检索结果-内蒙古大学图书馆

Pedestrian trajectory prediction method based on automatic driving

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 9291-9310页

作者： Huang, Mengtao Wang, Jiaxuan College of Electrical and Control Engineering Xi’an University of Science and Technology Xi’an China Xi’an Key Laboratory of Electrical Equipment Condition Monitoring and Power Supply Security Xi’an China

Pedestrian trajectory prediction plays a crucial role in autonomous driving, as its accuracy directly affects the autonomous driving system’s comprehension of the environment and subsequent decision-making processes. Current trajectory prediction methods tend to oversimplify pedestrians to mere point coordinates, utilizing positional information to infer interactions among individuals while overlooking the temporal correlations between them, thereby excessively simplifying pedestrian characteristics. To address the aforementioned issues, this paper proposes a trajectory prediction model for autonomous driving applications, that takes into account both pedestrian motion characteristics and scene interaction. The model optimizes the LSTM unit structure twice, serving to learn correlations among long trajectories of pedestrians and to integrate multiple forms of information into the neighborhood interaction module. Furthermore, our model introduces dual attention mechanisms for individuals and scenes, focusing on the key motion points of individual pedestrians and their interactive behavior with others in busy scenarios. The efficacy of the model was validated on the MOT16 pedestrian dataset and the Daimler pedestrian path prediction dataset, outperforming mainstream methods with 8% and 10% reductions in Average Displacement Error and Final Displacement Error respectively. © 2024 – IOS Press. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Interaction between Neighboring Supercritical Water Molecules and Density Fluctuation by Molecular Dynamics Simulations

引用

Journal of Thermal Science 2022年第3期31卷 907-922页

作者： WANG Yan XU Jinliang MA Xiaojing Key Laboratory of Condition Monitoring and Control for Power Plant Equipment of Ministry of Education North China Electric Power UniversityBeijing102206China Beijing Key Laboratory of Multiphase Flow and Heat Transfer North China Electric Power UniversityBeijing102206China

Supercritical water(scW)is important for various engineering *** structure and distribution of sc W is key to dominate the related processes and ***,scW is investigated using molecular dynamics(MD)simulation with controlled pressure and *** oscillation is observed to occur in a 1 nm thickness bin,indicating mass exchange of particles across the bin *** show that the low density scW behaves strong *** analysis of system density fluctuations is performed by square root error and maximum structure factor,demonstrating the agreement between the two *** scW molecules are tightly gathered to form“liquid island”locally,but are very sparse in other regions,which are similar to the gas-liquid mixture in subcritical pressure.A target molecule is tracked to plot 3D displacements and rotating angles,with the former indicating large amplitude ballistic(diffusing)motion and small amplitude oscillation,and the latter displaying two scales of angle *** translation and rotating motion are related to hydrogen bond break up and *** low density scW behaves isolated molecules with few combinations of hydrogen bonds between molecules,while the high density scW behaves more combinations of molecules via hydrogen *** two scales motion is expected to influence thermal/chemical process in supercritical state,deepening the fundamental understanding of scW structure.

关键词： supercritical water molecular dynamics density hydrogen bond translation and rotating motion

来源：评论

学校读者我要写书评

暂无评论

A Road Crack Detection Method based on Improved U-Net 4

A Road Crack Detection Method based on Improved U-Net

引用

4th International Conference on Computer Vision and Data Mining, ICCVDM 2023

作者： Chen, Yi College of Electrical and Control Engineering Xi’an University of Science and Technology Xi’an China Xi’an Key Laboratory of Electrical Equipment Condition Monitoring and Power Supply Security Xi’an China

ISBN: (纸本)9781510674448

Cracks in infrastructure engineering projects have a significant impact on the performance and functionality of roads, bridges, and buildings. Traditional crack detection methods are time-consuming and subjective, thus calling for faster and more accurate detection methods. This paper proposes a novel algorithm called the Multi-Layer Supervised Network, which combines the U-Net model and deformable convolution to address the challenges in crack detection. Our method utilizes the encoder-decoder architecture of the U-Net model to extract crack features and addresses the issues of gradient vanishing and overfitting through a multi-layer supervised mechanism. Meanwhile, the deformable convolution is introduced to be able to deal with different scales and angles of cracks adaptively and improve the feature expression capability. The experimental results demonstrate that our proposed method can accurately detect and segment cracks in images with good generalization ability. Compared to traditional image classification and object detection methods, our approach can extract more accurate crack information, providing valuable insights for the evaluation and maintenance of infrastructure engineering projects. © 2024 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Distinct facets to enhance the process of hydrogen production via methanol steam reforming-a review

引用

Energy Storage and Saving 2022年第1期1卷 53-69页

作者： Hangyu Yu Yuanzhi Li Chao Xu Fei Jin Feng Ye Xin Li Key Laboratory of Condition Monitoring and Control for Power Plant Equipment of MOE North China Electric Power UniversityHuilongguanBeijing102206China Key Laboratory of Solar Thermal Energy and Photovoltaic System Institute of Electrical EngineeringChinese Academy of SciencesBeijing100190China

Methanol steam reforming manifests great potential for generating hydrogen owing to its lower reaction temper-ature(200-300°C)and higher hydrogen/carbon ratio comparing with ethanol and methane *** this case,methanol steam reforming is applied in various renewable energy systems to assist the energy conversion and improve the system *** performance of methanol steam reforming reaction strongly depends on the catalysts and reactor *** this paper,the development of the copper-based,the noble metal-based and the nanomaterial catalysts were summarized by analyzing the effects of different modification methods,which indicates that cutting the cost and simplifying the manufacturing process are the future goal of catalyst ***,the reaction mechanism of different catalyst types was *** the reactor performance,conventional,miniature,micro,and membrane reactors were discussed and compared,where conventional reac-tor with high CO tolerance is more suitable for industrial application while membrane reactor with high H 2 purity and compact structure is ideal for fuel cell *** integration of the methanol steam reforming system into renewable power systems was reviewed as *** steam reforming technology is of great potential in exhaust heat recovery,cogeneration system and other renewable energy field,where more comprehensive researches should be performed.

关键词： Methanol steam reforming Catalyst modification Reactor design System integration Hydrogen

来源：评论

学校读者我要写书评

暂无评论

Research on Detection and Protection Technology of DC Residual Current 5

Research on Detection and Protection Technology of DC Residu...

引用

5th International Conference on Clean Energy and Electric power Engineering, ICCEPE 2024

作者： Gao, Shuping Xu, Kai College of Electrical and Control Engineering Xi'an University of Science and Technology Shaanxi Xi'an China Xi'an Key Laboratory of Electrical Equipment Condition Monitoring and Power Supply Security Shaanxi Xi'an China

ISBN: (纸本)9798350390315

In view of the nonlinear characteristics of DC residual current, the frequency slice wavelet transform method is proposed to deal with DC residual current, and the fault characteristics of DC residual current are extracted by time-frequency domain combination method. The waveform of DC residual current can be identified through the characteristics, and then the corresponding threshold value is set for different DC residual current according to the requirements of national standard. The line breaker acts to protect the circuit when the threshold is exceeded. Simulation analysis shows that the waveform extracted by this method has obvious characteristics and can effectively identify the DC residual current waveform to protect the line. © 2024 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Numerical modeling of droplets injection in the secondary flow of the wet steam ejector in the refrigeration cycle

引用

INTERNATIONAL JOURNAL OF REFRIGERATION 2022年 136卷 103-113页

作者： Dadpour, Daryoush Lakzian, Esmail Gholizadeh, Mohammad Ding, Hongbing Han, Xu [a]Center of Computational Energy Department of Mechanical Engineering Hakim Sabzevari University Sabzevar Iran [b]Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin 300072 China [c]Key Lab of Condition Monitoring and Control for Power Plant Equipment North China Electric Power University Ministry of Education Baoding 071003 China

Steam ejector plays a key role in the refrigeration system. The water has been used as a working fluid because water is more economical and non-toxic. The operating fluid often enters the evaporator as a water liquid and droplets evaporate by absorbing heat. Cooling load changing causes the vapor in the outlet of the evaporator to be accompanied by droplets. Therefore, there are droplets at the inlet of secondary nozzle and flow should be simulated as a wet steam flow with injection droplets at the secondary flow. In this paper, the effects of droplets injection at secondary flow have been investigated on the performance of the refrigeration cycle. For this purpose, the Eulerian-Eulerian method has been used and the results have been validated with experimental data. Six cases are considered with different wetness and number of droplets in the secondary flow. The results of case 6 show COP, T-outlet, and ER decrease about 22.93%, 15.66%, and 22.93%, respectively. In addition, the steam accompanies by droplets at the outlet of ejector. Therefore, it is essential for designers and operators to model and consider the effects of the droplets on the wall erosion to optimize the wet steam ejector and refrigeration cycle performance.

关键词： Wet steam ejector Refrigeration cycle Droplets injection COP ER

来源：评论

学校读者我要写书评

暂无评论

Exergoeconomic Analysis and Multi-Objective Optimization Using Nsga-Ii in a Novel Dual-Stage Selexol Process of Integrated Gasification Combined Cycle

SSRN

引用

SSRN 2023年

作者： Mei, Weiguang Zhai, Rongrong Zhao, Yingxin Yao, Zhiqiang Ma, Ning Key Laboratory of Condition Monitoring and Control for Power Plant Equipment Ministry of Education North China Electric Power University Beijing102206 China

To alleviate the problem of global climate change and provide a new perspective of carbon recovery, a novel configuration of H2S concentrator adopting pressure drop method and self-stripping method in dual-stage Selexol process of integrated gasification combined cycle is developed in this study. Comprehensive thermodynamic and exergoeconomic analysis are presented for the novel Selexol process. The SPECO (Specific Exergy Costing) method is employed to solve the exergoeconomic analysis of the dual-stage Selexol process, the specific exergy cost of each stream is calculated, and exergoeconomic analysis are carried out for each component. The ideal condition of components in the context of exergoeconomic analysis is defined, and the concrete improvement directions and methods of components which are not in ideal condition are given. Towards the exergoeconomic analysis, the multi-objective optimization of the model is carried out by using the Non-dominant Sorting Genetic Algorithm-II (NSGA-II) in conjunction with Aspen Plus. Besides, the ideal optimal point method is applied to the Pareto frontier in this study to get the optimal operating conditions according to the three targets for actual operation. The results of three cases turn out that only the case of CO2 capture efficiency and total exergy efficiency has competing relationship. © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Research on detection and protection technology of DC residual current 3

Research on detection and protection technology of DC residu...

引用

2024 3rd International Conference on power System and Energy Technology, ICPSET 2024

作者： Yang, Ruixiong Chen, Yong Xu, Kai Gao, Shuping Guangdong Power Grid Co. Ltd. DC Distribution Power Research Center Guangdong Zhuhai519000 China College of Electrical and Control Engineering Xi’an University of Science and Technology Shaanxi Xi’an710600 China Xi’an Key Laboratory of Electrical Equipment Condition Monitoring and Power Supply Security Shaanxi Xi’an710600 China

To realize that the residual current device can accurately and quickly detect the fault when the fluctuating DC residual current occurs in the system and improve the system’s safety, a DC residual current detection and protection method based on VMD was proposed. Particle Swarm Optimization (PSO) was used to optimize the penalty factor and the number of decomposition layers of VMD. The minimum envelope entropy of the residual current signal is used as the fitness function to obtain the optimal combination. The criterion of fault occurrence is established based on the optimal modal component mutation characteristic of the residual current decomposed by VMD. Experiments show that this method can identify faults quickly and effectively when pulsating DC residual current is generated in the system. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Research on Detection and Protection Technology of DC Residual Current 3

Research on Detection and Protection Technology of DC Residu...

引用

3rd International Conference on Electrical Engineering and control Science, IC2ECS 2023

作者： Yang, Ruixiong Chen, Yong Xu, Kai Gao, Shuping Guangdong Power Grid Co. Ltd. Dc Distribution Power Research Center Guangdong Zhuhai China College of Electrical and Control Engineering Xi'an University of Science and Technology Shaanxi Xi'an China Xi'an Key Laboratory of Electrical Equipment Condition Monitoring and Power Supply Security Shaanxi Xi'an China

ISBN: (纸本)9798350382426

At present, the waveforms generated in the power system are more and more complex, not only a single sinusoidal current, the pulsating DC component and the smooth DC component are often generated when the fault occurs. But the traditional AC residual current protector can only detect the AC residual current, and can not protect this complex waveform signal. In this paper, the pulsating DC residual current is studied, and a residual current detection method based on Fourier transform is proposed. It can effectively identify the residual current waveform, and set threshold according to different waveforms. It can accurately detect the residual current, but its anti-interference ability is poor. In order to solve the problem of anti-interference, a residual current detection method based on Kalman filter is proposed. The predicted value of Kalman filter is obtained after the generated residual current is filtered, and the threshold of the action of the system protection device can be set according to the predicted value. Simulation results show that this method can effectively improve the anti-interference ability of the system. © 2023 IEEE.

关键词： Fourier transform Kalman filtering Pulsating DC residual current

来源：评论

学校读者我要写书评

暂无评论

DC Microgrid Arc Fault Diagnosis Based on Feature Frequency Extraction and Kernel Extreme Learning Machine

DC Microgrid Arc Fault Diagnosis Based on Feature Frequency ...

引用

2025 International Conference on Electrical Automation and Artificial Intelligence, ICEAAI 2025

作者： Yang, Ruixiong Chen, Yong Zeng, Yingjie Gao, Shuping China Guangdong Power Grid Co. Ltd. DC Distribution Power Research Center Zhuhai519000 China College of Electrical and Control Engineer Xi'an University of Science and Technology Xi'an710054 China Xi'an Key Laboratory of Electrical Equipment Condition Monitoring and Power Supply Security Xi'an710054 China

ISBN: (纸本)9798331506797

To address the challenge of series arc fault detection in DC microgrid systems, this research proposes an arc fault diagnosis approach based on feature frequency extraction and kernel extreme learning machine (KELM). The arc fault characteristic frequency is chosen by means of the signal's variational mode decomposition (VMD) and Hilbert marginal spectrum (HMS) analysis. The singular value, sample entropy, and energy entropy of the modal component that corresponds to the eigenfrequency are computed in order to generate the eigenvector. Subsequently, the KELM is utilized for arc fault diagnosis. Experimental results demonstrate that the proposed method effectively extracts fault characteristics, achieving a recognition accuracy of 98.26% in arc fault diagnosis. © 2025 IEEE.

关键词： arc fault DC microgrid fault diagnosis Hilbert marginal spectrum kernel extreme learning machine

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：