检索结果-内蒙古大学图书馆

2023 China automation Congress, CAC 2023

作者： Dong, Sun Yihan, Liu Han, Yan Xiaochao, Liu Pengyuan, Qi School of Automation Science and Electrical Engineering Beihang University Beijing China Beijing Institute of Control Engineering National Key Laboratory of Space Intelligent Control Beijing100094 China Beijing Sun Wise Space Technology Ltd. Beijing100190 China Research Institute for Frontier Science Beihang University Beijing China

ISBN: (纸本)9798350303759

In the era of global personal communication and the rapid progress of small satellite technology, low-orbit constellations have emerged as a focal point for countries worldwide. These constellations, primarily employed for communication purposes, offer advantages such as enhanced signal strength and shorter revisit cycles due to their proximity to the Earth's surface. However, the high deployment cost associated with the large number of satellites in low-orbit constellations poses a significant challenge. As launch costs continue to decline and the number of satellites in constellations increases, there is a growing interest in leveraging these constellations during times of war or sudden disasters in specific regions. This entails designing communication-enhanced constellations tailored to the targeted area and formulating an active configuration evolution plan that facilitates seamless transition from the existing constellation to the desired configuration. The objective of this paper is to propose a scheme for optimizing constellation parameters to enhance communication capabilities within a specific region. Additionally, an active configuration evolution scheme with minimal fuel consumption is introduced to effectively address emergency scenarios. © 2023 IEEE.

关键词： Orbits

来源：评论

学校读者我要写书评

暂无评论

Time-Constrained Cooperative Guidance Based on Deep Neural Network 42

Time-Constrained Cooperative Guidance Based on Deep Neural N...

引用

42nd Chinese control Conference, CCC 2023

作者： Wang, Changhai Yu, Jianglong Dong, Xiwang Li, Qingdong Ren, Zhang Wang, Feifei Hu, Xijing School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Beijing Institute of Control and Electronic Technology Beijing100038 China

ISBN: (纸本)9789887581543

Time-constrained cooperative guidance based on deep neural network (DNN) is developed to address the problem of cooperative guidance of multiple missiles against maneuvering targets. Firstly, deep neural network is applied to estimate time-to-go. A simplified dataset is created to improve the estimation effect and the performance of training results is good. Secondly, time-constrained cooperative guidance law is designed. Time-constrained guidance (TCG) law based on variable navigation ratio is proposed and an optimal method of cooperative time is designed. Thirdly, simulation in 3-D space and equivalent experiment in 2-D space are carried out to verify the performance of guidance law. An equivalent experiment platform based on multiple unmanned ground vehicles (Multi-UGVs) is erected and the experiment to achieve cooperative guidance is carried out. © 2023 Technical Committee on control Theory, Chinese Association of automation.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Influence of Active Filter on the Unstable Resonance for Traction Power Supply System 16th

Analysis of the Influence of Active Filter on the Unstable R...

引用

16th Annual Conference of China Electrotechnical Society, CES 2021

作者： Niu, Chen Wang, Guo School of Automation and Electrical Engineering Lanzhou Jiaotong University Gansu Lanzhou730070 China Key Laboratory of Opto-Technology and Intelligent Control Ministry of Education Lanzhou Jiaotong University Lanzhou730070 China Rail Transit Electrical Automation Engineering Laboratory of Gansu Province Lanzhou China

ISBN: (纸本)9789811915277

This paper analyzes the influence law of resonance of traction power supply system. First, establish a unified impedance model of the traction power supply system with a source filter in the dq coordinate system;secondly, use the Nyquist criterion to analyze the influence of the parameters of the active filter on the resonance stability of the traction power supply system;Finally, a time-domain simulation model is constructed for verification. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Resonance

来源：评论

学校读者我要写书评

暂无评论

Short-term Wind Power Probabilistic Forecasting Based on Attention Mechanism and Bidirectional LSTM

Short-term Wind Power Probabilistic Forecasting Based on Att...

引用

2023 International Conference on Smart electrical Grid and Renewable Energy, SEGRE 2023

作者： Wang, Naixiao Cai, Xinlei Xu, Zhuofan Guo, Yufeng Zhang, Tingxiang China Southern Power Grid Company Limited Electric Power Dispatching and Control Center of Guangdong Power Grid Co Guangzhou China Harbin Institute of Technology School of Electrical Engineering and Automation Harbin China

ISBN: (纸本)9798350323269

In order to quantify the uncertainty of regional wind power generation, this paper proposes a probabilistic forecasting method of wind power based on attention mechanism and bidirectional long short-term memory (Bi-LSTM). First, data cleaning is performed on the historical wind power data, and a feature set for prediction model training is constructed. Then, to make the prediction model selectively focus on the information with strong correlation, while ignoring the information with weak correlation, an attention mechanism is introduced to capture the dependencies and relationships between different parts of the input. Afterwards, a Bi-LSTM is used to construct the forecasting model, which realized the long-term memory of the power sequence effectively reduces the occurrence of falling into local optimum. Finally, the currently generated deterministic forecasts are compared with past forecasts, the most similar past forecasts are selected, and the corresponding observations are used to generate probabilistic forecasts. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Self-Tuning Neural Network controller Based on Fuzzy Logic for Multiple Positions Tracking of a Pneumatic Driven Soft Endoscope Actuator

Self-Tuning Neural Network Controller Based on Fuzzy Logic f...

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Renzo Acosta Julio Tafur Ruth Canahuire Enginnering Department Control and Automation Engineering Master Degree Program Pontificia Universidad Catolica del Peru Lima Peru Department of Electrical and Mechatronics Engineering Universidad de Ingenieria y Tecnologia - UTEC Lima Peru

ISBN: (数字)9798350394245

ISBN: (纸本)9798350394252

This paper presents the dynamic modelling and end effector position control of a soft endoscope. Soft endoscope system under study consists mainly of a pneumatic driven soft actuator (PDSA) with four independently chambers. Recurrent neural network (RNN) and dynamic back propagation (DBP) training algorithm are used to obtain PDSA dynamic model. PDSA position controller is based on a feedforward neural network (FNN) and it is trained using PDSA closed loop system (CLS) and DBP training algorithm. CLS stability analysis concludes that it is not possible control PDSA end effector position using one position controller for different end effector initial and desired positions. Fuzzy logic methodology is used to integrate several positions controllers in a one controller valid for all operation range. The controller implementation and close loop system simulation are performed in MATLAB for different end effector desired position to validate system performance in all range of operation.

关键词： Training Fuzzy logic Backpropagation Recurrent neural networks Endoscopes Heuristic algorithms Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Improved ICP for 3D Reconstruction of Lightning Arrester 5

Research on Improved ICP for 3D Reconstruction of Lightning ...

引用

5th International Conference on Robotics, Intelligent control and Artificial Intelligence, RICAI 2023

作者： Lu, Senjian Hou, Beiping Zhang, Qinlong Zheng, Yangbin Shao, Fangkun Ge, Shihao Zhu, Wen School of Automation and Electrical Engineering Zhejiang University of Science and Technology Hangzhou310023 China Zhejiang Intl. Science and Technology Cooperation Base of Intelligent Robot Sensing and Control China Technology 310023 China

ISBN: (纸本)9798350357950

The lightning arrester is an electrical device used to prevent damage to the insulation of electrical equipment caused by over voltages, including lightning and switching impulses. Creepage distance, umbrella distance, and diameter are crucial parameters for lightning arrester protection. However, traditional manual detection methods are laborious and cumbersome. Moreover, due to the highly symmetrical structure of the lighting arrester itself, the traditional methods have difficulties such as easy reverse registration, etc. This paper proposes an approach for obtaining multi-angle point cloud maps by using robotic arm and depth camera, and a quadratic point cloud registration algorithm is presented, it incorporates both the FGR (fast global registration) registration and improved ICP (Iterative Closest Point) registration algorithms. Specifically, the FGR registration algorithm is initially employed for the approximate registration of two point-cloud, and then The KICP (ICP uses KDTREE to accelerate the ICP algorithm) is used for fine registration. The experimental results demonstrate that the average registration time is 60% faster than traditional method with high registration accuracy. Therefore, this method has good Real time performance and robustness for reconstructing lightning arrester. © 2023 IEEE.

关键词： improved ICP lightning arrester three-dimensional reconstruction

来源：评论

学校读者我要写书评

暂无评论

A New Automatic User Calibration Algorithm for Three-Dimensional Gaze Estimation

A New Automatic User Calibration Algorithm for Three-Dimensi...

引用

2022 International Conference on Machine Learning and Knowledge engineering, MLKE 2022

作者： Sun, Hang Chi, Jiannan Ustb School of Automation and Electrical Engineering Beijing China Shunde Graduate School Ustb Foshan China Engineering Research Center of Intelligence Perception and Autonomous Control Ministry of Education Beijing China

ISBN: (纸本)9781665495677

Gaze estimation systems use subject-specific parameters to estimate the user's gaze direction. Advanced remote gaze estimation systems obtain the parameters including the angles between the visual axis and the optical axes of each eye through the automatic calibration algorithms. In these automatic calibration algorithms, the coordinates of the observation surface should be known when calculating the angles between the visual axis and optical axis. However, in head-mounted systems, the coordinates of the observation surface cannot be determined. This paper proposes a new automatic calibration algorithm that does not require the coordinates of the observation surface and subject' active participation in calibration. In order to estimate the angles between the visual and optical axes of each eye, differential evolution algorithms are used to minimize the distance between the visual axes of the left and right eyes while subjects naturally look at the point of gaze (PoG). Simulation results have demonstrated the effectiveness of the algorithm. © 2022 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Online compensation of acceleration on error while drilling based on MICOA

引用

Journal of Electronic Measurement and Instrumentation 2025年第1期39卷 187-194页

作者： Yang, Jinxian He, Ziwei School of Electrical Engineering and Automation Henan Polytechnic University Jiaozuo454003 China Henan Key Laboratory of Intelligent Detection and Control of Coal Mine Equipment Jiaozuo454003 China

To improve the measurement accuracy of the downhole accelerometer, a method for online compensation of accelerometer errors based on a magnetic-inertial coati optimization algorithm is designed. Firstly, an error compensation model is established based on the sources of error;the constraint conditions of the gravity angle and the magnetic-gravity angle are established using a gyroscope and a magnetometer;the difference between the true value of the acceleration and the modulus of the theoretical value is set as the objective function. Secondly, based on the coati optimization algorithm, the initial search boundary for error parameters is determined according to the recursive gravity acceleration, and the boundary is narrowed based on the relative distance among the current error parameters, the optimal error parameters, and the boundary values;a boundary point selection is designed to screen the initial error parameters, enabling the algorithm to initially search in the direction of high-quality solutions while retaining some inferior solutions to increase the diversity of error parameters;in the global exploration stage of the algorithm, parameters are designed to adjust the search range of accelerometer error parameters based on the error between the current error parameters and the average error parameters. Finally, the ratio of the modulus of gravity is set as the threshold for deep development, and a Gaussian mutation vector is constructed to enable the accelerometer error parameters to break out of local optima. Experimental results show that after MICOA compensation, the accelerometer error decreases, and the range of inclination angle decreases by approximately 62. 5%;at different drilling angles, the root mean square error and standard deviation of the inclination angle can be maintained below 1°. © 2025 Editorial Office of EMI Journal. All rights reserved.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

A General Method for Optimal Decentralized control with Current State/Output Feedback Strategy

arXiv

引用

arXiv 2024年

作者： Li, Hongdan Sun, Yawen Zhang, Huanshui College of Electrical Engineering and Automation Shandong University of Science and Technology Shandong Qingdao266590 China The College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao266590 China The School of Control Science and Engineering Shandong University Shandong Jinan250061 China

This paper explores the decentralized control of linear deterministic systems in which different controllers operate based on distinct state information, and extends the findings to the output feedback scenario. Assuming the controllers have a linear state feedback structure, we derive the expression for the controller gain matrices using the matrix maximum principle. This results in an implicit expression that couples the gain matrices with the state. By reformulating the backward Riccati equation as a forward equation, we overcome the coupling between the backward Riccati equation and the forward state equation. Additionally, we employ a gradient descent algorithm to find the solution to the implicit equation. This approach is validated through simulation examples. © 2024, CC BY.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

Distributed formation-aggregation control algorithm for a cluster of quadrotors

引用

Journal of the Franklin Institute 2023年第3期360卷 1560-1581页

作者： Sun, Yongbin Li, Jiayi Wang, Zixuan He, Xiuyu Fu, Qiang Zou, Yao School of Automation Science and Electrical Engineering Beihang University Beijing100191 China School of Intelligence Science and Technology University of Science and Technology Beijing Beijing100083 China Key Laboratory of Perception and Control of Intelligent Bionic Unmanned Systems Ministry of Education University of Science and Technology Beijing Beijing100083 China

This paper focuses on the solution to a formation-aggregation problem concerned with a cluster of quadrotors. In particular, all the quadrotors are steered towards a target region while reaching an expected formation configuration. However, only a subset of quadrotors, treated as leaders, have access to the projections onto the target region;and in the meantime, each quadrotor just exchanges information with its neighbors. It is assumed that the quadrotors without the knowledge of the target region, treated as followers, are within the convex hull of the leaders in the expected configuration. A distributed formation-aggregation control algorithm is proposed under the hierarchical framework. To be specific, resorting to an auxiliary dynamic system with a distributed idea, a command force is first synthesized in the position loop for the concerned formation-aggregation objective. Next, an applied thrust and a command attitude are extracted from the synthesized command force. Finally, an applied torque is synthesized in the attitude loop such that the attitude tracking to the command one is realized. In terms of the Lyapunov theory, it is shown that the leaders are capable of guiding the overall quadrotor cluster into the target region in the expected configuration. Simulations are carried out to validate the theoretical results. © 2022 The Franklin Institute

关键词： Computer networks

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：