检索结果-内蒙古大学图书馆

Research on fault diagnosis of a railway point machine based on a multi-entropy feature extraction method and support vector machine

引用

Transportation Safety and Environment 2023年第4期5卷 58-66页

作者： Yunting Zheng Shaohua Chen Zhiyong Tan Yongkui Sun Automation and Electrical Engineering College Dalian Jiaotong UniversityDalian 116028LiaoningChina CRRC Dalian Co.Ltd. Dalian 116021LiaoningChina National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong UniversityBeijing 100044China

A new fault diagnosis method is proposed to effectively extract the fault features of the sound signal of typical faults of ZDJ9 railway point machines.A multi-entropy feature extraction method is proposed by combing multi-scale permutation entropy and wavelet packet ***,empirical mode decomposition is performed on sound signals to obtain modal components with different time ***,multi-scale permutation entropy is extracted from these ***,the wavelet packet entropy of the sound signals of these sensitive nodes is obtained by analysing the reconstructed signals of the last layer *** the multi-scale permutation entropy and the wavelet packet entropy can distinguish the subtle features of the signal,the subtle features of the information among the high-dimensional features,ReliefF is ***,a support vector machine(SVM)is used to judge the original sismal can be obtained as the feature vector of the 2DJ9 iway point mnchine in ditterent states,To reduce the redundant fault type of a ZDJ9 rilway point machine.

关键词： railway point machine fault diagnosis sound signal support vector machine(SVM)

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Model-Free Predictive Current control for PMSMs Incorporating Discrete Space Vector Modulation 19th

An Enhanced Model-Free Predictive Current Control for PMSMs ...

引用

19th Annual Conference of China Electrotechnical Society, ACCES 2024

作者： Yang, Yuhui Qin, Qing Qin, Yingmei Che, Yanqiu School of Automation and Electrical Engineering Tianjin University of Technology and Education Tianjin300222 China Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin University of Technology and Education Tianjin300222 China

ISBN: (纸本)9789819613823

Model-free predictive current control (MFPCC) has excellent parameter robustness owing to unused parameters of the controller. However, the method has the current gradient update stagnation problem due to the limited availability of only 7 voltage vectors, which results in a high current/torque ripple. To address this shortcoming, an enhanced MFPCC for permanent magnet synchronous machines (PMSMs) incorporating discrete space vector modulation (DSVM) is proposed in this paper. First, the basic voltage vectors are expanded from 7 to 37 by DSVM. Then, a novel current gradient updating method is developed to effectively reduce the current/torque ripple caused by current gradient updating stagnation. Finally, a candidate vector preselection method is designed to simplify the calculation process of current gradient updating. The effectiveness of the proposed method is verified on a 2 kW PMSM driving experimental platform. The experimental results show that the THD is reduced from 25.5% to 7.8% while the dq-axes current ripple is respectively reduced from 5.1 A and 5.8 A to 2.2A and 1.5 A. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Study of aircraft skin defect detection and characterization methods 11

Study of aircraft skin defect detection and characterization...

引用

2023 IEEE 11th International Conference on Information, Communication and Networks, ICICN 2023

作者： Wang, Xinfeng Liu, Qing Jia, Kun Zhang, Yan Zhang, Haiyin Zhen, Jia Shang, Kaida Xi'An University of Technology School of Automation and Information Engineering Xi'an China Xi'An Aerocomm Measurement and Control Technology Co. Ltd Xi'an China

ISBN: (纸本)9798350314014

With the development of modern vehicle functions and technologies, surface geometry defects such as dents and cracks generated during the assembly and service of a vehicle not only endanger flight safety and reduce load capacity but also limit its functional characteristics. Accurate detection of surface geometry defects is critical, and these defects must be controlled within a small margin of error. However, conventional methods have difficulty meeting practical requirements in terms of detection accuracy and measurement size. In this paper, based on the analysis of the structural characteristics of the aircraft surface, an aircraft skin defect detection and characterization method is proposed, which processes the defect point cloud data, combines the segmentation algorithm of area growth to detect defects, and analyzes the geometric analysis and characterization through the depth of defects to achieve the accurate measurement of defects, and the experimental results show that the measurement of round holes with different depths of standard parts, the measurement results and the true value of The error are less than 0.05mm;the measurement of the outer surface of the aircraft engine compartment can detect different types of defects such as scratches or dents, and the method in this paper can be extended to the defect detection field of other large industrial equipment. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Sensitivity Analysis of the Flexible Spiral Magnetic Field Energy Harvester 10

Sensitivity Analysis of the Flexible Spiral Magnetic Field E...

引用

10th International Conference on Power and Energy Systems engineering, CPESE 2023

作者： Wang, Wei Xu, Chenjin Wang, He Su, Wenbo Ji, Zhenya Hu, Minqiang Nanjing Normal University State Key Laboratory of Smart Grid Protection and Control Nari Group Corporation Nari School of Electrical and Automation Engineering Nanjing China State Key Laboratory of Smart Grid Protection and Control Nari Group Corporation Nanjing China Nanjing Normal University Nari School of Electrical and Automation Engineering Nanjing China

ISBN: (纸本)9798350327625

The magnetic field energy harvesting has become a more suitable method for powering the monitoring sensors due to its simple energy harvesting structure, high power density, and stable energy source. However, existing magnetic field energy harvester have limitations such as restricted installation size, single application scenario, and difficulty in installation or disassembly. Motivated by the above problems, this paper proposes a flexible spiral magnetic field energy harvesting (SMFH) method, which is verified by the establishment of energy harvesting models, theoretical derivation, and simulation analysis. On this basis, a comprehensive performance analysis is performed on the number of windings, load characteristics, flexibility, weight, and non-ideal resonant state. Also, the sensitivity of the flexible SMFEH to various parameter changes is deeply analyzed. Finally, the experiments have verified the feasibility of the flexible SMFEH. © 2023 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Research on IGBT Lifetime Prediction Based on Residual BP Neural Network 10th

Research on IGBT Lifetime Prediction Based on Residual BP Ne...

引用

10th Frontier Academic Forum of Electrical engineering, FAFEE 2022

作者： Sui, Yi Na, Kun Liu, Wei Yuan, Zihang Zhu, Mingjun Zheng, Ping School of Electrical Engineering and Automation Harbin Institute of Technology Harbin150001 China Xi’an Flight Automatic Control Research Institute Xi’an710076 China

ISBN: (纸本)9789819934034

Insulated Gate Bipolar Transistor (IGBT) are widely used in electric vehi-cles, aerospace and other fields with high reliability requirements. This paper first analyzes its failure mechanism according to the internal structure of the IGBT, and selects the collector-emitter turn-off peak voltage value VCE-p as the characteristic parameter for life prediction;Using the IGBT accelerated thermal aging data set published by NASAPCoE laboratory to extract data to explore the relationship between characteristic parameter VCE-p and junction temperature;The IGBT life prediction model is built on the basis of BP neural network and the analysis results show that the gradient disappears when the model reaches a certain depth and the prediction accuracy is low under small sample data;This paper further proposes an IGBT life prediction model based on residual BP neural network. Multiple residual network modules are superimposed to increase the depth of the BP neural network. Comparing and analyzing the two models with the performance evaluation index, it can be seen from the results that the prediction result of residual BP neural network has a higher accuracy, and also has a better effect when the sample data is small. © Beijing Paike Culture Commu. Co., Ltd. 2023.

关键词： Junction temperature

来源：评论

学校读者我要写书评

暂无评论

Single-ended protection method for hybrid HVDC transmission line based on transient voltage characteristic frequency band

引用

Protection and control of Modern Power Systems 2023年第2期8卷 207-217页

作者： Hongchun Shu Shixin Wang Shunguang Lei Yunnan Key Laboratory of Green Energy Electric Power Measurement DigitalizationControl and ProtectionKunming University of Science and TechnologyKunming 650500Yunnan ProvinceChina School of Electrical Engineering and Automation Harbin Institute of TechnologyHarbin 150001Heilongjiang ProvinceChina

Hybrid high-voltage direct current(HVDC)transmission has the characteristic of long transmission distance,complex corridor environment,and rapid fault evolution of direct current(DC)*** high fault current can easily cause irreversible damage to power devices,rapid and reliable line protection and isolation are necessary to improve the security and reliability of hybrid HVDC transmission *** address such requirement,this paper proposes a single-ended protection method based on transient voltage frequency band ***,the frequency characteristics of the smoothing reactor,DC filter,and DC line are analyzed,and the characteristic frequency band is defined.A fault criterion is then constructed based on the voltage characteristic frequency band energy,and faulty pole selection is performed according to the fault voltage characteristic frequency band energy *** proposed protection method is verified by simulation,and the results show that it can rapidly and reliably identify internal and external faults,accurately select faulty poles without data communication synchronization,and has good fault-resist-ance and anti-interference performance.

关键词： Boundary frequency characteristics Characteristic frequency band Hybrid HVDC Single-end protection Transient voltage

来源：评论

学校读者我要写书评

暂无评论

XSpace: Self-learning platform for implementation of digital control algorithms 14

XSpace: Self-learning platform for implementation of digital...

引用

14th IEEE Global engineering Education Conference, EDUCON 2023

作者： Caceres, Pablo Cardenas Cieza Huane, Leslie Y. Horna Vilcahuaman, Ingrid M. Pauyac Estrada, Claudia R. Casano, Celso De-La-Cruz Tafur Sotelo, Julio C. Pontificia Universidad Catolica Del Peru Department of Engineering Electronics Section Lima Peru Degree Program Pontificia Universidad Catolica Del Peru Department of Engineering Control and Automation Master Engineering Lima Peru

ISBN: (纸本)9798350399431

In the electronic engineering undergraduate program, Peruvian universities offer different theoretical courses of Automatic control that do not present enough practical approach to the algorithms that are studied during the progress of these courses;however, the approach to implementation is very important to achieve good performance in the industry and researching. In this work is presented XSpace, an innovative and friendly platform which consists of a robust hardware that allows the student to take it home;this way, the student is given the opportunity to implement digital control algorithms learned in the theoretical classes. The effectiveness of this platform is shown using a proposed methodology which evidences greater interest, efficiency and efficacy in students at the Automatic control area. This project was implemented in the 'control Systems' course at Pontificia Universidad Catolica del Peru (PUCP) from 2020 to 2022. Results are presented through a student survey and a history of average grades during the academic periods the platform was employed. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Adaptive control for Stochastic Nonlinear Systems with Input Saturation Based on Multi-dimensional Taylor Network 20

Adaptive Control for Stochastic Nonlinear Systems with Input...

引用

20th IEEE International Conference on Mechatronics and automation, ICMA 2023

作者： Zheng, Xiao-Yi Yan, Hong-Sen Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Southeast University School of Automation Nanjing210096 China

ISBN: (纸本)9798350320831

For stochastic nonlinear systems with input saturation, few of the existing control methods use a suitable auxiliary system to solve input saturation problem, and most of them are for deterministic systems. In this study, according to the backstepping approach and the Lyapunov stability theorem, utilizing multi-dimensional Taylor network (MTN), an adaptive controller is presented to secure that all closed-loop signals keep bounded in probability, in which MTN is implemented to approach the uncertain function during the controller design. Moreover, the impact raised by input saturation is mitigated by designing an appropriate auxiliary system, in which the order of the auxiliary system is the same as that of the controlled system. Furthermore, unlike the majority of prior findings, the final output signal could be constrained in a mean quartic sense by an explicit expression of the input saturation error (the difference between the control signal and the saturation input) and the parameters used for design. Finally, the efficiency of the suggested control methodology is confirmed by providing an example. © 2023 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Composite-mask GAN based on refined optical flow and disparity map for SLAM visual odometry

引用

Optoelectronics Letters 2025年

作者： JI Yuehui JIANG Jingwei LIU Junjie SONG Yu GAO Qiang School of Electrical Engineering and Automation， Tianjin University of Technology Tianjin Key Laboratory of Control Theory and Application for Complex Systems

Although deep learning methods have been widely applied in slam visual odometry over the past decade with impressive improvements， the accuracy remains limited in complex dynamic environments. In this paper， a composite mask-based generative adversarial network is introduced to predict camera motion and binocular depth maps. Specifically， a perceptual generator is constructed to obtain the corresponding parallax map and optical flow from between two neighboring frames. Then， an iterative pose improvement strategy is proposed to improve the accuracy of pose estimation. Finally， a composite mask is embedded in the discriminator to sense structural deformation in the synthesized virtual image， thereby increasing the overall structural constraints of the network model， improving the accuracy of camera pose estimation， and reducing drift issues in the Visual Odometer. Detailed quantitative and qualitative evaluations on the KITTI dataset show that the proposed framework outperforms existing conventional， supervised learning and unsupervised depth VO methods， providing better results in both pose estimation and depth estimation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LSTM-TD3-based control for delayed drone combat strategies 19th

LSTM-TD3-based control for delayed drone combat strategies

引用

19th Chinese Intelligent Systems Conference, CISC 2023

作者： Ji, Bingyu Wang, Jun Zhang, Hailin Zhang, Ya School of Automation Southeast University Nanjing210096 China Key Laboratory Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9789819968817

Reinforcement learning has made great achievements in the field of game confrontation, and military rendition intelligence is also imminent. In this paper, we propose a game confrontation game model based on LSTM and deep reinforcement learning for the red and blue sides of the drones in the delayed *** action buffer pair is added to the original battlefield environment to create a large latency environment, a TD3 algorithm is designed to join LSTM to predict the state trend, and a historical data pool is built using PER. The training results in the simulation platform show that the model has a significant improvement in effectiveness in the large latency environment, with a 0.22 improvement in battle damage ratio and a 34.76% improvement in win rate over the original model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Reinforcement learning

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：