检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Zhong-Yi Xu, Chen-Yang Zhao, Li-Xuan Hou, Hui-Rang Meng, Qing-Hao Tianjin Key Laboratory of Process Measurement and Control Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin300072 China

Electroencephalogram (EEG) is a non-invasive tool for real-time neural monitoring, widely used in depression detection via deep learning. However, existing models primarily focus on binary classification (depression/normal), lacking granularity for severity assessment. To address this, we proposed the DepL-GCN, i.e., Depression Level classification based on GCN model. This model tackles two key challenges: (1) subjectivity in depression-level labeling due to patient self-report biases, and (2) class imbalance across severity categories. Inspired by the model learning patterns, we introduced two novel modules: the sample confidence module and the minority sample penalty module. The former leverages the L2-norm of prediction errors to progressively filter EEG samples with weak label alignment during training, thereby reducing the impact of subjectivity;the latter automatically upweights misclassified minority-class samples to address imbalance issues. After testing on two public EEG datasets, DepL-GCN achieved accuracies of 81.13% and 81.36% for multi-class severity recognition, outperforming baseline models. Ablation studies confirmed both modules’ contributions. We further discussed the strengths and limitations of regression-based models for depression-level recognition. Copyright © 2025, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Weld Defect Recognition and Detection from Video Using Deep Learning Methods

Weld Defect Recognition and Detection from Video Using Deep ...

引用

Cybernetics & Informatics (K&I)

作者： Slavomir Kajan Marek Trebul’a František Duchoň Zuzana Kovaríková Michal Kováč Jarmila Pavlovičová Institute of Robotics and Cybernetics Faculty of Electrical Engineering and Information Technology Slovak University of Technology in Bratislava Bratislava Slovakia VUEZ a.s. Levice Slovakia

ISBN: (数字)9798331541811

ISBN: (纸本)9798331541828

This paper deals with the design of method for recognizing and detecting a weld defect from video captured by robot using deep learning methods. Quality control of welds is currently handled by robotic quality control methods. One task of the robotic system is to detect a weld defect from the captured video. Our approach to weld defect recognition and detection uses convolutional neural network (CNN) and YOLO detector. We use CNN to search for areas with the potential occurrence of weld defects. The YOLO detector is used for accurate detection of weld defects. For these purposes, a dataset of weld images was created using the robot, in which the quality inspector marked defects in the welds. The Grad-CAM method was used in the paper to visualize CNN decision-making and the accuracy of the detection process was calculated.

关键词： YOLO Deep learning Visualization Accuracy Welding Data visualization Detectors Quality control Convolutional neural networks Robots

来源：评论

学校读者我要写书评

暂无评论

Compensation control of PMSMs Based on a High-order Sliding Mode Observer with Inertia Identification

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Li, Ke Ding, Jie Sun, Xiaodong Lei, Gang Dianov, Anton Demidova, Galina Prakht, Vladimir Jiangsu University School of Electrical and Information Engineering Zhenjiang212013 China Jiangsu University Automotive Engineering Research Institute Zhenjiang212013 China University of Technology Sydney School of Electrical and Data Engineering NSW2007 Australia Wenzhou University Pingyang Institute of Intelligent Manufacturing Wenzhou325035 China ITMO University Faculty of Control Systems and Robotics Petersburg197101 Russia Ural Federal University Department of Electrical Engineering Ekaterinburg620062 Russia

This article proposes a new sliding mode control (NSMC) reaching law to improve the speed tracking and anti-interference performance of permanent magnet synchronous motors (PMSMs). The NSMC improves the sliding mode control (SMC) in approaching speed and reducing chattering. Firstly, considering that the external load interference will adversely affect the control system, a high-order sliding mode observer (HOSMO) is designed to observe the load torque, and the observed value is compensated to the output of the speed controller. Then, combined with the Landau algorithm, a variable adaptive gain algorithm is introduced to decrease the impact of inertia mismatch on the system control performance. The algorithm identifies the rotational inertia online, reduces the effect of load disturbance on the identification performance, and updates the identification results to the observation in processors and controllers. Experimental results show that the proposed control method reduces the speed and current fluctuations of the system when load torque and inertia vary and improves the system's robustness. © 2013 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Distributed Prescribed-Time Observer for Nonlinear Systems in Block-Triangular Form

引用

IEEE control Systems Letters 2025年 9卷 222-227页

作者： Vincent de Heij M. Umar B. Niazi Karl H. Johansson Saeed Ahmed Jan C. Willems Center for Systems and Control and the Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen Groningen The Netherlands Division of Decision and Control Systems Digital Futures KTH Royal Institute of Technology Stockholm Sweden Department of Electrical Engineering and Computer Science Laboratory for Information and Decision Systems Massachusetts Institute of Technology Cambridge MA USA

This letter proposes a design of a distributed prescribed-time observer for nonlinear systems representable in a block-triangular observable canonical form. Using a weighted average of neighbor estimates exchanged over a strongly connected digraph, each observer estimates the system state despite the limited observability of local sensor measurements. The proposed design guarantees that distributed state estimation errors converge to zero at a user-specified convergence time, irrespective of observers’ initial conditions. To achieve this prescribed-time convergence, distributed observers implement time-varying local output injection gains that monotonically increase and approach infinity at the prescribed time. The theoretical convergence is rigorously proven and validated through numerical simulations, where some implementation issues due to increasing gains have also been clarified.

关键词： Observers Convergence Nonlinear systems Symmetric matrices Observability Directed graphs control systems Vectors Linear systems Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Extinguishing Real Fires by Fully Autonomous Multirotor UAVs in the MBZIRC 2020 Competition

Field Robotics

引用

Field robotics 2025年 2卷 406-436页

作者： Viktor Walter Vojtěch Spurný Matěj Petrlík Tomáš Báča David Žaitlík Lyubomyr Demkiv Martin Saska Department of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague http://mrs.felk.cvut.cz Robotics Group of SoftServe Inc. and with the Institute of Computer Science and Information Technologies Lviv Polytechnic National University Ukraine

In this paper, we describe a system for combating real fires with sprayed liquid extinguishing agent using a team of multirotor UAVs. The system design relies on onboard sensors and operates without the need for human intervention throughout its complex mission, from its takeoff to landing. The core UAV platform can estimate its state, self-localize, navigate and locate and extinguishing fires. Thermal and RGB cameras are used, each with a specialized computer vision subsystem and are combined with planar LIDAR for 3D localization of fires on multistory building facades. The system conducts aerial firefighting with a software stack that addresses flight dynamics and sensor limitations and a liquid-spraying subsystem incorporating a rigidly-attached water nozzle. The approach presented in this paper was motivated by the Mohamed Bin Zayed International robotics Challenge (MBZIRC 2020) firefighting scenario, which focused on coordinated multi-UAV teams that can autonomously combat high-rise building fires. The MBZIRC series places particular emphasis on fast and reliable deployment of robots in realistic conditions. These contests promote development of real-world applications that are greatly needed by society, but which still exceed State-of-the-Art in the robotics community. To our knowledge, our system was the only MBZIRC 2020 contender to extinguish a facade fire successfully in autonomous mode without using an RTK-GNSS system. Our approach contributed to victory in the overall competition and we have now adapted it into an industrial prototype for a firefighting UAV. A video attachment to this paper is available at http://***/fr2020firechallenge-facadefires.

关键词： Robots Buildings Autonomous aerial vehicles Location awareness Robot kinematics Inspection Navigation Cameras Monitoring Sensor systems

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Neural Asynchronous control of Nonhomogeneous Markov Jump Power Systems with Hybrid Cyberattacks and Unknown States

引用

IEEE Transactions on Power Systems 2025年

作者： Luo, Wende Chen, Haiyang Zong, Guangdeng Zhao, Xudong Qufu Normal University School of Engineering Rizhao276826 China Tiangong University School of Control Science and Engineering Tianjin300387 China Nanjing Institute of Technology School of Automation Nanjing211167 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian116024 China

This paper studies the observer-based eventtriggered neural asynchronous control problem of nonhomogeneous Markov jump power systems (MJPSs) under hybrid cyberattacks. Both periodic denial-of-service attacks and deception attacks (DAs) are involved because of the openness of networks. An event-triggered mechanism is established to ease the network load. Besides, neural network (NN) approaches are adopted to suppress the adverse effects of DAs on nonhomogeneous MJPSs, and the hidden Markov model (HMM) is employed to capture the asynchronous phenomenon between the system mode and the controller mode. With NN approaches and HMM, an observer-based NN asynchronous controller is designed. By constructing the mode- and parameter-dependent Lyapunov function, sufficient criteria ensuring boundedness in probability for nonhomogeneous MJPSs are obtained. Then, a design algorithm is shown to simultaneously obtain the controller gains, observer gains, and event-triggering weight matrices based on the established conditions. Finally, the single-machine infinitebus power system and 3-machine 6-bus power system are applied to justify the validity of the proposed algorithm. © 1969-2012 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Model-Free Predictive control for Harmonic Suppression of PMSMs Based on Adaptive Resonant controller

引用

IEEE Transactions on Energy Conversion 2025年

作者： Li, Teng Sun, Xiaodong Su, Zonghao Zha, Xuhao Dianov, Anton Prakht, Vladimir Demidova, Galina Ma, Jinlin Jiangsu University Automotive Engineering Research Institute Zhenjiang212013 China Wenzhou University Pingyang Institute of Intelligent Manufacturing Wenzhou325035 China Ural Federal University Department of Electrical Engineering Ekaterinburg620062 Russia ITMO University Faculty of Control Systems and Robotics Petersburg197101 Russia Jiangsu University School of Automotive and Traffic Engineering Zhenjiang212013 China

To simultaneously suppress the periodic and aperiodic disturbances experienced by permanent magnet synchronous motors in model predictive control, a model-free predictive current control with adaptive resonance control based on an ultra-local model is proposed. Firstly, the ultra-local models of the speed loop and the current loop are established respectively, and the unmodeled and uncertain unknown part F in the ultra-local model is estimated by using a high-order fast terminal sliding mode observer, and its stability is analyzed. Then, an adaptive resonant controller (ARC) is designed to suppress the periodic disturbance caused by the dead zone effect. The ARC and the model-free control based on the ultra-local model are combined to compensate for their respective shortcomings, achieving the suppression of periodic and aperiodic disturbances in the system. Finally, by comparing with the traditional duty cycle model predictive control and the model-free model predictive control without ARC, the proposed scheme is proved to be robust to periodic and aperiodic disturbances. © 2025 IEEE. All rights reserved.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Individually Demagnetized Power Converter for Switched Reluctance Motors

引用

IEEE Transactions on Transportation Electrification 2025年第3期11卷 8439-8449页

作者： Liu, Hemiao Chen, Hao Wang, Xing Gorbounov, Yassen Wheeler, Patrick Anuchin, Alecksey Demidova, Galina Korovkin, Nikolay Liudmila, Sakhno Shenzhen Research Institute China University of Mining and Technology Shenzhen515100 China School of Electrical Engineering China University of Mining and Technology Xuzhou221116 China Xinjiang Institute of Engineering Xinjiang Urumqi830000 China International Joint Research Center of Central and Eastern European Countries on New Energy Electric Vehicle Technology and Equipment Xuzhou221008 China International Cooperation Joint Laboratory of New Energy Power Generation and Electric Vehicles of Jiangsu Province Colleges and Universities Xuzhou221008 China Xuzhou Key Laboratory of New Energy Electric Vehicle Technology and Equipment Xuzhou221008 China Department of Automation Mining Production University of Mining and Geology St. Ivan Rilski Sofia1700 Bulgaria School of Electrical Engineering University of Nottingham University Park Campus Nottingham United Kingdom Moscow111250 Russia Faculty of Control Systems and Robotics Engineer Saint-Petersburg National Research University of Information Technologies Mechanics and Optics Saint Petersburg197101 Russia Institute of Energy Peter the Great Saint-Petersburg Polytechnic University Saint Petersburg195251 Russia

Switched reluctance motors (SRMs) are capable of operating at high speeds and high loads. However, the large back-EMF results in the excitation winding current being demagnetized more slowly, which in turn reduces the efficiency and output of the motor system. This study proposes a novel individually demagnetization power converter (IDPC) specifically designed for SRMs to effectively utilize the demagnetization energy through an independent demagnetization circuit. Compared with traditional converters, the IDPC can accept direct current (DC) and high-frequency alternating current (AC) inputs while achieving fast demagnetization and energy recovery. The topology and working principle of the IDPC are analyzed in detail in this paper using a three-phase 12/8 SRM as the research object. In addition, the influence of the winding demagnetization voltage on the negative torque during the demagnetization phase was studied, as well as the functional implementation and logic control strategy of the IDPC. Simulation and experimental results confirm the validity of the proposed topology and high-frequency AC drive characteristics, as well as their advantages in terms of efficiency, output capacity and dynamic performance. © 2015 IEEE.

关键词： Reluctance motors

来源：评论

学校读者我要写书评

暂无评论

Doppler-SLAM: Doppler-Aided Radar-Inertial and LiDAR-Inertial Simultaneous Localization and Mapping

arXiv

引用

arXiv 2025年

作者： Wang, Dong Haag, Hannes Herraez, Daniel Casado May, Stefan Stachniss, Cyrill Nüchter, Andreas Informatics XVII – Robotics Julius-Maximilians-Universität Würzburg Germany Faculty of Electrical Engineering Precision Engineering Information Technology Nuremberg Institute of Technology Georg Simon Ohm Germany CARIAD SE University of Bonn Germany Center for Robotics University of Bonn Lamarr Institute for Machine Learning and Artificial Intelligence Germany

Simultaneous localization and mapping (SLAM) is a critical capability for autonomous systems. Traditional SLAM approaches, which often rely on visual or LiDAR sensors, face significant challenges in adverse conditions such as low light or featureless environments. To overcome these limitations, we propose a novel Doppler-aided radar-inertial and LiDAR-inertial SLAM framework that leverages the complementary strengths of 4D radar, FMCW LiDAR, and inertial measurement units. Our system integrates Doppler velocity measurements and spatial data into a tightly-coupled front-end and graph optimization back-end to provide enhanced ego velocity estimation, accurate odometry, and robust mapping. We also introduce a Doppler-based scan-matching technique to improve front-end odometry in dynamic environments. In addition, our framework incorporates an innovative online extrinsic calibration mechanism, utilizing Doppler velocity and loop closure to dynamically maintain sensor alignment. Extensive evaluations on both public and proprietary datasets show that our system significantly outperforms state-of-the-art radar-SLAM and LiDAR-SLAM frameworks in terms of accuracy and robustness. To encourage further research, the code of our Doppler-SLAM and our dataset are available at: https://***/Wayne-DWA/Doppler-SLAM. © 2025, CC BY-NC-ND.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Predicting the Impact of Filter Parameters on the Accuracy of Biosignal Measurement

Machine Learning in Predicting the Impact of Filter Paramete...

引用

Digital Signal Processing and its Applications (DSPA), International Conference on

作者： Yeldos A. Altay Raisa K. Uskenbayeva Abu-Alim E. Ayazbay Alexey V. Fedorov Department of Robotics and Technical Means of Automation Satbayev University Almaty Kazakhstan Institute of Automation and Information Technologies Vice-Rector Satbayev University Almaty Kazakhstan Electronic engineering Almaty University of Power Engineering and Telecomunications Almaty Kazakhstan Faculty of Control Systems and Robotics ITMO University Saint-Petersburg Russian Federation

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

In this scientific article under consideration, a machine learning model has been developed that allows predicting the impact of filter parameters on the accuracy of measuring a biosignal - an ECG (electrocardiography) signal. For the first time, quantitative results have shown the degree of influence and the error introduced into the measured biosignal and described through dependence. The results of assessing the obtained relationship of indicators demonstrate an inverse correlation relationship that characterizes a decrease in the accuracy of measurement at the output of a high-order digital filtering system. The machine learning model is based on the linear regression method the dependence of which is approximated by the method based on least squares and visualized using a scattergram. The adequacy of the developed machine learning model was confirmed by calculating the coefficient of determination and checking its statistical significance. The developed model can be used to create new or improve existing biomedical data processing systems to increase the reliability of the results.

关键词： Accuracy Shape Filtering Biological system modeling Machine learning Biomedical measurement Electrocardiography Distortion Distortion measurement Digital filters

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：