检索结果-内蒙古大学图书馆

2023 Tianjin University-IET Electrical and Information Engineering Doctoral Forum, TJU IET 2023

作者： Jin, Sheng Meng, Qinghao Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin University Tianjin China

ISBN: (纸本)9781839539824

This paper proposes a novel approach for visual simultaneous localization and mapping (vSLAM), called Saliency-SLAM. This method effectively emulates the visual attention mechanism by integrating a saliency prediction model. In contrast to conventional vSLAM methods, which treat all feature points as equally significant, salient feature points are given greater importance in Saliency-SLAM. Therefore, we construct a novel saliency dataset specifically for vSLAM task to train a saliency prediction model by integrating multi-level visual information. Then, we propose to use the salient value of predicted result as the weight of significance for the feature points during the optimization process. Exhaustive experiments have been conducted on the KITTI dataset, demonstrating that our proposed method outperforms existing approaches in terms of localization accuracy. © The Institution of Engineering & technology 2023.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Traj-LLM: A New Exploration for Empowering Trajectory Prediction With Pre-Trained Large Language Models

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-14页

作者： Lan, Zhengxing Liu, Lingshan Fan, Bo Lv, Yisheng Ren, Yilong Cui, Zhiyong School of Transportation Science and Engineering Beihang University Beijing China Beijing Key Laboratory of Traffic Engineering College of Metropolitan Transportation Beijing University of Technology Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Transportation Science and Engineering State Key Lab of Intelligent Transportation System Beihang University Beijing China

Predicting the future trajectories of dynamic traffic actors is a cornerstone task in autonomous driving. Though existing notable efforts have resulted in impressive performance improvements, a gap persists in scene cognitive and understanding of complex traffic semantics. This paper proposes Traj-LLM, the first to investigate the potential of using pre-trained Large Language Models (LLMs) without explicit prompt engineering to generate future motions from vehicular past trajectories and traffic scene semantics. Traj-LLM starts with sparse context joint encoding to dissect the agent and scene features into a form that LLMs understand. On this basis, we creatively explore LLMs' strong understanding capability to capture a spectrum of high-level scene knowledge and interactive information. To emulate the human-like lane focus cognitive function and enhance Traj-LLM's scene comprehension, we introduce lane-aware probabilistic learning powered by the Mamba module. Finally, a multi-modal Laplace decoder is designed to achieve scene-compliant predictions. Extensive experiments manifest that Traj-LLM, fueled by prior knowledge and understanding prowess of LLMs, together with lane-aware probability learning, transcends the state-of-the-art methods across most evaluation metrics. Moreover, the few-shot analysis serves to substantiate Traj-LLM's performance, as even with merely 50% of the dataset, it surpasses the majority of benchmarks relying on complete data utilization. This study explores endowing the trajectory prediction task with advanced capabilities inherent in LLMs, furnishing a more universal and adaptable solution for forecasting agent movements in a new way. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Motion Characteristics of Control Rod Drive Mechanism Based on Correction of Electromagnetic Force Calculation Deviation 17th

Motion Characteristics of Control Rod Drive Mechanism Based ...

引用

17th Annual Conference of China Electrotechnical Society, CES 2022

作者： Qian, Wang Qiwei, Xu Yun, Yang Yangming, Chen Shaolin, Li Sheng, Liu State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing University Chongqing China

ISBN: (纸本)9789819904501

With the rapid development of advanced technologies such as digital prototype of the Control Rod Drive Mechanism, it is necessary to simulate the operation process of the Drive Mechanism in real time, which needs to be realized based on the mathematical model of the electromagnetic force. The electromagnetic force formula of the Drive Mechanism derived from Maxwell’s suction formula has the problems of inaccurate calculation results, so a deviation correction method for electromagnetic force calculation is proposed. Taking the transient electromagnetic field simulation results of the Finite Element Method as the optimization objective, the parameter of the fixed reluctance value in the mathematical model of the electromagnetic force is modified by the Least Square Fitting Method. The corrected electromagnetic force error is reduced from 30.0% to 1.2%. A multi physical field kinematics simulation model is built based on MATLAB/Simulink software to obtain the force and motion state of the lift armature. Compared with the traditional finite element simulation method combined with multiple software, the proposed scheme not only ensures the calculation accuracy, but also greatly improves the calculation speed. © 2023, Beijing Paike Culture Commu. Co., Ltd.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Data-Efficient Synchronous Machine Winding Short Circuit Faults Diagnosis Based on Frequency Response Analysis and Active Learning

引用

IEEE Sensors Journal 2025年第11期25卷 19804-19815页

作者： Chen, Yu Zhao, Zhongyong Liu, Jiangnan Wang, Wei Yao, Chenguo Huazhong University of Science and Technology State Key Laboratory of Advanced Electromagnetic Technology School of Electrical and Electronic Engineering Wuhan430074 China Southwest University College of Engineering and Technology Chongqing400716 China Yibin Academy of Southwest University Sichuang64400 China Guangzhou Power Supply Bureau of Guangdong Power Grid Co. Ltd Guangzhou510620 China Chongqing University State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing400044 China

Winding short-circuit (SC) faults are a prevalent issue in synchronous machines, and the accurate and timely identification of these faults is critical for maintaining power system stability. Current methods for inspecting synchronous machine windings often rely on periodic inspections based on human expertise. Numerous studies have explored the application of deep learning (DL) models for detecting synchronous machine winding SC faults. However, these models often exhibit excessive complexity and overlook physical overhead, leading to inefficient utilization of computational power and data resources. To address these limitations, this study proposes a dual-channel deep learning (DL) model integrated with the active learning (AL) query strategy. In this study, winding SC faults are manually simulated on a 5 kVA synchronous machine, and corresponding frequency response analysis (FRA) data are recorded. Subsequently, the proposed method is validated on the test set and benchmarked against previous studies. Experimental results demonstrate that the proposed method significantly reduces the data annotation effort and accelerates model training to the order of seconds (under 5 seconds) while maintaining satisfactory accuracy (≥ 95%). Comparative experimental results further indicate that the proposed model, requiring only 1/20th of the labeled training samples used in previous studies, achieves a substantial reduction of approximately 99.8% in both model parameters and training time. © 2001-2012 IEEE.

关键词： Synchronous machinery

来源：评论

学校读者我要写书评

暂无评论

Ultrasound Plane Wave Reference Frame Multi-Hypothesis Prediction Reconstruction

Ultrasound Plane Wave Reference Frame Multi-Hypothesis Predi...

引用

2023 IEEE International Ultrasonics Symposium, IUS 2023

作者： Tong, Lin Wang, Ping Li, Xitao Li, Qianwen Chen, Jinghan Shen, Yue Chongqing University State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing China

ISBN: (纸本)9798350346459

The emergence of ultrasound plane wave technology has driven the development of ultrasonic ultrafast frame rate imaging technology. However, simultaneously, it has placed an increased burden on hardware sampling, transmission, and data storage. Compressed sensing technology is widely employed in ultrasound sparse sampling and imaging. However, it faces challenges in effectively recovering useful signals when the sampling rate is low or the echo noise is excessive. Based on the characteristics of ultrasound echo signals, this paper employs a multi-hypothesis prediction method to reconstruct correlated echo signals. This approach can efficiently reconstruct ultrasound echo signals while reducing the reliance on the sparsity of the original echo signals. On PICMUS experimental data, the image similarity surpasses that of methods relying solely on sparsity or both sparsity and correlation. Without compromising image quality, this paper's method accomplishes signal compression and reconstruction from the perspective of signal correlation. © 2023 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Coordinated Frequency Control Strategy of Offshore Wind Farm via MMC-HVDC Considering Secondary Frequency Drop 26

Coordinated Frequency Control Strategy of Offshore Wind Farm...

引用

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

作者： Zhou, Zhiting Li, Hui Tan, Hongtao Chongqing University State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing China

ISBN: (纸本)9798350317589

Offshore wind farm (OWF) integrated into the onshore grid through Modular Multilevel Converter-based high-voltage direct current (MMC-HVDC) cannot respond to the frequency changes of the onshore grid system under conventional control methods. Furthermore, the wind turbine contributes to frequency regulation by releasing the kinetic energy stored in the rotor, which may cause a secondary frequency drop (SFD) during speed recovery. Therefore, this paper proposes a coordinated frequency control strategy for OWF-MMC-HVDC considering SFD. Firstly, considering the DC voltage fluctuation limit, the coupling relationship between the frequency of onshore grid system and the DC voltage of grid-side converter station is established, and it actively participates in the system frequency control by changing the DC voltage reference value. Secondly, we develop a frequency transfer model for OWF that considers the losses in submarine cables. Additionally, we design a variable-rate speed recovery function, which not only shortens the speed recovery time but also mitigates the occurrence of SFD. Through simulations involving load increases and wind speed fluctuations, we validate that the proposed control strategy successfully prevents SFD. © 2023 IEEE.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Effect of Thermal Field on Moisture Distribution Characteristics of Ester Oil-paper Insulation Interface: Insights From Molecular Dynamics 22

Effect of Thermal Field on Moisture Distribution Characteris...

引用

22nd IEEE International Conference on Dielectric Liquids, ICDL 2023

作者： Zhou, Jian Wang, Feipeng Wang, Qiang Chongqing University State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing China

ISBN: (纸本)9798350302172

Ester insulating oils, which are used in environmentally friendly transformers, have been found to exhibit different performance characteristics from traditional mineral insulating oils due to their molecular structure. The mechanisms behind the thermal aging of ester oil-paper insulation systems are being investigated, with moisture being identified as a significant factor that impacts insulation. However, it is difficult to observe the dynamics of moisture at the oil-paper insulation interface through macroscopic experiments. In this study, the authors used molecular dynamics simulations to model the diffusion behavior of moisture at the interface of ester oil-paper insulation at various temperatures (298-373 K). The results showed that at 298 K, water molecules in the ester insulating oil tend to form clusters, but as the temperature increases, these molecules diffuse from the oil to the paper and accumulate at the oil-paper interface. The diffusion coefficient of water molecules in the normal direction of the interface was found to be significantly smaller than its tangential direction diffusion coefficient, with a minimum value at 343 K. The authors also observed that the binding capacity of the insulating oil to water molecules decreases with increasing temperature as the molecules diffuse from the oil to the paper. These findings provide valuable data for improving our understanding of the thermal aging of ester oil-paper insulation systems and may inform the design of experimental prediction and testing schemes for this system. © 2023 IEEE.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Squeezing More Past Knowledge for Online Class-Incremental Continual Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 722-736页

作者： Da Yu Mingyi Zhang Mantian Li Fusheng Zha Junge Zhang Lining Sun Kaiqi Huang the State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150080China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190the School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100049 the CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China IEEE

Continual learning(CL)studies the problem of learning to accumulate knowledge over time from a stream of data.A crucial challenge is that neural networks suffer from performance degradation on previously seen data,known as catastrophic forgetting,due to allowing parameter *** this work,we consider a more practical online class-incremental CL setting,where the model learns new samples in an online manner and may continuously experience new ***,prior knowledge is unavailable during training and *** works usually explore sample usages from a single dimension,which ignores a lot of valuable supervisory *** better tackle the setting,we propose a novel replay-based CL method,which leverages multi-level representations produced by the intermediate process of training samples for replay and strengthens supervision to consolidate previous ***,besides the previous raw samples,we store the corresponding logits and features in the ***,to imitate the prediction of the past model,we construct extra constraints by leveraging multi-level information stored in the *** the same number of samples for replay,our method can use more past knowledge to prevent *** conduct extensive evaluations on several popular CL datasets,and experiments show that our method consistently outperforms state-of-the-art methods with various sizes of episodic *** further provide a detailed analysis of these results and demonstrate that our method is more viable in practical scenarios.

关键词： Catastrophic forgetting class-incremental learning continual learning(CL) experience replay

来源：评论

学校读者我要写书评

暂无评论

Investigation of Non-local Thermodynamic Equilibrium Effects of Medium Voltage AC Air Arc 4

Investigation of Non-local Thermodynamic Equilibrium Effects...

引用

4th IEEE International Conference on Electrical Materials and Power Equipment, ICEMPE 2023

作者： Zhou, Tong Yang, Qing Yuan, Tao Chongqing University State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing China

ISBN: (纸本)9798350334678

The medium-voltage (MV) power distribution networks have a complex topology, and this can easily cause air arc faults. However, the current of the air arc is low, and the arc temperature is only a few thousand Kelvin. In this case, the arc is in non-local thermodynamic equilibrium (non-LTE). The LTE state of arc is the basis for the establishment of arc model and the calculation of transport coefficient. In this paper, the non-LTE effect of the MV AC air arc is studied by the moiré deflection and the optical emission spectroscopy (OES) techniques. © 2023 IEEE.

关键词： Optical emission spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Interaction Mechanism Analysis and Synchronization Stability Control for Paralleled PLL-VSCs system during LVRT

Interaction Mechanism Analysis and Synchronization Stability...

引用

2023 IEEE International Conference on Power Science and technology, ICPST 2023

作者： Huang, Sen Yao, Jun Lin, Yongchao Luo, Yi Chongqing University State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing China

ISBN: (纸本)9798350311358

Due to the weak immunity of power electronic devices, the phase-locked loop-synchronized voltage source converters (PLL-VSCs) face severe transient instability risk during low voltage ride through (LVRT). Unlike the existing research, this paper takes a paralleled PLL-VSCs system as the study object and discusses the interaction mechanism between the PLL-VSCs. It is found that the interaction between PLL-VSCs is determined by the mutual-impedance voltage drop, which is mainly affected by different current injection angles during LVRT. And then, in order to ensure the best transient stability of the paralleled system, a current optimization control strategy is proposed. Finally, the correctness of the theoretical analysis and the effectiveness of the proposed strategy are validated by simulations. © 2023 IEEE.

关键词： Transients

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：