检索结果-内蒙古大学图书馆

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Yuan, Hao Cao, Guang-Zhong Hu, Hongjin Lei, Yu Du, Yanliang Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen University Shenzhen China College of Civil and Transportation Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781665464543

The field of scene text detection has gained increasing attention in recent years. However, it faces the challenges of high computational overhead. This paper proposes a Lightweight Multi-Step Feature Fusion Network (LMFFNet), an enhanced model designed to reduce computational burden in scene text detection tasks. Based on the lightweight MobileNetV3 backbone network, the proposed network combines the Triplet Attention Feature Enhancement Module (TFEM) and the Dynamic Feature Fusion Module (DFFM) to achieve efficient scene text detection. The TFEM expands the receptive field of the model and better utilizes features of various scales. The DFFM, which incorporates Convolutional Block Attention Module (CBAM), adaptively fuses features of different scales to improve the performance and robustness of the model. In the loss function, Dice Loss is used to address the imbalance between positive and negative samples. The proposed LMFFNet achieves a detection accuracy of 90.7% on the ICDAR2015 dataset, with a 91.7% reduction in parameter count and a 70.0% reduction in overall model overhead compared to the baseline model DBNet (ResNet-50).The effectiveness of the lightweight scene text detector is verified. © 2024 IEEE.

关键词： attention mechanism feature fusion lightweight text detection

来源：评论

学校读者我要写书评

暂无评论

Analysis of Power and Power Spectral Density for Quaternary Random Pulse Position Modulation 14

Analysis of Power and Power Spectral Density for Quaternary ...

引用

14th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2025

作者： Chen, Hung-Chi Wu, Hsiang-Kai Wu, Chih-Chiang Department of Electronics and Electrical Engineering Hsinchu Taiwan Institute of Electrical and Control Engineering Hsinchu Taiwan Mechanical and Mechatronics Systems Research Laboratories Hsinchu Taiwan

ISBN: (纸本)9798331516116

In this paper, the quaternary random pulse position modulation (QRPPM) is proposed to further reduce the power of dominant harmonic clusters. From the analysis of the power and power spectral density, the minimum integer-harmonics power dispersion rate (HPDR) is increased from 50.0% of the conventional random center/edge alignment PWM (RCEA-PWM) to 75.0% of the proposed QRPPM. Some results are provided to validate the proposed method. © 2025 IEEE.

关键词： Pulse position modulation

来源：评论

学校读者我要写书评

暂无评论

Vibration Suppression in a Two-Mass Drive System Using Three Input Shaping-Comparative Study 6

Vibration Suppression in a Two-Mass Drive System Using Three...

引用

6th International Conference on Computing, Electronics and Communications engineering, iCCECE 2023

作者： Chen, Guan Zhu, Lintao Zheng, Weilong Wang, Can Shenzhen University College of Mechatronics and Control Engineering Shenzhen China STMicroelectronics Shenzhen China

ISBN: (纸本)9798350340921

Input shapers have widely used to suppress mechanical oscillations in high-precision positioning systems, and the commonly used are zero vibration (ZV) input shaper, zero vibration and derivative (ZVD), and extra-insensitive (EI). The current research only examines the performance of specified input shapers, lacking the applicable conditions for each input shape. How to choose the right input shaper for a specific system has not been solved yet. In this paper, for motor drive systems with flexible connections, firstly, the characteristics of three input shapers are analyzed using the algebraic method and the amplitude-frequency characteristic method. Then, the conditions for the existence of the intersection frequencies of the three input shapers are investigated and the respective intersection frequencies are calculated. Finally, the intersection frequency is used as the dividing point to divide the whole frequency domain band into different intervals, and the applicable conditions of each input shaper are studied for three aspects: system oscillation frequency identification accuracy, oscillation suppression requirement and response speed. The simulation results verify the performance of the three input shapers and the applicable conditions analyzed. © 2023 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

The Impact of Emotion on Takeover Performance in Human-machine Shared Driving

The Impact of Emotion on Takeover Performance in Human-machi...

引用

13th International Conference on Transportation and Traffic engineering, ICTTE 2024

作者： Jiayuan, Wang Tingru, Zhang Institute of Human Factors and Ergonomics College of Mechatronics and Control Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781837242931

ISBN: (纸本)9781837242672

This study aimed to explore the performance differences of different emotions on driver takeover performance in L3 automated driving systems. 48 driving-experienced college students were recruited. Based on the two-dimensional emotion model, four emotions of valence (positive/negative) x arousal (high/low) were selected for induction and verification. Driving behavior data was collected in a simulated driving environment. Driving tasks included 4 obstacle avoidance scenarios. Results show that valence approximately affects takeover time and significantly affects vehicle longitudinal control. Negative emotions led to longer takeover times and sad led to worse longitudinal vehicle control. Arousal had a greater impact on lateral performance. Under high-arousal emotions, drivers have more unstable steering wheel control. This study is of great significance for optimizing automated driving system design and improving driving safety and driver experience. © The Institution of engineering & Technology 2024.

关键词： Human engineering

来源：评论

学校读者我要写书评

暂无评论

Plasticity and rejuvenation of aged metallic glasses by ultrasonic vibrations

引用

Journal of Materials Science & Technology 2024年第14期181卷 231-239页

作者： Zhe Chen Shuai Ren Rui Zhao Jian Zhu Xin Li Heting Zhang Hongji Lin Jiahua Zhu Sajad Sohrabi Wenqing Ruan Jiang Ma Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots Shenzhen UniversityShenzhen 518060China Shenzhen Key Laboratory of High Performance Nontraditional Manufacturing College of Mechatronics and Control EngineeringShenzhen UniversityShenzhen 518060China Institute of Physics Chinese Academy of SciencesBeijing 100190China School of Mechanical Electrical and Information EngineeringShandong UniversityWeihai 264209China

Metallic glasses(MGs)possess exceptional properties,but their properties consistently deteriorate over time,thereby resulting in increased complexity in *** thus poses a formidable challenge to the forming of long-term aged ***,we report ultrasonic vibration(UV)loading can lead to large plas-ticity and strong rejuvenation in significantly aged MGs within 1 s.A large UV-induced plasticity(UVIP)of 80%height reduction can be achieved in LaNiAl MG samples aged at 85%of its glass transition tem-perature(0.85 T_(g))for a duration of up to 1 *** energy threshold required for UVIP monotonously increases with aging *** the UV loading process,the aged samples show strong rejuvenation,with the relaxation enthalpy even surpassing that of as-cast *** findings suggest that UV loading is an effective technique for forming and rejuvenating aged MGs simultaneously,providing an alterna-tive avenue to explore the interplay between the property and microstructures as well as expanding the application prospects of MGs.

关键词： Metallic glass Ultrasonic vibration induced plasticity Aging Rejuvenation

来源：评论

学校读者我要写书评

暂无评论

A Novel Lightweight Disease Detection Algorithm Used in Ground-Penetrating-Radar 50

A Novel Lightweight Disease Detection Algorithm Used in Grou...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Gan, Huanming Hu, Hongjin Cao, Guang-Zhong Lei, Yu Du, Yanliang Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen University Shenzhen China College of Civil and Transportation Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781665464543

To solve the problems of excessive parameters in deep learning models of Ground Penetrating Radar (GPR) disease detection, this paper proposes a lightweight disease detection algorithm based on YOLOv8. A lightweight model is obtained by replacing its backbone network with the GhostHGNetV2 network. The SimAM attention mechanism module is used to improve the ability to perceive different levels of feature representation. Additionally, the WIOU is used as the loss function to improve the convergence and accuracy of the algorithm detection performance. Experimental results demonstrate that the proposed algorithm reduces the parameters of original networks by 25.3%, model size by 28.8%, and computational complexity (GFLOPs) by 20.3%. The effectiveness of the proposed lightweight disease detection algorithm is verified. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of Sub-Synchronous Oscillations on Hybrid Wind Farms with DFIG and PMSG 8

Analysis of Sub-Synchronous Oscillations on Hybrid Wind Farm...

引用

8th Asia Conference on Power and Electrical engineering, ACPEE 2023

作者： Long, Chaoyang Wang, Yun Luo, Fengyun Wu, Yanping Shenzhen University Mechatronics and Control Engineering Shenzhen China WuHan Guide Infrared Group of Guidance and Control Station China

ISBN: (纸本)9798350345520

This paper has investigated the sub-synchronous oscillations (SSO) phenomenon in hybrid wind farms with DFIG and PMSG. Firstly, a mathematical model of the hybrid wind farms is established. The model includes four parts: hybrid wind turbine, DFIG rotor machine-side controller (RSC), PMSG stator grid-side controller (GSC) and series compensation line module. Based on this model, the factors affecting the SSO phenomenon in the hybrid wind farms are explored by eigenvalue analysis. It is concluded that the variation of wind speed increases the possibility of SSO generation in DFIG wind farms, but the addition of PMSG wind farms can suppress the effect of wind speed variation. In comparison to single DFIG wind farms or PMSG wind farms, hybrid wind farms are less likely to generates SSO that results from the variation of PLL parameters. In addition, too large series compensation degree can lead to a more severe dynamic response of SSO phenomenon. © 2023 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

A Novel Sliding Mode control Method for Permanent Magnet Synchronous Motor 26

A Novel Sliding Mode Control Method for Permanent Magnet Syn...

引用

26th International Conference on Electrical Machines and Systems, ICEMS 2023

作者： Zhou, Haohan Cao, Guangzhong Hu, Hongjin Wang, Haotian Shenzhen University Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen China

ISBN: (纸本)9798350317589

The permanent magnet synchronous motor (PMSM) requires a high tracking response and static accuracy. To achieve this purpure, we present a novel approach for enhancing the speed control of PMSM by integrating a sliding mode controller with an optimized proportional resonant (SMC-PR) controller. The SMC can improve the disturbance rejection performance. The optimized PR controller can achieve steady-state tracking accuracy. With the combination of these two controllers, the PMSM control system can obtain high steady-state performance, fast dynamic response, and strong robust performance. The simulation of the proposed controller is performed on the MATLAB/ Simulink platform. The efficacy of the introduced controller is verified through comprehensive simulation results and analysis. © 2023 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Adaptive Notch Filter Design of a Single-Link Flexible Manipulator based on System Identification 6

Adaptive Notch Filter Design of a Single-Link Flexible Manip...

引用

6th International Conference on Computing, Electronics and Communications engineering, iCCECE 2023

作者： Liu, Chengwei Zhu, Lintao Zheng, Weilong Wang, Can Shenzhen University College of Mechatronics and Control Engineering Shenzhen China STMicroelectronics Motor Control Application Department Shenzhen China

ISBN: (纸本)9798350340921

This paper proposes an adaptive notch filter (ANF) control method based on recursive least squares (RLS) parameter identification, to suppress the vibration at the end of a single-link flexible manipulator (SFM), for the end inherent vibration frequency generated during operation. Firstly, the damping of SFM is considered, and its transfer function model is established to analyze the causes of vibration generated at the end. Then, the self-Tuning expressions for the notch filter (NF) parameters are derived based on the results of RLS parameter identification. Finally, the simulation and experimental results show that the method can automatically suppress the vibration problem caused by the end of SFM during the motion online. © 2023 IEEE.

关键词： Flexible manipulators

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection of Medical Cables Based on Anomaly Detection 49

Surface Defect Detection of Medical Cables Based on Anomaly ...

引用

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

作者： Yue, Junyu Cao, Guangzhong Hu, Zhiyong Lei, Yu Wang, Haotian College of Mechatronics and Control Engineering Shenzhen University Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots Shenzhen China

ISBN: (纸本)9798350331820

Medical cables have strict requirements for appearance quality, even minor surface defects are considered non-compliant. Surface defects in medical cables exhibit diverse types, uneven distribution and inconspicuous features, which is difficult to identify. This paper proposes Abnormal Generative Adversarial Networks (AbnormalGAN), a surface defect detection method of medical cables based on anomaly detection. The proposed method combines generative adversarial network (GAN) and anomaly detection. The input samples are fed into the generator to reconstruct the positive sample features, 'repairing' the surface defect areas of the medical cables. Then, get the abnormal score which is obtained based on the sum of pixel errors between the input and generated samples. The surface defects of medical cables are identified based on the abnormal score. Experimental results show that the proposed method is able to identifies surface defects in medical cables accurately, including previously unseen defects. The accuracy rate on the medical cable dataset reaches 99.8%. © 2023 IEEE.

关键词： Generative adversarial 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：