写书评

暂无评论

Flexible piezoelectric wind energy generator

Flexible piezoelectric wind energy generator

引用

2015 4th International Conference on Computer, Mechatronics, control and Electronic Engineering (ICCMCEE 2015)

作者： Wang Pengyingkai Sui Li Liu Guohua Shi Gengchen Science and technology on Electromechanical Dynamic Control Laboratory Beijing Institute of Technology

ISBN: (纸本)9781510813465

This paper proposes the scheme of a flexible piezoelectric generator. The generator using direct piezoelectricity of PVDF, can covert wind power to charge output. It possesses such advantages as: light, small-sized and better flexibility. Using FEA method, this paper carries out modal analysis and harmonic response analysis for the generator. From the modal analysis results, we get the generator's the first for modal are 6.95 Hz, 43.51 Hz, 76.06 Hz and 122.84 Hz. From harmonic response analysis results, we get the amplitude-frequency characteristic curve of the generator's output voltage, and the results show that the generator will generate higher voltage when it vibration in second-order than first –order. In order to verify the accuracy of simulation, a series experiments are carried out. Simulation and experiment on the generator proved the reliability in the wind and shows the excellent quality of generating electric energy.

关键词： Piezoelectric generator Wind Flexible FEA method

来源：评论

学校读者我要写书评

暂无评论

Joint radar and communication based on piece-wised LFM signals 4

Joint radar and communication based on piece-wised LFM signa...

引用

4th International Conference on Defence technology, ICDT 2024

作者： Wang, Xin Duu, Yingsen Zhang, Xiang Wu, Dan Zhang, Ke Xi'an Institute of Electromechanical Information Technology Xi'an China Science and Technology on Electromechanical Dynamic Control Laboratory Xi'an China

Existing joint radar detection and communication(JDC] systems suffer from high peak-to-average power ratiofPAPR] or distance blind spot zones. In this paper, we present a novel JDC system based on piece-wised linear frequency modulation(LFM] signals. Based on the proposed piece-wised LFM modulation signal, the novel JDC system can achieve linear frequency modulation continuous wave(LFMCW) detection, and the PAPR and blind zone issues are solved. Besides, spread spectrum communication can be simultaneously conducted with the same modulation signal. Simulation results show that the proposed JDC system has similar detection performance to the traditional sawtooth LFMCW detection scheme, and the bit-error rate of communication is less than 10~6 when the the bit rate is 500kbps and the signal-to-noise ratio is 10 dB. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Object Detection Based on Digital Twin-Based Road Scenarios 2

Object Detection Based on Digital Twin-Based Road Scenarios

引用

2nd IEEE International Conference on control, Electronics and Computer technology, ICCECT 2024

作者： Yu, Zhang Huimin, Chen Weihan, Wang Beijing Institute of Technology Science and Technology on Electromechanical Dynamic Control Laboratory Beijing100081 China

ISBN: (纸本)9798350380958

With the rapid development of artificial intelligence and digital technology, digital twins are becoming more and more widely used in various fields, and have high application value in industrial production, architectural design and other fields. There are few datasets of extreme scenarios used in traditional object detection and vehicle autonomous driving training, resulting in unsatisfactory results of object detection and autonomous driving technology in complex environments. In this paper, a digital twin model of the road scene is built based on the rules of City Engine and the Unreal Engine 4 platform, which can be used to build a model of complex road scenes and shorten the model construction cycle. Based on the constructed digital twin model, the target detection task is carried out, and it is verified that the target detection and autonomous driving tests can be carried out in the digital twin model. It provides ideas for solving the problem of insufficient testing of autonomous driving and object detection tasks in complex and extreme scenarios. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：