检索结果-内蒙古大学图书馆

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Li, Jinyang Tong, Jiahui Gao, Guangyu Xu, Wenbin School of Computer Science and Technology Beijing Institute of Technology China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Optical Radiation Laboratory Beijing Institute of Environmental Characteristics Beijing100854 China

ISBN: (纸本)9781450398572

Traditional deep learning models firmly rely on a large amount of labeled data during pre-training. Whereas it lacks generalization in the face of unfamiliar categories. Recently, few-shot learning is a hot topic in computer vision to classify unseen classes with limited labels. A representative approach is to extract features from the support and query sets, respectively, and compare similarities via metric learning. However, convolutional neural networks often focus only on a local region and ignore the global region, which severely reduces the accuracy of the matching. Specifically, in this paper, we pile lightweight attention-based blocks in the embedding module, which combines an adaptive kernel size 2D convolutional network with a cross-channel attention mechanism to encode multi-scale features and implicitly increase the receptive field. The SE-relation module chooses to construct learnable non-linear comparators to compare the relationship utilizing channel information. Finally, we show experimental results on standard few-shot testing benchmarks such as mini-ImageNet and tiered-ImageNet to demonstrate effectiveness. © 2023 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Tension Cable Configuration and Dynamic Modeling of Truss Modular Deployable Antenna 23rd

Tension Cable Configuration and Dynamic Modeling of Truss Mo...

引用

23rd IFToMM China International Conference on Mechanism and Machine Science and engineering, IFToMM CCMMS 2022

作者： Tian, Dake Guo, Zhenwei Jin, Lu Gao, Haiming Zhang, Junwei Shi, Zuwei Hu, Anjun Zhao, Bingfeng School of Mechanical Engineering Shenyang Jianzhu University Liaoning Shenyang110168 China School of Civil Engineering Shenyang Jianzhu University Liaoning Shenyang110168 China Key Laboratory of Vibration and Control of Aero-Propulsion System of Ministry of Education Northeastern University Liaoning Shenyang110819 China

ISBN: (纸本)9789811993978

Aiming at the development needs of large-scale, modular and on-orbit assembly of satellite antenna, a hexagonal prism modular truss deployable antenna structure with strong topology and good adaptability is proposed. The structure composition and deployment principle of the antenna are expounded. In order to improve the stiffness of the configuration antenna, two types of tension cable configurations are proposed based on the structural characteristics of the hexagonal prism module. Firstly, the static analysis model of the antenna deployment state is established based on the node method, and the mechanical influence relationship between the tension cable and the antenna beams is established, and the value range of pretightening force of the tension cable is derived. Secondly, based on the coordinates of the key nodes of the antenna structure, the dynamic analysis model of the three-layer 19-module antenna support structure is established. Finally, by comparing and analyzing the dynamic characteristics of no cable, cross tension cable and parallel tension cable, the influence of tension cable configuration on antenna stiffness is verified. The analysis results show that the overall stiffness of the antenna support structure can be increased by more than 2.6 times by the two tension cable configurations, and the parallel tension cable is more indigenous to the increase of the antenna stiffness. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

Trajectory Optimization and control Method Based on Multistage Nonlinear Model Predictive control 4

Trajectory Optimization and Control Method Based on Multista...

引用

4th International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2023

作者： Zheng, Qingchun Peng, Zhi Zhu, Peihao Zhai, Ran Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin China School of Mechanical Engineering Tianjin University of Technology Tianjin China Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin China

ISBN: (纸本)9798350314526

To improve the trajectory optimization efficiency of robot manipulators, this paper proposes a novel approach for trajectory optimization and control of manipulators based on multistage nonlinear model predictive control (msNLMPC). This approach is realized by using a neural state space model as the prediction model of nonlinear model predictive control (NLMPC). The simulation results show that the actual trajectory of the manipulator in our proposed scheme coincides with the desired trajectory. The manipulator achieves the control task of following the optimal trajectory. Our proposed method improves the trajectory optimization efficiency of the robot manipulator. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A review on the catalytic pyrolysis of lipids to produce alternative aromatic hydrocarbons: Synthesis of hierarchically porous zeolites and aromatization mechanism

引用

Circular Economy 2025年第1期4卷

作者： Song, Pengye Guo, Shaojie Zuo, Menghao Wang, Xin Qiu, Huiyu Shen, Boxiong Tianjin Key Laboratory of Clean Energy and Pollution Control School of Energy and Environmental Engineering Hebei University of Technology Tianjin300401 China School of Chemical Engineering Hebei University of Technology Tianjin300130 China Hebei Engineering Research Center of Pollution Control in Power System Tianjin300401 China

Catalytic pyrolysis of non-edible lipids to produce alternative aromatic hydrocarbons is an important strategy to reduce CO2 emission in the petrochemical industry, which is hindered by coking and quick deactivation of zeolites. Hierarchically porous zeolites can mitigate this problem. In this review, the catalytic pyrolysis of non-edible lipids for aromatic hydrocarbons and the mechanism of aromatization are comprehensively summarized. First, the synthesis of hierarchically porous zeolite catalysts, including hard template methods, soft template methods, and postprocessing methods, which are necessary for further discussion of catalyst applications and aromatization mechanisms, is discussed. Hierarchically porous zeolite catalysts, which retain the excellent catalytic activity and selectivity of microporous zeolites, can essentially and substantially improve mass transfer and diffusion efficiency in zeolites to avoid fast deactivation of catalysts due to coking. Second, the application of hierarchically porous zeolites in aromatic hydrocarbon production is summarized. The loading of metal oxides in hierarchically porous zeolites can largely improve the deoxygenation performance of oxygen-containing lipid feedstocks. This review also discusses the aromatization mechanism used during catalytic pyrolysis to produce renewable liquid products. The formation of olefins or unsaturated groups and dehydrogenation are the critical steps for aromatization. Future research can prioritize the synergistic interaction between micropores and mesopores in hierarchically porous zeolite catalysts. Efforts can also be directed towards rational modification of the acidity of catalysts through methods such as surface modification and support optimization. This review provides necessary information about technologies for the sustainable transformation from fossil fuel-based aromatic hydrocarbons to bio-based aromatic hydrocarbons. © 2025 The Author(s)

关键词： Aromatization

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization of Integrated Energy system for Cchp Based on Improved Cuckoo Search Algorithm

SSRN

引用

SSRN 2024年

作者： Zheng, KaiYue Zhao, ChuanZhen School of Control Science and Engineering Key Laboratory of Intelligent Control of Electrical Equipment Tiangong University Tianjin300387 China School of Electronics & Information Engineering Tianjin Key Laboratory of Optoelectronic Detection Technology and System Tiangong University Tianjin300387 China

This paper discusses the optimization and scheduling of an integrated energy system for combined cooling, heating and power (CCHP). It seeks to provide better scheduling of device outputs in the system and to decrease the daily economic and environmental operating costs of the system. We build an integrated energy system with wind turbine, micro gas turbine, electric cooling unit and so on, and establish a multi-objective optimization model with the goal of minimizing economic and environmental costs. In addition, we propose a novel optimal scheduling method. It combines chaotic mapping and cuckoo search algorithm to address issues such as slow convergence speed and high iteration counts in traditional optimization algorithms. Finally, the improved cuckoo search algorithm is used to solve the system optimization problem. The optimization solution is implemented in the case of satisfying the constraints of equipment output and power balance. The simulation results show that the CCHP system can effectively improve the economic efficiency and reduce the pollutant emissions compared with the common micro-grid system. Furthermore, compared with other algorithms, the improved cuckoo algorithm shows much better performance in solving the model and can decrease the whole system's total cost. © 2024, 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

Numerical investigation of the critical heat flux in a 5 × 5 rod bundle with multi-grid

引用

Nuclear engineering and Technology 2022年第5期54卷 1914-1928页

作者： Liu, Wei Shang, Zemin Yang, Shihao Yang, Lixin Tian, Zihao Liu, Yu Chen, Xi Peng, Qian State Key Laboratory of Reactor System Design Technology Nuclear Power Institute of China Chengdu 610213 China School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing 100044 China

To improve the heat transfer efficiency of the reactor fuel assembly, it is necessary to accurately calculate the two-phase flow boiling characteristics and the critical heat flux (CHF) in the fuel assembly. In this paper, a Eulerian two-fluid model combined with the extended wall boiling model was used to numerically simulate the 5 × 5 fuel rod bundle with spacer grids (four sets of mixing vane grids and four sets of simple support grids without mixing vanes). We calculated and analyzed 11 experimental conditions under different pressure, inlet temperature, and mass flux. After comparing the CHF and the location of departure from the nucleate boiling obtained by the numerical simulation with the experimental results, we confirmed the reliability of computational fluid dynamic analysis for the prediction of the CHF of the rod bundle and the boiling characteristics of the two-phase flow. Subsequently, we analyzed the influence of the spacer grid and mixing vanes on the void fraction, liquid temperature, and secondary flow distribution. The research in this article provides theoretical support for the design of fuel assemblies. © 2021 Korean Nuclear Society

关键词： 5 × 5 rod bundle Critical heat flux Eulerian two-fluid model Flow boiling

来源：评论

学校读者我要写书评

暂无评论

State-of-Charge Balancing control for Battery Energy Storage systems of Near-Space Vehicles with An Electric-Thermal-Aging Coupling Model

State-of-Charge Balancing Control for Battery Energy Storage...

引用

第42届中国控制会议

作者： Zhiqiang Zuo Yunhao Du Yijing Wang Zhicheng Zhang Peng Li Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin University Key Laboratory of System Control and Information Processing Ministry of Education

State-of-charge(SoC) balancing is crucial for improving the efficiency and lifetime of the battery energy storage system in near-space vehicles. In this paper, the So C balancing control problem is investigated by a coupling battery model with electric-thermal-aging dynamics. Firstly, a system identification experiment is carried out to obtain the internal parameters of the battery. Secondly, a weight optimization index is designed by integrating the balancing speed and battery state-of-health(SoH). Then, a receding horizon control algorithm is proposed to realize multi-unit battery SoC balancing with partial swarm optimization(PSO). Finally, the effectiveness of the proposed strategy is verified by simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Identification of Boost Converter Components with Multiple Updating RLS Algorithm

Online Identification of Boost Converter Components with Mul...

引用

第42届中国控制会议

作者： Tong Zhou Zhicheng Zhang Zhiqiang Zuo Yijing Wang Peng Li Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information EngineeringTianjin University Key Laboratory of System Control and Information Processing Ministry of Education

In this paper,component parameters of the boost converter are identified online using a multiple updating recursive least squares(MURLS) *** component parameters,such as resistance,inductor inductance and capacitor capacitance,are obtained directly through the identification procedure rather than transfer function *** MURLS algorithm is applied to improve the rapidity of system identification compared to the traditional recursive least squares(RLS) algorithm,which is verified by a comparative simulation between MURLS and RLS and the simulation of a load-switching scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An end-to-end instance segmentation method based on improved ConvNeXt V2

引用

International Journal of Wireless and Mobile Computing 2024年第4期26卷 384-392页

作者： Wang, Wenlu Sun, Ying Xu, Manman Bai, Dongxu Huang, Li Zou, Chunlong Chen, Baojia Tang, Dalai Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Hubei Wuhan China College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China College of Mechanical Engineering Hubei University of Automotive Technology Hubei Shiyan China Hubei Key Laboratory of Hydroelectric Machinery Design and Maintenance China Three Gorges University Hubei Yichang China School of Computer Information Management Inner Mongolia University of Finance and Economics Hohhot China

In order to improve the efficiency of indoor mobile robots in locating and segmenting environmental instances, an instance segmentation method based on RTMDet is proposed. Firstly, the more powerful ConvNeXt V2 is used as the backbone network of the model, which improves the performance of the existing RTMDet model. Subsequently, NAS-FPN is used as a converged network to detect the network at any given time. Finally, AdamW is used as the model optimiser, which effectively solves the problem of excessive memory occupation when updating parameters and improves the performance of the model. The proposed method obtains the highest evaluation index in all cases. After training and testing on the Cityscapes data set, the recognition accuracy reaches 65.0%. © 2024 Inderscience Enterprises Ltd.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization and Termination of Sequential Prediction Maintenance and Spare Parts Ordering under Dynamic Remaining Useful Time Prediction 5

Joint Optimization and Termination of Sequential Prediction ...

引用

5th International Conference on system Reliability and Safety engineering, SRSE 2023

作者： Zhang, Yongfei Zhang, Xiaohong Yang, Tianxiang Li, Yuxin Shen, Juan Sun, Chaoli Taiyuan University of Science & Technology Taiyuan School of Economics & Management Taiyuan China Taiyuan University of Science & Technology Division of Industrial and System Engineering 030024 China Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Taiyuan030024 China

ISBN: (纸本)9798350305944

In the research of Prognostics and Health Management (PHM), prediction is a dynamic process, and the corresponding maintenance decisions are also dynamic. The problem of updating and termination decisions in dynamic sequential decision-making is a rarely studied but worthy of attention problem. To address these problems, a joint decision-making and termination problem for sequential prediction maintenance and spare parts ordering under dynamic remaining life prediction was studied. The Bayesian update and EM algorithm were used in combination to achieve dynamic remaining life and reliability prediction. An adaptive detection and sequential prediction maintenance strategy based on dynamic prediction results was developed, and a judgment criterion for decision termination was given. At the adaptive detection moment, the system balanced the cost of spare parts storage and stockout, preventive maintenance cost, and post-failure maintenance cost, and determined the optimal maintenance and spare parts ordering time. Based on the termination criterion, the truly executed maintenance and spare parts ordering time were selected from the dynamic redundant decision results. Finally, the effectiveness of the proposed strategy and method were verified through experiments. © 2023 IEEE.

关键词： Forecasting

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：