检索结果-内蒙古大学图书馆

11th International Symposium on Precision Mechanical Measurements

作者： Dai, Jun Lei, Yingying Zhao, Junwei Mei, Yundong School of Mechanical and Power Engineering Henan Polytechnic University Jiaozuo454003 China Henan International Joint Laboratory of Advanced Electronic Packaging Materials Precision Forming Henan Polytechnic University Jiaozuo454003 China School of Mechanical and Electrical Engineering Huanghe Jiaotong University Jiaozuo454950 China

ISBN: (纸本)9781510680296

Simultaneous localization and mapping (SLAM) is a significant challenge for autonomous mobile robotics, as it necessitates the reconstruction of an unfamiliar environment while simultaneously determining the robot's position using a map. The mobile robot employed a diverse range of sensors in the SLAM process to gather and interpret a map representation. Geometric model-based strategies have historically been employed for addressing SLAM problems. However, these techniques are prone to errors in tough environments, and single-sensor SLAM systems have degradation and adverse effects on localization and mapping outcomes in extreme environments characterized by high dynamics or coefficient characteristics. Recently, there has been a significant increase in the development of multi-sensor fusion SLAM techniques aimed at achieving more stable and resilient systems. This paper focuses on the development process and contemporary research conducted on multi-sensor fusion SLAM. This paper initially presents the overall structure of SLAM. It then provides a detailed explanation of the functions of front-end odometry, back-end optimization, loopback detection, and map building modules. Additionally, it provides a summary of the algorithms employed in SLAM. Furthermore, it describes and summarizes the classical representative open source algorithms based on the types of sensors to be combined. It also introduces commonly utilized public datasets, along with accuracy evaluation indexes and measurement tools. In conclusion, this paper presents a comprehensive examination of the development process, along with a summary of prominent research studies on the fusion of many sensors in SLAM. © 2024 SPIE.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

An Analytical Solution for Magnetic Field Distribution of Rectangular Magnets 7

An Analytical Solution for Magnetic Field Distribution of Re...

引用

7th IEEE International electrical and Energy Conference, CIEEC 2024

作者： Lou, Meiyan Ding, Jiaxin Fuzhou Polytechnic Department of Mechanical and Electrical Engineering Fuzhou350108 China School of Mechanical Engineering and Automation Fuzhou University Fuzhou350108 China

ISBN: (纸本)9798350359558

This paper presents a three-dimensional analytical solution for the magnetic field distribution of permanent magnet mechanisms with rectangular magnets. The model is based on the magnetic vector potential theory for the permanent magnet via the equivalent current. Analytical expressions of the magnetic flux intensity for a single magnet and the total magnets are deduced. Green formula and Simpson method are applied to solve the analytical expressions. The results agree well with those calculated by the finite element method. The proposed analytical model can provide a reference for the design and optimization of permanent magnetic mechanisms with rectangular magnets. © 2024 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Towards Better Unguided Depth Completion via Cross-Modality Knowledge Distillation in the Frequency Domain

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-14页

作者： Liu, Moyun Chen, Bing Chen, Youping Xie, Jingming Yao, Lei Zhang, Yang Hu, Qin Du, Jiawei Zhou, Joey Tianyi School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong China School of Mechanical Engineering Hubei University of Technology Wuhan China School of Automation Wuhan University of Technology Wuhan China Singapore

The inherent sparsity of LiDAR data often leads to extremely sparse depth maps, which poses a challenge for the development of LiDAR-based egocentric vehicles, such as self-driving cars and mobile robots. To overcome this limitation, guided depth completion methods use calibrated camera images to create precise, dense depth predictions from sparse LiDAR data. However, the extreme reliance on camera image limits its generalization of guided depth completion, especially its robustness to weather and light. In this paper, we aim to utilize camera images only during training phase to improve unguided depth completion, and discard camera in the inference phase. We comprehensively analyze the pivotal role of camera images in the depth completion task and emphasize the significance of the frequency distribution within the local windows, quantitatively demonstrating its substantial contribution. Subsequently, we introduce cross-modality knowledge distillation to align LiDAR features with camera features in the frequency domain, yielding corresponding guidance features. We devise a guidance and selection module to mitigate unavoidable inaccuracies in knowledge distillation, while it can enhance depth features and adeptly selects more precise encoded values from both the guidance branch and the unguided input. To further refine the completion result, we propose a progressive depth completion module incorporating two sub-networks connected by an attention for refinement module. This module produces weighted features from the decoder of the first stage to enhance the features in the encoder of the second stage. We denominate our method as Better Unguided Network (BUNet) and evaluate its efficacy on the KITTI depth completion benchmark and NYUv2 dataset, demonstrating its superiority over methods that exclude camera images during the inference phase. IEEE

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Working Condition Identification Method for the Scarifying Tooth Harrow Monitoring System of a Roller-type Residual Film Collector

引用

Journal of engineering Science and Technology Review 2024年第2期17卷 58-65页

作者： Xue, Dangqin Zhang, Xiaodong Dong, ZhaoSen Zhang, Jiaxi Shi, Huojie Nanyang Institute of Technology Nanyang473000 China College of Automation Engineering Henan Polytechnic Institute Nanyang473000 China Mechanical and Electrical Engineering Institute Xinjiang Agricultural University Urumqi830052 China Department of Biological Systems Engineering Washington State University PullmanMI98101 United States

The roller-type residual film collector is the main machine type for collecting residual films. The scarifying tooth harrow bears the largest resistance among all the components of the entire machine, and it directly affects the quality and efficiency of the residual film collector. In this study, the arithmetic optimization algorithm- variational mode decomposition - bidirectional long short-term memory (AOA-VMD-BiLSTM) model was proposed to improve the working condition identification accuracy of the scarifying tooth harrow. First, the locations of three scarifying tooth harrow monitoring points were analyzed, the arithmetic optimization algorithm was introduced to optimize the variational mode decomposition (VMD) parameters, and the optimal parameter combination of the three monitoring points was acquired. Second, the reconstructed signal for the three monitoring points on the scarifying tooth harrow after VMD decomposition was subjected to two-way updating and recursion with bidirectional long short-term memory (BiLSTM) as the core of the model, and iterative training of the scarifying tooth harrow under four working conditions was performed. Last, the new sample set and the original dataset were imported into two deep learning models, namely, BiLSTM and long short-term memory (LSTM), followed by a comparative validation of the training results of VMD-BiLSTM, VMD-LSTM, BiLSTM, and LSTM models. Results demonstrate that among the models, VMD-BiLSTM exerts the best processing effect on complex signals and has a higher convergence rate, better convergence stability, and higher accuracy. In the VMD-BiLSTM diagnostic model, each performance index can exceed 97.3%. This model performs better than VMD-LSTM, BiLSTM, and LSTM models and realizes intelligent classification under four signal conditions of the scarifying tooth harrow: no load, normal operation, mild overload, and serious overload. The proposed method provides great significances for improving the intelligenc

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A New Training Method for Photovoltaic Forecasting Based on ELM Auto-Encoder and Sparrow Search Algorithm

A New Training Method for Photovoltaic Forecasting Based on ...

引用

2023 International Conference on Smart electrical Grid and Renewable Energy, SEGRE 2023

作者： Ge, Yiwen Quan, Hao Li, Zixiong Zhang, Wenjie Yang, Dazhi Nanjing University of Science and Technology School of Automation Department of Electrical Engineering Nanjing China Hong Kong Polytechnic University Department of Electrical Engineering Hong Kong Harbin Institute of Technology School of Electrical Engineering and Automation Harbin China

ISBN: (纸本)9798350323269

Forecasting technology is an effective way to mitigate the randomness and volatility of solar energy in the modern power system, considering the high proportion of solar energy in the power system and high degree of electricity electronic characteristics, To enhance the accuracy of photovoltaic prediction model, a two-stage training method is proposed based on extreme learning machine (ELM) and sparrow search algorithm (SSA). In the first stage, ELM combined with auto-encoder (AE) is utilized to estimate the weight matrix between the connection layers. In the second stage, the optimization of parameters is performed by using the SSA. Case studies show that the two-stage model delivers highly accurate predictions. After subjecting the SSA-ELM-AE model to the two-stage optimization process, significant improvement has been observed in the prediction results. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Approach Using Genetic Algorithm and Genetic Programming for Remote Sensing Crop Classification 13

A Two-Stage Approach Using Genetic Algorithm and Genetic Pro...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Liang, Jing Yang, Zexuan Zhang, Tuo Bi, Ying Zhengzhou University School of Electrical and Information Engineering Zhengzhou China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang China Henan Institute of Technology School of Electrical Engineering and Automation Xinxiang China

ISBN: (纸本)9798350308365

Crop classification is an important task in remote sensing image analysis. To effectively classify crops, it is necessary to extract or obtain a set of effective features from raw pixels. However, existing methods have several limitations, including poor interpretability of the learned models and the requirements of sufficient training data and domain expertise. To address this, this paper develops a two-stage approach using Genetic Algorithm (GA) and Genetic Programming (GP) to automatically learn a feature set that can effectively classify crops using remote sensing images. In the first stage of the new approach, a GP method is applied to automatically construct a set of high-level features by evolving tree-based solutions. In the second stage, a GA method is employed to select a small subset of features from the constructed features and the original features by removing redundant ones. The performance of the new approach is evaluated on three datasets in two scenarios, i.e., classifying four main crop types and all crop types, respectively. The results demonstrate that the new approach achieves more accurate crop classification compared with eight competitive methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Evolutionary Framework for Multi-Objective Optimization 13

A Two-Stage Evolutionary Framework for Multi-Objective Optim...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Chen, Peng Liang, Jing Qiao, Kangjia Suganthan, Ponnuthurai Nagaratnam Ban, Xuanxuan School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China School of Electrical Engineering and Automation Henan Institute of Technology Xinxiang China Kindi Computing Research Center Qatar University Doha Qatar

ISBN: (纸本)9798350308365

In the field of evolutionary multi-objective optimization, the approximation of the Pareto front (PF) is achieved by utilizing a collection of representative candidate solutions that exhibit desirable convergence and diversity. Although several multi-objective evolutionary algorithms (MOEAs) have been designed, they still have difficulties in keeping balance between convergence and diversity of population. To better solve multi-objective optimization problems (MOPs), this paper proposes a Two-stage Evolutionary Framework For Multi-objective Opti-mization (TEMOF). Literally, algorithms are divided into two stages to enhance the search capability of the population. During the initial half of evolutions, parental selection is exclusively conducted from the primary population. Additionally, we not only perform environmental selection on the current population, but we also establish an external archive to store individuals situated on the first PF. Subsequently, in the second stage, parents are randomly chosen either from the population or the archive. In the experiments, one classic MOEA and two state-of-the-art MOEAs are integrated into the framework to form three new algorithms. The experimental results demonstrate the superior and robust performance of the proposed framework across a wide range of MOPs. Besides, the winner among three new algorithms is compared with several existing MOEAs and shows better results. Meanwhile, we conclude the reasons that why the two-stage framework is effect for the existing benchmark functions. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimization and Characterization of High-efficiency Induction Motors With Flat Wires

Optimization and Characterization of High-efficiency Inducti...

引用

IEEE Conference and Expo Transportation Electrification Asia-Pacific (ITEC Asia-Pacific)

作者： Hengming Zhang Haichao Feng Jinling Lv Xiaozhuo Xu Wei Hua School of Electrical Engineering and Automation Henan Polytechnic University Jiaozuo China School of Electrical Engineering Southeast University Nanjing China

ISBN: (数字)9798331529277

ISBN: (纸本)9798331529307

Aiming at the demand of high efficiency and low cost of the drive source motor in the field of new energy vehicles, a flat-wire induction motor is designed as the drive source motor in this paper. The design aims to improve the characteristics of the induction motor such as slot fullness, efficiency, power density and starting performance. The motor is electromagnetically designed and characterized by the design specifications of the motor under different working conditions. In order to improve the starting performance of the motor, the symmetric convex slot structure is optimized to maximize the skin effect to improve the starting performance of the motor. Simulation results show that the optimized flat-wire induction motor meets the overall performance specifications under different operating conditions and can be better used as a drive source for electric vehicles.

关键词： Employee welfare Power system measurements Induction motors Simulation Wires Transportation Electrification Electric vehicles Skin effect Optimization

来源：评论

学校读者我要写书评

暂无评论

Research on Low Frequency Stability of Photovoltaic Connected High Speed Traction Power Supply System in Light Load Scenarios 5

Research on Low Frequency Stability of Photovoltaic Connecte...

引用

5th IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2025

作者： Yang, Yixia Wang, Ying Li, Jiahao Xie, Ziyun Mu, Xiuqing Wang, Wenwen College of Intelligent Manufacturing Gansu Industry Polytechnic College Tianshui China School of Automation and Electrical Engineering Lanzhou Jiaotong University Lanzhou China

ISBN: (纸本)9798331533694

Low-frequency oscillations are a common issue in traction power supply systems, and the integration of photovoltaic (PV) systems exacerbates the coupling and nonlinearity within these systems, leading to a complex photovoltaic-Train-network coupled system that increases the likelihood of electrical parameter mismatches. This paper investigates the low-frequency stability of the system during the photovoltaic integration process under light-load conditions in a single-Arm traction power system. The study first analyzes the topology and operational principles of integrating photovoltaic systems into the traction power supply system via a back-To-back inverter. Small-signal modeling techniques are then employed to derive the mathematical models of the photovoltaic system, the back-To-back inverter, and the train-network system. Based on the source-load relationship and the equivalent impedances of each subsystem, the coupling matrix of the photovoltaic-Train-network system is established. The low-frequency stability of the system under the light-load scenario is analyzed, and the effects of various control strategies of the photovoltaic system on system stability are assessed using the extended forbidden zone criterion. Finally, the effectiveness of the stability analysis is verified through StarSim HIL semi-physical testing. © 2025 IEEE.

关键词： Frequency stability

来源：评论

学校读者我要写书评

暂无评论

Optimization and Characterisation of Flat-wire Permanent Magnet Motors for Electric Vehicles

Optimization and Characterisation of Flat-wire Permanent Mag...

引用

IEEE Conference and Expo Transportation Electrification Asia-Pacific (ITEC Asia-Pacific)

作者： Jinling Lv Haichao Feng Hengming Zhang Xiaozhuo Xu Wei Hua School of Electrical Engineering and Automation Henan Polytechnic University Jiaozuo China School of Electrical Engineering Southeast University Nanjing China

ISBN: (数字)9798331529277

ISBN: (纸本)9798331529307

Permanent magnet synchronous motors (PMSMs) are favoured in the field of electric vehicles because of their advantages such as high power density and high efficiency. In this paper, a flat wire winding is applied to a PMSM, and a flat-wire PMSM is designed to improve the slot fullness and heat dissipation performance, and further enhance the motor performance. According to the design index of the motor, the motor structure and preliminary electromagnetic parameters are determined. A finite element model of the motor is established to analyse the influence of the stator and rotor structural parameters on the torque and torque ripple of the motor, and the rotor auxiliary slot is used to reduce the torque ripple. The electromagnetic characteristics of the motor are studied and analysed, and the efficiency Map is drawn to obtain the highest efficiency of 96.55%, and the percentage of the efficient operation area with an efficiency greater than 85% is 91.5%. The results show that the motor meets the design indexes and the needs of electric vehicle drive motors, and provides a basis for the design of this type of motor.

关键词： Windings Stator windings Rotors Motors Electric vehicles Permanent magnet motors Finite element analysis Wire Torque measurement Electromagnetics

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：