检索结果-内蒙古大学图书馆

第43届中国控制会议

作者： Yatao Liu Xinliang Zhang Yanqi Wang Yitian Zhou Lijie Jia School of Electrical Engineering and Automation Henan Key Laboratory of Intelligent Detection and Control of Coal Mine EquipmentHenan Polytechnic University Anhui Institute of Information Technology Zhoushan Yangwangnaxin Technology Co.Ltd

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

When applying deep learning networks to the machinery fault diagnosis, it is crucial to train the networks under the sufficient fault samples. To achieve such condition under the imbalance samples, it is essential for the generative networks to learn a complete distribution for the imbalanced samples. Existing data augmentation methods often employ generative models directly to reconstruct samples. Under the limited number of samples, it is a challenge to achieve discriminative features for the fault due to the sample underrepresentation. To address this issue, this paper introduces an innovative approach using coupled generative adversarial networks(CoGAN). The CoGAN framework integrates several systematic enhancements to enhance the robustness of the generative adversarial networks. Firstly, to tackle the imbalance between fault and normal sample distributions,parallel coupled networks are employed to jointly learn their distributions. These networks share weights in the extraction layers of the generator, serving as a representative feature distribution generator for the raw samples. Secondly, a one-sided label smoothing strategy is adopted to mitigate model overfitting in scenarios with limited samples. Finally, historical averaging and gradient penalty are incorporated into the cost function to mitigate adversarial vulnerabilities, ensuring a more stable training performance. Experimental results on the roll bearing dataset from Case Western Reserve University demonstrate that the proposed approach consistently achieves higher accuracy compared to state-of-the-art models across different training sample sizes. This effectively enhances fault diagnosis performance and significantly reduces the dependency on extensive training data.

关键词： deep learning,imbalanced samples fault diagnosis coupled generative model adversarial networks gradient penalty

来源：评论

学校读者我要写书评

暂无评论

Analysis of Air-Gap Field Modulation Effect on Torque for 6-Slot 4-Pole High-Speed Permanent Magnet Machine

Analysis of Air-Gap Field Modulation Effect on Torque for 6-...

引用

Magnetic Conference - Short Papers (INTERMAG Short Papers), IEEE International

作者： Kai Li Chen Wang Ya Li Zhuoran Zhang School of Electrical Engineering Anhui Polytechnic University Wuhu China School of Electrical Engineering and Automation Anhui University Hefei China College of Automation Engineeringm Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (数字)9798350362213

ISBN: (纸本)9798350362220

The air-gap field modulation (AGFM) effect on torque contributions for a 6-slot/4-pole high-speed permanent magnet (HSPM) machine is investigated and analyzed to illustrate its torque generation mechanism. Firstly, the permeance and magnetomotive force (MMF) model are deduced to analyze to identity the main-order working harmonics, and the Maxwell stress tensor (MST) method is employed to calculate the air-gap field harmonic electromagnetic torque and quantify the contribution of the main working field harmonics. Then, the influences of different stator parameters on the AGFM effect are studied and optimized to improve the torque density of HSPM machine. Finally, a 10kW 6-slot/4-pole HSPM machine prototype is fabricated and experimented to validate the theoretical analysis.

关键词： Torque Tensors Magnetomechanical effects Air gaps Modulation Prototypes Stators

来源：评论

学校读者我要写书评

暂无评论

Phenomenological Modeling and Spectral Analysis of Spalling Planetary Gearboxes: A Theoretical and Experimental Study

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Liu, Zongyao Wang, Yutong Wang, Yadong Mao, Shixiang Feng, Wei Chang, Yong Henan University of Technology School of Mechanical and Electrical Engineering Henan Key Laboratory of Super Hard Abrasive Grinding Equipment Zhengzhou450001 China Henan University of Technology School of Mechanical and Electrical Engineering Zhengzhou450001 China Shanghai University School of Mechatronic Engineering and Automation Shanghai200444 China

As a common failure mode of gears, tooth spall can be easily arisen due to face fatigue. The occurrence of tooth spall can lead to a series of complex properties on the vibration spectrum and brings difficulty to the fault diagnosis of planetary gearboxes. However, the spectral analysis of planetary gearboxes due to a tooth spall has not been yet deeply conducted. Aiming at this issue, a phenomenological model is established to investigate the vibration induced by a spalling fault in planetary gearboxes. In the model, the detailed engagement process of the spalling tooth is considered, and two kinds of fault induced signals due to the entry and exit of the spalling tooth zone are simulated through a step-like and an impulse-like response function. Then vibration signals and their spectra of planetary gearboxes with a spalling sun and a spalling planet gear are obtained, respectively. Finally, the proposed phenomenological models are validated using experimental data collected from a planetary gearbox test rig. The validation results showed that the proposed phenomenological model is effective to exhibit the spectral structures of planetary gearboxes with a spalling tooth. © 1963-2012 IEEE.

关键词： Vibrations (mechanical)

来源：评论

学校读者我要写书评

暂无评论

ILC Coupled with Unscented Kalman Filter Strategy for Trajectory Tracking

ILC Coupled with Unscented Kalman Filter Strategy for Trajec...

引用

Robotics, Control and automation engineering (RCAE), International Conference on

作者： Ziwei Huangfu Wei Li Yiyang Chen Lei Wang School of Electrical Engineering Anhui Polytechnic University Wuhu China School of Mechanical and Electrical Engineering Soochow University Suzhou China School of Automation Wuxi University Wuxi China

ISBN: (数字)9798350355642

ISBN: (纸本)9798350355659

This paper employs an iterative learning control (ILC) approach to achieve tracking task for non-repetitive time-varying systems (NTVSs). In industrial production tasks, the actual model of the system is usually unknown, and the nominal model will have a certain degree of error, which brings complexity and difficulty to the design of control task. To tackle this issue, ILC framework incorporates unscented Kalman filter strategy to estimate parameter, which yields the proposed algorithm. The robust convergence property of the scheme is proven in theory based on the design goal. Finally, the advantage of the proposed method is demonstrated by comparison with other methods.

关键词： Trajectory tracking Production Control systems Filtering theory Complexity theory Kalman filters Time-varying systems Robots Convergence Iterative learning control

来源：评论

学校读者我要写书评

暂无评论

The Implementation of Physical Parameters and Frequency Modulation in the Grid-Forming Converter with Energy Storage System

The Implementation of Physical Parameters and Frequency Modu...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Minxuan Peng Neng Peng Yi Wang Shuangyin Dai Kaihsun Chuang Xiaoming Zha Jianjun Sun School of Electrical Engineering and Automation Wuhan China State Grid Henan Electric Power Company Zhengzhou China

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

The grid-forming converter, which controls the output frequency through DC-link voltage, suffers from DC-link voltage exceeding limits and oscillation divergence during transient operation due to the mismatch between control parameters and physical components. Based on a grid-connected converter with an energy storage system, this paper proposes a parameter selection method corresponding with physical inertia and damping using the DC-link voltage synchronous control. This paper analyzes the equivalent inertia correspondence based on the operating range of DC-link voltage. Then, the parameter-corresponding method is proposed based on a composite three-port converter. Through the theoretic analysis and simulation analysis, the energy storage device supports extra inertia and damping with the proposed method while achieving frequency modulation. Finally, the effectiveness of the proposed method is verified through the 10kW prototype experiments.

关键词： Damping Frequency modulation Prototypes Stability analysis Voltage control Transient analysis Oscillators Frequency control Energy storage Grid forming

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis and Optimization of Vapor Injection Refrigeration Cycle

Performance Analysis and Optimization of Vapor Injection Ref...

引用

International Conference on Renewable Energy Research and Applications (ICRERA)

作者： Jidong Li Maolin Cai Weiqing Xu Guanwei Jia School of Automation Science and Electrical Engineering Beihang University Beijing China School of Physics and Electronics Henan University Kaifeng China

ISBN: (数字)9798350375589

ISBN: (纸本)9798350375596

Refrigerant vapor-injection technique has been proved to improve the performance of refrigeration systems, which can mitigate the problem of exhaust overheating and supplement refrigerant flow for compressor at low evaporation temperature. To analyze the refrigeration performance, the evaporation and condensation temperature, heat exchange temperature difference, injecting pressure and evaporator superheat are comprehensively analyzed. The applicability for different refrigerants is extensively evaluated. Compared with the conventional system, the vapor-injection cycle demonstrates better performance especially under severe conditions.

关键词： Heating systems Renewable energy sources Evaporation Performance analysis Refrigeration Refrigerants Optimization Heat transfer Arithmetic

来源：评论

学校读者我要写书评

暂无评论

Adaptive Vibration Suppression Control for Direct-Drive Flexible Manipulators Based on PMSM Self-Sensing

Adaptive Vibration Suppression Control for Direct-Drive Flex...

引用

IEEE Student Conference on Electric Machines and Systems

作者： Zhang-Hao Huang Jian-Xin Shen Dan Shi Yunchong Wang College of Electrical Engineering Zhejiang University Hangzhou China School of Automation Zhejiang Polytechnic University of Mechanical and Electrical Engineering College of Electrical Engineering Zhejiang University Hangzhou China

ISBN: (数字)9798350366945

ISBN: (纸本)9798350366952

In flexible manipulator systems driven directly by permanent magnet synchronous motors (PMSM), residual vibration following servo positioning has a detrimental effect on the precision and efficiency of industrial operations. This study proposes an adaptive vibration suppression control strategy based on PMSM self-sensing, which is founded upon the dynamics model of direct-drive flexible manipulators. This strategy permits the estimation of vibration frequency and damping coefficient without the necessity for supplementary vibration sensors and fast Fourier transform (FFT). The parameters of the input shaper are dynamically adjusted by means of adaptive frequency and damping coefficient identification. Simulation results verify the effectiveness of the proposed control method.

关键词： Vibrations Damping Fast Fourier transforms Simulation Estimation Permanent magnet motors Frequency estimation Sensors Servomotors Manipulator dynamics

来源：评论

学校读者我要写书评

暂无评论

A New Road Extraction Method from Satellite Images Using Genetic Programming

引用

Guidance, Navigation and Control 2024年第2期4卷 47-79页

作者： Jing Liang Yaxin Chang Ying Bi Caitong Yue Boyang Qu Mengnan Liu School of Electrical and Information Engineering Zhengzhou University ZhengzhouP.R.China School of Electrical Engineering and Automation Henan Institute of Technology XinxiangP.R.China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang P.R.China School of Electronic and Information Zhongyuan University of Technology ZhengzhouP.R.China State Key Laboratory of Power System of Tractor Luoyang P.R.China

Extracting roads from satellite images is an important task in thefield of computer vision with a wide range of ***,efficient road extraction from satellite images remains a complex challenge due to issues such as data labeling and the diversity of road *** methods often struggle to balance accuracy,robustness,and *** programming(GP)is based on aflexible and interpretable structure that is robust and does not require a large amount of data *** position the road extraction problem as a binary semantic segmentation task and introduce GP ***,an approach for extracting pixel neighborhood features is proposed,and features from multiple images in the DeepGlobe road extraction dataset are ***,an advanced feature construction method based on GP is ***,these advanced features are utilized for training classifier and classi-fication to achieve road *** have validated the effectiveness of the approach on the DeepGlobe road extraction *** results demonstrated that the proposed approach exhibits superior performance compared to traditional classification methods and multilayer perceptron(MLP)in terms of accuracy,generalization,and *** study provides a valuable reference for the integration of GP into the domain of road extraction from satellite images,showcasing their potential to enhance the accuracy and efficiency.

关键词： Road extraction genetic programming feature construction

来源：评论

学校读者我要写书评

暂无评论

Load Change Assessment-Based Feedforward Compensation for FCS-MPCC Used in PMSMs Considering Load Disturbances 49

Load Change Assessment-Based Feedforward Compensation for FC...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Liu, Wenjie Sun, Shichao Han, Yaofei Gong, Chao Huang, Ziqi Li, Weilin School of Automation Northwestern Polytechnical University Xi'an China Tongji University National Maglev Transportation Engineering R&d Center Shanghai China Hong Kong Polytechnic University Department of Electrical Engineering Hong Kong

ISBN: (纸本)9798350331820

This paper presents a load change assessment-based feedforward compensation method for finite control set model predictive current control (FCS-MPCC) in permanent magnet synchronous motors (PMSMs). The objective is to address the adverse effects of load disturbances on FCS-MPCC, which can lead to deteriorated control performance and system instability. To mitigate these effects, a novel feedforward compensation mechanism is proposed by integrating a load change assessment mechanism within the FCS-MPCC framework. The mechanism enables real-time estimation of load changes by accurately capturing their rate and direction. A sliding mode torque observer (SMTO) is developed to ensure accurate load estimation, characterized by fast response and strong robustness. The stability of the SMTO is analyzed using a Lyapunov function. Furthermore, a technique is proposed to generate feedforward compensation values based on the load change assessment, specifically applied to the q-axis reference current. Comparative simulation results verify the effectiveness of the proposed strategies. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Resilient Consensus of Multi-Agent Systems on Time-Varying Directed Graphs Under Byzantine Attacks and Actuation Attacks

Resilient Consensus of Multi-Agent Systems on Time-Varying D...

引用

2023 China automation Congress, CAC 2023

作者： Gong, Xin Shu, Zhan Feng, Zhiguang Lin, Hong School of Cyber Science and Engineering Southeast University Nanjing China University of Alberta Department of Electrical and Computer Engineering AB Canada College of Automation Harbin Engineering University Harbin China Institute of Intelligence Science and Engineering Shenzhen Polytechnic University Shenzhen China

ISBN: (纸本)9798350303759

This work deals with the distributed attack-resilient consensus problem for continuous-time multi-agent systems on time-varying directed graphs. An unknown fraction of agents are Byzantine agents, which send false information to deceive their neighbors. Moreover, each normal agent suffers from actuation attacks. In order to ensure the resilience of all normal agents against the above hybrid attacks, a new kind of edge-based protocols is formulated, which achieves resilient consensus via signed feedback. Then, the finite-time zero-error control performance of the above protocol is proven for (2f+1) - robust time-varying directed topologies, based on strictly Lyapunov stability analysis. © 2023 IEEE.

关键词： Directed graphs

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：