检索结果-内蒙古大学图书馆

Reinforcement learning-based distributed cooperative sliding mode control for unmanned surface vehicles

Neural Computing and Applications 2024年 1-10页

作者： Zhang, Guangchen Gao, Han Yang, Xiaofei Hu, Jiabao He, Shuping School of Mathematics and Information science North Minzu University Wenchang Ningxia Yinchuan750021 China School of Automation Beijing Institute of Technology Beijing Beijing100081 China School of Automation Jiangsu University of Science and Technology Jiangsu Zhenjiang212114 China School of Automation Anhui University Anhui Hefei230601 China School of Electronic Information and Electrical Engineering Chengdu University Sichuan Chengdu610106 China

The complex marine environment poses a huge challenge to the ocean operations of unmanned surface vehicles (USVs). In this article, we will utilize sliding mode control theory and reinforcement learning (RL) method to consider collaborative control problem for USVs during the ocean operations. Firstly, by using the Kronecker product property, the USVs are further rewritten as an equivalent extended dimensional system, which can be implemented by the distributed control operations. For this extended dimensional system, we formulate the controller with sliding mode gain and reinforcement learning update rate. On this basis, we solve the collaborative control problem for USVs, and then, the corresponding algebraic criteria are also formulated in detail. Subsequently, the reachability is demonstrated for the designed sliding surface. To ends of the paper, an USV numerical example is given to verify the effectiveness of the collaborative control method and algorithm design proposed in this article. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Nyström kernel algorithm based on least logarithmic hyperbolic cosine loss

引用

Journal of Electronic Science and technology 2023年第3期21卷 82-93页

作者： Shen-Jie Tang Yu Tang Xi-Feng Li Bo Liu Dong-Jie Bi Guo Yi Xue-Peng Zheng Li-Biao Peng Yong-Le Xie School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu611731China Shanghai Spaceflight Precision Machinery Institute Shanghai201600China

Kernel adaptive filters(KAFs)have sparked substantial attraction for online non-linear learning *** is noted that the effectiveness of KAFs is highly reliant on a rational learning *** this,the logarithmic hyperbolic cosine(lncosh)criterion with better robustness and convergence has drawn attention in recent ***,existing lncosh loss-based KAFs use the stochastic gradient descent(SGD)for optimization,which lack a trade-off between the convergence speed and *** recursion-based KAFs can provide more effective filtering ***,a Nyström method-based robust sparse kernel recursive least lncosh loss algorithm is derived in this *** via measures and synthetic data against the non-Gaussian noise confirm the superiority with regard to the robustness,accuracy performance,and computational cost.

关键词： Kernel adaptive filter(KAF) logarithmic hyperbolic cosine (lncosh)loss Nyström method Recursive

来源：评论

学校读者我要写书评

暂无评论

FIR FILTER BASED VOLTAGE-CURRENT PHAS CALIBRATION METHOD FOR POWER ANALYSERS 10

FIR FILTER BASED VOLTAGE-CURRENT PHAS CALIBRATION METHOD FOR...

引用

10th International Symposium on Test automation and Instrumentation, ISTAI 2024

作者： Zhao, Jia Shi, Wei Ren, Wei School of Health and Intelligent Engineering Chengdu Medical College of China Chengdu China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781837242672

Aiming at the difficult problem of low sampling rate of high-resolution ADC in power analysis, this paper proposes a real-time voltage and current phase correction method based on an FIR digital filter. The homologous clock technique is used to achieve multi-channel data acquisition synchronization. The combination of integer and fractional parts in a high precision phase correction approach is discussed. The FIR digital filter is implemented in FPGA using the serial-parallel combination technique. Additionally, the FIR filter only uses 4*18 KB of RAM and 4 DSP 48E1 IP cores to implement real-time filter calculation on the FPGA. Experiments demonstrate that the proposed method can achieve 1.95 ns step and a correction index of-512.5 us to +512.5 us when the sampling rate is 2 MSa/s. Good real-time performance and sparse resource usage are the main attributes of the proposed approach. The proposed method is used to get good phase correction results on a power analyzer with 2 MSa/s and 18 bits. © The Institution of engineering & technology 2024.

关键词： FIR filters

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Control Method for Nonlinear Characteristics of Variable Frequency Regulation for Wide-Distance-Range Adaptive WPT System

引用

IEEE Transactions on Power Electronics 2025年第7期40卷 10221-10241页

作者： Xia, Ziyi Dai, Xin Li, Yanling Wang, Liuping Chen, Fengwei Ma, Jun Chongqing University College of Automation Chongqing400044 China Xihua University School of Electrical Engineering and Electronic Information Chengdu610039 China Royal Melbourne Institute of Technology School of Engineering MelbourneVIC3000 Australia

In the realm of output control for wireless power transfer (WPT) systems, variable frequency (VF) regulation of the transmitter inverter stands out as a leading and sophisticated research direction, as it facilitates the adjustment of the voltage conversion ratio and holds significant promise for long-distance power transfer applications. However, the VF regulation process in WPT systems is characterized by strong nonlinearity and is highly sensitive to variations in the inverter driving frequency. In addition, increasing transfer distances exacerbate these nonlinearities due to changing mutual inductances. Consequently, traditional approaches to VF regulation are constrained by a limited operating range, which impedes the application of WPT technology in scenarios involving varying distances. To address these challenges and enhance the system's adaptability to different power transmission distances while managing multiparametric uncertainties in WPT systems, this article develops a data-driven model-free adaptive control (MFAC) method. Initially, an online modeling approach utilizing dynamic linearization is proposed to characterize the VF regulation process using solely system input-output data. Subsequently, a switched control strategy based on the estimated data model is devised to calculate the optimal operating frequency for the WPT system. Finally, a prototype with maximum output of 3.88 kW is constructed to demonstrate the feasibility of the proposed approach. The results indicate that the data-driven control system exhibits a robust dynamic response and strong resilience across varying transfer distances ranging from 5 to 65 cm, corresponding to a distance-diameter ratio of 0.125-1.625. © 1986-2012 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Efficient OpenMP Based Z-curve Encoding and Decoding Algorithms

引用

Computers, Materials & Continua 2025年第1期82卷 1313-1327页

作者： Zicheng Zhou Shaowen Sun Teng Liang Mengjuan Li Fengling Xia School of Electronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650500China School of Communications Information Engineering Yunnan Communications Vocational and Technical CollegeKunming650500China Library Yunnan Normal UniversityKunming650500China Faculty of Civil Aviation and Aeronautics Kunming University of Science and TechnologyKunming650500China

Z-curve’s encoding and decoding algorithms are primely important in many Z-curve-based *** bit interleaving algorithm is the current state-of-the-art algorithm for encoding and decoding *** simple,its efficiency is hindered by the step-by-step coordinate shifting and bitwise *** tackle this problem,we first propose the efficient encoding algorithm LTFe and the corresponding decoding algorithm LTFd,which adopt two optimization methods to boost the algorithm’s efficiency:1)we design efficient lookup tables(LT)that convert encoding and decoding operations into table-lookup operations;2)we design a bit detection mechanism that skips partial order of a coordinate or a Z-value with consecutive 0s in the front,avoiding unnecessary iterative *** propose order-parallel and point-parallel OpenMP-based algorithms to exploit the modern multi-core *** results on discrete,skewed,and real datasets indicate that our point-parallel algorithms can be up to 12.6×faster than the existing algorithms.

关键词： Z-curve lookup table OpenMP bit detection mechanism

来源：评论

学校读者我要写书评

暂无评论

Numerical Investigation on Transient Bounce Arc and Anode Surface Temperature 7

Numerical Investigation on Transient Bounce Arc and Anode Su...

引用

7th International Conference on Electric Power Equipment - Switching technology, ICEPE-ST 2024

作者： Chen, Shuang Yang, Ze Shi, Zongqian Wang, Lijun Sun, Jiajia School of Electronic Information and Electrical Engineering Chengdu University Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China Xi'an Jiaotong University State Key Laboratory of Electrical Insulation and Power Equipment Xi'an China

ISBN: (纸本)9798350388947

In this research, the closing arc and the bouncing arc are studied with transient MHD model. A transient self-consistent model is established using the dynamic meshing technology. The simulation results show that the ion density decreases significantly with the expansion of the arc column. As a result, the energy flux from the arc to the anode center decreases gradually as a power function. Since the energy flux is very high at the arc ignition, the anode temperature increases significantly at first. Then the maximum anode temperature begins to fall due to the decrease of the maximum energy flux. © 2024 IEEE.

关键词： Electromagnetic transients

来源：评论

学校读者我要写书评

暂无评论

Dynamic Target Enclosing Control Scheme for Multi-Agent Systems via a Signed Graph-Based Approach

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 560-562页

作者： Weihao Li Kaiyu Qin Mengji Shi Jingliang Shao Boxian Lin the School of Aeronautics and Astronautics University of Electronic Science and Technology of ChinaChengdu 611731 the Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu 611731China the School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

Dear Editor,This letter investigates the target enclosing control problem of multi-agent systems.A signed graph-based control strategy is presented,where the agents are steered to enclose the dynamic target from both sides as they *** is inspired by the phenomenon that signed networks exhibit bipartite clustering if the underlying graph is structurally balanced,so that the agents may naturally enclose the zero point from opposite sides(+and.)if proper controllers are *** adopting a distributed observer to estimate the information of dynamic target。

关键词： networks agent Dynamic

来源：评论

学校读者我要写书评

暂无评论

Mobile-YOLO-SDD: A Lightweight YOLO for Real-time Steel Defect Detection 18

Mobile-YOLO-SDD: A Lightweight YOLO for Real-time Steel Defe...

引用

18th CIRP Conference on Computer Aided Tolerancing, CAT 2024

作者： Luo, Shen Xu, Yuanping Zhu, Ming Zhang, Chaolong Kong, Chao Jin, Jin Li, Tukun Jiang, Xiangqian Guo, Benjun School of Software Engineering Chengdu University of Information Technology Chengdu China School of Automation Chengdu University of Information Technology Chengdu China School of Computing and Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom

Defect detection is essential in the steel production process. Recent years have seen significant advancements in steel surface defect detection based on deep learning methods, notably exemplified by the YOLO series models capable of precise and rapid detection. However, challenges arise due to the high complexity of surface textures on steel and the low recognition rates for minor defects, making real-time and accurate detection difficult. This study introduces Mobile-YOLO-SDD (Steel Defect Detection), a lightweight YOLO-based model designed with high accuracy for real-time steel defect detection. Firstly, based on the effective YOLOv5 algorithm for steel defect detection, the backbone network is replaced with MobileNetV2 to reduce the model size and computational complexity. Then, the ECA (Efficient Channel Attention) module was integrated into the C3 module to reduce the number of parameters further while maintaining the defect detection rate in complex backgrounds. Finally, the K-Means++ algorithm regenerates anchor boxes and determines optimal sizes, enhancing their adaptability to actual targets. Experimental results on NEU-DET data demonstrate that the improved algorithm achieves a 60.6% reduction in model size, a 60.8% reduction in FLOPs, and a 1.8% improvement in mAP compared to YOLOv5s. These results confirm the effectiveness of Mobile-YOLO-SDD and lay the foundation for subsequent lightweight deployment of steel defect detection models. © 2024 The Authors. Published by Elsevier B.V.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Chip-scale Magnetic Field Sensor Based on Frequency Readout Cavity Optomechanical System

A Chip-scale Magnetic Field Sensor Based on Frequency Readou...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Li, Zhe Xian, Chengwei Kuang, Pengju Xiong, Jinglong Huang, Zihan Zhang, Senyu Wen, Guangjun Chen, Kai Huang, Yongjun University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China University of Electronic Science and Technology of China School of Information and Communication Engineering Sichuan Provincial Engineering Research Center of Communication Technology for Intelligent IoT Chengdu611731 China Chengdu Technological University School of Electronic Engineering Chengdu611730 China

ISBN: (纸本)9798350375909

In this paper, the working principle of cavity optomechanical system is analyzed, and a new chip-scale magnetic field sensor based on frequency readout cavity optomechanical system is proposed. The relationship between the magnetic field and displacement of the mechanical part of the new chip-scale magnetic field sensor is verified, the structure and parameters of the new chip-scale magnetic field sensor are simulated and designed, the optical characteristics of two-dimensional photonic crystal microcavity are simulated and analyzed, and the mechanical resonant frequency of the cavity affected by the displacement and the input laser wavelength and intensity is demonstrated. Then, the whole magnetic field sensor is simulated and analyzed. The results show that when the input laser intensity is 199μW, the sensitivity is 7.9Hz/μT. The new chip-scale magnetic field sensor simulated in this paper has important application value in the fields of navigation, positioning, magnetic imaging, medical imaging and environmental monitoring. © 2024 IEEE.

关键词： Microcavities

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of High-precision Frame-type Optomechanical Gyroscope

Design and Analysis of High-precision Frame-type Optomechani...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Xian, Chengwei Kuang, Pengju Huang, Zihan Zhang, Senyu Li, Zhe Wen, Guangjun Huang, Yongjun University of Electronic Science and Technology of China School of Information and Communication Engineering Sichuan Provincial Engineering Research Center of Communication Technology for Intelligent IoT Chengdu611731 China Chengdu Technological University School of Electronic Engineering Chengdu611730 China University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China

ISBN: (纸本)9798350375909

In this paper, a new structure of high precision frame-type optomechanical gyroscope is proposed. Based on the basic theory of photonic crystal cavity optomechanical system, the working mechanism of the new high precision micro gyroscope is analyzed. Through the simulation optimization and numerical calculation of the mechanical structure and optical structure of the gyroscope, the theoretical measurement sensitivity of angular velocity is 261.9mV/(°/s), and the rate noise density is 0.011(°/s)/Hz1/2. Based on the micro-nano fabrication process, the sample of the cavity optomechanical gyroscope chip was fabricated on SOI, and the preliminary test of the gyroscope chip was carried out on the vacuum test platform. With the same magnitude of inertia mass, the precision of this new micro gyroscope is obviously better than that of the traditional microelectromechanical system (MEMS) gyroscope, which provides a new path for realizing a high-precision, easy-to-integrate-on-chip, and strongly anti-electromagnetic interference gyroscope, and has great potential application value in high precision inertial navigation, micro vibration detection and other technical fields. © 2024 IEEE.

关键词： Gyroscopes

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：