检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yongjin Yuan Zheng Wang Feiping Nie Xuelong Li School of Computer Science Northwestern Polytechnical University Xi’an P.R. China School of Artificial Intelligence OPtics and ElectroNics(iOPEN) Northwestern Polytechnical University Xi’an P.R. China Key Laboratory of Intelligent Interaction and Applications (Northwestern Polytechnical University) Ministry of Industry and Information Technology Xi’an P. R. China Science and Technology on Electromechanical Dynamic Control Laboratory China

At data mining field, it is a fundamental problem to dispose of high-dimensional data. Many existing unsupervised methods select features by manifold learning or exploring spectral analysis, thus preserving the intrinsic structure of raw data. But most of them follow an assumption that all features are equally importance. To settle this problem, we draw a novel feature selection module that simultaneously performs learning of feature weights matrix, similarity graph structure and projection matrix, so that the local structure after feature weighting and subspace sparse projection is received. Finally, we solve the model based on ℓ 2,0 -norm directly by an iterative optimization algorithm and demonstrate the feasibility and effectiveness of our approach via extensive experiments.

关键词： Signal processing algorithms Signal processing Feature extraction Iterative algorithms Entropy Manifold learning Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

Fuze Echo Recognition Based on Improved V-G Convolutional Neural Network

Fuze Echo Recognition Based on Improved V-G Convolutional Ne...

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Dengdian Huang Bo Tian Tie Li Yali Hou Science and Technology on Electromechanical Dyamic Control Laboratory XityCountry

ISBN: (纸本)9781665418133

In order to solve the problem that it is difficult for the traditional fuse target recognition algorithm to recognize the object with the same size as the target under the condition of ground object coupling and low signal-to-noise ratio, the V-G convolution neural network is used for Fuse echo The improved V-G convolution neural network is used in this method, and the data of laser and radio fuse missile target rendezvous is used as The improved V-G convolution neural network is used in this method, and the data of laser and radio fuse missile target rendezvous is used as the training library to identify the targets outside the library and classify the targets inside the library. The simulation results show that the recognition accuracy is more than 95%, and the fuse echo recognition can be carried out efficiently.

关键词： Training Missiles Fuses Target recognition Convolution Neural networks Lasers

来源：评论

学校读者我要写书评

暂无评论

Design of dual band millimeter wave beam shaped array antenna

Design of dual band millimeter wave beam shaped array antenn...

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Rui-hu Wen Wei Chen Xue-qi Cao Jing-ya Wang Lan-jie Niu Meng-xin Ma Science and Technology on Electromechanical Dynamic Control Laboratory Xi'anChina710065 Xi'an Institute of Electromechanical Information Technology Xi'an China Shaanxi Applied Physics and Chemistry Rescarch Insittute Xi'an China

ISBN: (纸本)9781665418133

Aiming at the requirement of dual-channel dual-band millimeter wave for high-frequency radio fuze determination, a miniaturized dual-band microstrip beam-shaped array antenna which consists of six patch radiation units and microstrip feed network is designed. Independent adjustment of the two working frequency bands can be achieved by adjusting the size of the patch and the length of the slot.

关键词： Technical requirements Microstrip antenna arrays Antenna theory Surface waves Shape Dielectric substrates Dual band

来源：评论

学校读者我要写书评

暂无评论

GPIO Based Iterative Learning control for Manipulators with Time-Varying Disturbances

GPIO Based Iterative Learning Control for Manipulators with ...

引用

第42届中国控制会议

作者： Huangyuwei Lu Zuo Wang Jiankun Sun Xi Xiao Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex systems of Engineering Ministry of Education Shenzhen Research Institute Southeast University School of Artificial Intelligence and Automation Huazhong University of Science and Technology Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration

To improve the disturbance rejection ability and repetitive tracking accuracy of manipulators,a composite iterative learning control(ILC) scheme via generalized proportional integral observer(GPIO) is proposed.A high-order polynomial is first employed to model the time-varying disturbances that include unmodeled dynamics,parameter uncertainties and load fluctuations.A GPIO is then designed to estimate the disturbances and high-order time *** introducing estimations into a PD-type ILC at each iteration,a composite control scheme is obtained,such that the undesirable influence of time-varying disturbances can be effectively attenuated in the repetitive tracking process of *** this paper,the rigorous stability analysis of the closed-loop system is presented to guarantee that the tracking error exponentially converges to zero as the iteration number tends to *** effectiveness of the proposed control scheme is finally verified by simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A hierarchical simulation framework incorporating full-link physical response for short-range infrared detection

引用

Defence technology 2025年

作者： Gao, Mingze Xu, Lixin Hu, Shiyuan Shi, Xiaolong Gao, Jiaming Wu, Yanjiang Chen, Huimin Science and Technology on Electromechanical Dynamic Control Laboratory Beijing Institute of Technology Beijing100081 China Tianjin Institute of Aerospace Mechanical and Electrical Equipment Tianjin300301 China

Missile-borne short-range infrared detection (SIRD) technology is commonly used in military ground target detection. In complex battlefield environments, achieving precise strike on ground target is a challenging task. However, real battlefield data is limited, and equivalent experiments are costly. Currently, there is a lack of comprehensive physical modeling and numerical simulation methods for SIRD. To this end, this study proposes a SIRD simulation framework incorporating full-link physical response, which is integrated through the radiative transfer layer, the sensor response layer, and the model-driven layer. In the radiative transfer layer, a coupled dynamic detection model is established to describe the external optical channel response of the SIRD system by combining the infrared radiation model and the geometric measurement model. In the sensor response layer, considering photoelectric conversion and signal processing, the internal signal response model of the SIRD system is established by a hybrid mode of parametric modeling and analog circuit analysis. In the model-driven layer, a co-simulation application based on a three-dimensional virtual environment is proposed to drive the full-link physical model, and a parallel ray tracing method is employed for real-time synchronous simulation. The proposed simulation framework can provide pixel-level signal output and is verified by the measured data. The evaluation results of the root mean square error (RMSE) and the Pearson correlation coefficient (PCC) show that the simulated data and the measured data achieve good consistency, and the evaluation results of the waveform eigenvalues indicate that the simulated signals exhibit low errors compared to the measured signals. The proposed simulation framework has the potential to acquire large sample datasets of SIRD under various complex battlefield environments and can provide an effective data source for SIRD application research. © 2025 China Ordnance Society

关键词： Radiative transfer

来源：评论

学校读者我要写书评

暂无评论

A Method for Reconstructing the Shape of Wing Panels Based on Fiber Optic Sensors and Tomographic Imaging Principles

A Method for Reconstructing the Shape of Wing Panels Based o...

引用

Prognostics and System Health Management Conference (PHM-Qingdao)

作者： Jun Zhan Jie Zeng Chao Xiang Jinpeng Cui Cheng Zeng Linfeng Zhu Mingyu Lu State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and Astronautics Nanjing China Aviation key laboratory of science and technology on aero electromechanical system integration Nanjing engineering institute of aircraft system jincheng AVIC Nanjing China Changping District Xiaotangshan Future Science and Technology City COMAC Beijing Aircraft Technology Research Institute Beijing China

ISBN: (数字)9798350354010

ISBN: (纸本)9798350354027

The aircraft wing structure shape reconstruction method based on discrete strain information not only provides data support for the digital collaborative health monitoring and prediction technology of wing structure but also helps to improve the aerodynamic shape and flight quality of the aircraft, achieve structural stealth, and enhance the pointing accuracy of the on-board conformal antenna. As result, a wing skin panel shape reconstruction method based on the principle of tomographic imaging and strain information perception is proposed. According to the idea of tomographic imaging, a “non-intrusive” layout form that only requires sensors to be arranged on the periphery of the monitoring area is designed, breaking through the limitation that sensors can not be arranged in the monitoring area under special working conditions. A method for constructing the deflection shape function of the wing skin panel based on the concept of synthetic curvature is proposed, solving the problem of error accumulation and elimination of deformation inversion at non-monitoring points of the measured structure caused by the uncertainty of the limited discrete layout of sensors and the choice of interpolation fitting method. On this basis, a model deformation monitoring and inversion system for wing skin panel based on fiber optic grating sensors is constructed. The experimental results show that under the single-end fixed bending and torsion working condition, the average relative error of the panel model shape reconstruction is 4.17%. Under the double-end fixed double-concentrated load working condition, the average relative error of the shape reconstruction is 8.07%. The wing deformation distribution information reconstructed by the method proposed in this paper can be mapped onto the virtual twin model of the wing, providing technical support for the safety assessment, early warning, and on-condition maintenance of the entire service life of key structures of the aircraft.

关键词： Employee welfare Shape Deformation Layout Imaging Sensors Aircraft Monitoring Image reconstruction Strain

来源：评论

学校读者我要写书评

暂无评论

Reliability-aware control of Power Converters in Mobility Applications

Reliability-aware Control of Power Converters in Mobility Ap...

引用

European control Conference (ECC)

作者： Amin Rezaeizadeh Gioele Zardini Emilio Frazzoli Silvia Mastellone Institute of Electric Power Systems University of Applied Science Northwest Switzerland Windish Switzerland Laboratory for Information and Decision Systems Massachusetts Institute of Technology Cambridge MA USA Institute for Dynamic Systems and Control ETH Zürich Switzerland

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

The large scale adoption of Battery Electric Vehicles (BEVs) is still limited by cost, reliability and lifetime considerations. The power converters of a BEVs, and more specifically the semiconductor switching devices, are the second most likely component to fail due to the damage caused by the current-induced temperature cycling. In this paper we address the active mitigation of damage in e-mobility power converters, by introducing a novel frequency-domain speed controller for the power train that reduces the thermal stress on the power electronic Insulate Gate Bipolar Transistors (IGBTs), while simultaneously ensuring effective speed tracking performance. We integrate the multi-objective problem in an $\mathcal{H}_{\infty}$ control framework, which embeds the semiconductor reliability model in the weights functions. The method is tested using standardised driving cycles in two different scenarios: reliability-aware, and performance-oriented cases. Finally a lifetime analysis of the IGBTs, in both scenarios is performed leveraging the Rainflow algorithm and temperature data.

关键词： Insulated gate bipolar transistors Degradation Temperature distribution Switches Insulation life Temperature control Reliability

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Cooperative Guidance Law with Multi-Constraint

Deep Reinforcement Learning-Based Cooperative Guidance Law w...

引用

Chinese Automation Congress (CAC)

作者： Zhihao Gao Junfang Fan Denghui Dou Yi Ji Yafeng Li Jinmin Wu Beijing Key Laboratory of High Dynamic Navigation Technology School of Automation Beijing Information Science and Technology University Beijing China Beijing Key Laboratory of UAV Autonomous Control School of Aerospace Engineering Beijing Institute of Technology Beijing Institute of Technology Beijing China School of Automation Beijing Information Science and Technology University Beijing China

To enhance the destructive capabilities of small air-to-surface missiles, it is necessary to address the challenges related to terminal attack angle constraints and multi-missile coordinated attacks, we propose a cooperative guidance law with multi-constraint based on deep reinforcement learning in this paper. Firstly, an intelligent control term is introduced into the biased proportional navigation law with angle constraints. Secondly, a reward function is designed to reduce terminal attack angle error and flight time error, ensuring that the missile successfully reaches the target within the expected flight time, while simultaneously converging the attack angle to the desired value. Finally, the deep deterministic policy gradient algorithm is employed for the purpose of training and generating intelligent guidance instructions. Simulation results substantiate the efficacy of the devised guidance method in achieving accurate target strikes, both for individual missiles and in scenarios involving multiple missiles. And exhibiting better stability and guidance accuracy compared to the traditional biased proportional navigation law.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement Learning-Based Guidance Law with Impact Angle Constraint

A Deep Reinforcement Learning-Based Guidance Law with Impact...

引用

Chinese Automation Congress (CAC)

作者： Xu Wang Junfang Fan Denghui Dou Yi Ji Yafeng Li Jinmin Wu School of Automation Beijing Information Science and Technology University Beijing Key Laboratory of High Dynamic Navigation Technology Beijing China School of Aerospace Engineering Beijing Institute of Technology Beijing Key Laboratory of UAV Autonomous Control Beijing Institute of Technology Beijing China School of Automation Beijing Information Science and Technology University Beijing China

Addressing the challenge of ineffective impact angle control when employing conventional biased proportional navigation guidance for precision-guided missiles against maneuvering targets, this study proposes a guidance law with impact angle constraint by integrating deep reinforcement learning algorithms with biased proportional navigation guidance. The algorithm enhances traditional proportional navigation guidance by introducing a target maneuver compensation bias term. This bias term is treated as an action in a learning framework and optimized using the Proximal Policy Optimization algorithm. Simulation experiments validate that the proposed algorithm, compared to conventional proportional navigation guidance, not only reduces miss distance and impact angle error but also shortens flight time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Research on Bank Card Number Recognition Based on ASFF+YOLOv7 and Multi-Scale Feature Line Fusion

A Research on Bank Card Number Recognition Based on ASFF+YOL...

引用

IEEE International Conference on Cyber technology in Automation, control, and Intelligent Systems

作者： Jiajun Cheng Yaoyan Wu Weitao Gao Jun Fu Faculty of Robot Science and Engineering Northeastern University Shenyang Liaoning China State Key Laboratory of Dynamic Testing Technology School of Electrical and Control Engineering North University of China Taiyuan Shanxi China

Electronic payments have become the primary mode of payment today, and bank card recognition is widely used in industries such as mobile, mobile banking, and third-party payments. To address issues such as low fault tolerance due to factors such as complex backgrounds, significant perspective distortion that is difficult to recover, and high illumination variation, we propose a Bank Card Number Recognition algorithm based on ASFF + YOLOv7 and Multi-Scale Feature Line Fusion. The algorithm comprises two parts: the front-end dataset generation stage introduces an efficient semi-automatic traditional bank card dataset generation algorithm, which reduces the manual annotation cost while ensuring relative accuracy and significantly improves work efficiency. In the back-end recognition stage, we have improved the traditional deep learning model for the long-tail digit string dataset, achieving a precision of 99.19% and a recall rate of 98.65%.

关键词：

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：