检索结果-内蒙古大学图书馆

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Chang, Shuyuan Wang, Liyong Yang, Li Zhang, Jinle Beijing Key Laboratory of Advanced Manufacturing Technology Beijing University of Technology Beijing100124 China Key Laboratory of Modern Measurement and Control Technology in Ministry of Education Beijing Information Science and Technology University Beijing100192 China Science and Technology on Vehicle Transmission Laboratory China North Vehicle Research Institute Beijing100072 China

ISBN: (纸本)9781837242672

In practical rotating machinery fault diagnosis (FD) tasks, the scarcity of labeled fault data often impedes the model's ability to learn effective classification boundaries, resulting in poor performance with limited training samples. To address this issue, this paper introduces a rotation machinery few-shot FD algorithm based on a Relational Attention Network (RAN). The network comprises four modules: feature embedding, feature concatenation, attention computation, and relation computation. RAN achieves a large-margin feature space by utilizing extended concatenation and attention on feature pairs. Specifically, the feature embedding module extracts signal features and constructs both a prototype-query feature pair matrix and a query-query feature pair matrix. Subsequently, the attention computation module assigns higher weights to indistinguishable heterogeneous feature pairs within the two matrices. Finally, the attention-weighted feature pair matrices are fed into the relation computation module to generate a relation score matrix. The effectiveness and superiority of this method were validated on a bearing fault dataset. Experimental results demonstrate that RAN outperforms various comparison methods in recognition accuracy under limited training sample conditions. © The Institution of Engineering & technology 2024.

关键词： Rotating machinery

来源：评论

学校读者我要写书评

暂无评论

A Review of the Research on the Influencing Factors of Lubrication Performance for Sliding Bearings

引用

Recent Patents on Engineering 2022年第6期16卷 38-48页

作者： Yu, Xiaodong Zhan, Shiwei Huang, Dianbin Sun, Fan Wang, Fakun Han, Fei Zhao, Yan Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology Harbin150080 China

Background: Sliding bearing is a kind of bearing that works under sliding friction, which has the characteristics of stable operation, safety and reliability, and is noiseless. With the technological progress of the machinery industry, modern machinery and equipment is developing in the direction of high speed and heavy load, its power is getting higher and higher, and the working envi-ronment is getting worse, so plain bearings are more and more widely used. Objective: In order to improve the lubricating performance of sliding bearings, the influencing factors of the lubricating performance of sliding bearings are summarized and commented on. Methods: The research progress and achievements at home and abroad are summarized from three aspects: influencing factors of lubrication performance of radial sliding bearings, thrust sliding bear-ings, and influencing factors of lubricating oil on lubrication performance of sliding bearings, which provides reference for the future development of sliding bearings. Results: The study discusses the experimental method, simulation process, and experimental results of the factors affecting the lubrication performance of sliding bearing. Conclusion: The texture, deformation, surface morphology of oil cavity, eccentric load, and flow state of sliding bearings all affect the lubricating performance of sliding bearings, and lubricating oil also affects the lubricating performance of sliding bearings. © 2022 Bentham Science Publishers.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

A Human-Object Interaction Behavior Recognition Algorithm Based on Transformer 5

A Human-Object Interaction Behavior Recognition Algorithm Ba...

引用

5th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2023

作者： Fang, Zhenbin Lu, Xingjian Lei, Huan Liang, Junxiong Jiao, Zeyu Zhong, Zhenyu Institute of Intelligent Manufacturing School of Automation Guangdong University of Technology Gdas Guangdong Key Laboratory of Modern Control Technology Guangzhou China Institute of Intelligent Manufacturing Gdas Guangdong Key Laboratory of Modern Control Technology Guangzhou China

ISBN: (纸本)9798350333442

Human-object interaction behavior recognition is a high-level computer vision task for computers to understand the content of images in real scenes. Thanks to the introduction of Transformer and DETR, the performance of the algorithms for human-object interaction recognition has improved significantly in the first stage, however, the existing models still suffer from inadequate feature extraction and model bias. Based on this, we optimize and improve the algorithm's performance in terms of both fine-grained contextual information extraction and dynamic weighting. We conducted training and testing on the HICO-DET dataset and found through extensive experiments that (1) our proposed fine-grained contextual information-based Human-object interaction behavior recognition algorithm improves the performance of 'Full', 'Rare' and 'Non-Rare' mAP by 2.48%, 7.42% and 1.44% respectively compared with the original algorithm. (2) During model training, we introduced dynamic weights to improve the optimization of the model for rare Human-object interaction behavior, which can effectively improve the model performance. These experimental results validate the feasibility, effectiveness and adaptability of our proposed fine-grained module, global context extraction module and dynamic weight training strategy. © 2023 IEEE.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Theoretical insights into efficient oxygen evolution reaction using non-noble metal single-atom catalysts on W_(2)CO_(2)MXene

引用

Rare Metals 2024年第10期43卷 5082-5094页

作者： Jing-Yu Zhou Zhi-Cheng Han Shu Zhao Tao Yang Da-Zhou Yan Hai-Jun Yu Institute of Advanced Battery Materials and Devices College of Materials Science and EngineeringBeijing University of TechnologyBeijing 100124China Key Laboratory of Advanced Functional Materials Ministry of EducationBeijing University of TechnologyBeijing 100124CChhiinnaa China ENFI Engineering Corporation Beijing 100038China National Engineering Research Center of Silicon-Based Materials Manufacturing Technology Luoyang 471000China

The pursuit of highly active oxygen evolution reaction(OER)catalysts,especially those free of noble metals,is a focal point in fuel cell *** extensive density functional theory calculations,this study designed and evaluated the activity and stability of singleatom catalysts(SACs)composed of 3d,4d and 5d transition metals supported on tungsten-based MXene for OER *** highlighted the exceptional OER performance of Ni@W_(2)CO_(2),Rh@W_(2)CO_(2)and Pt@W_(2)CO_(2),displaying remarkably low overpotentials The catalytic activity of TM@W_(2)CO_(2)SACs exhibited a robust correlation with surface properties,particularly the d-band center index and surface work *** Ni@W_(2)CO_(2),Rh@W_(2)CO_(2)and Pt@W_(2)CO_(2)emerged as promising candidates for OER and oxygen reduction reaction(ORR)bifunctional catalysis,while Pt@W_(2)CO_(2)and Rh@W_(2)CO_(2)showed high potential for OER and hydrogen evolution reaction(HER)bifunctional catalysis The effectiveness of tungsten-based MXene as a substrate for non-noble-metal SACs marks a breakthrough in OER catalyst design,driving advancements towards sustainable energy solutions and addressing critical challenges in energy conversion and storage.

关键词： Oxygen evolution reaction Single-atom catalysts MXene Non-noble metal Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Efficient blocked symmetric compressed sparse column method for finite element analysis

引用

Frontiers of Mechanical Engineering 2025年第1期20卷 87-104页

作者： Yingjun WANG Shijie LUO Jinyu GU Yuanfang ZHANG National Engineering Research Center of Novel Equipment for Polymer Processing The Key Laboratory of Polymer Processing Engineering of the Ministry of EducationGuangdong Provincial Key Laboratory of Technique and Equipment for Macromolecular Advanced ManufacturingSouth China University of TechnologyGuangzhou 510641China Shien-Ming Wu School of Intelligent Engineering South China University of TechnologyGuangzhou 511442China

In finite element analysis(FEA),optimizing the storage requirements of the global stiffness matrix and enhancing the computational efficiency of solving finite element equations are pivotal *** address these goals,we present a novel method for compressing the storage of the global stiffness matrix,aimed at minimizing memory consumption and enhancing FEA *** method leverages the block symmetry of the global stiffness matrix,hence named the blocked symmetric compressed sparse column(BSCSC)*** also detail the implementation scheme of the BSCSC method and the corresponding finite element equation solution *** approach optimizes only the global stiffness matrix index,thereby reducing memory requirements without compromising FEA computational *** then demonstrate the efficiency and memory savings of the BSCSC method in FEA using 2D and 3D cantilever beams as *** addition,we employ the BSCSC method to an engine connecting rod model to showcase its superiority in solving complex engineering ***,we extend the BSCSC method to isogeometric analysis and validate its scalability through two examples,achieving up to 66.13%memory reduction and up to 72.06%decrease in total computation time compared to the traditional compressed sparse column method.

关键词： finite element analysis global stiffness matrix blocked symmetric property memory reduction isogeometric analysis

来源：评论

学校读者我要写书评

暂无评论

Printing and electromagnetic characteristics of 3D printing frequency selective surface using graphene

引用

Journal of Materials Science & technology 2022年第16期111卷 49-56页

作者： Guo-Xiang Zhou Zhe Zhao Yan-zhao Zhang Wen-jin Liu Zhi-Hua Yang De-Chang Jia Yu Zhou Key Laboratory of Advanced Structural-Functional Integration Materials&Green Manufacturing Technology Harbin Institute of TechnologyHarbin 150001China Institute for Advanced Ceramics School of Materials Science and EngineeringHarbin Institute of TechnologyHarbin 150080China State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyHarbin 150080China

The study of Frequency Selective Surface(FSS)by Direct ink writing(DIW)has attracted much attention due to the convenience and effectiveness of 3D printing ***,the limited printing precision of DIW has heavily restricted its applications as the electromagnetic performance is highly sensitive to it,especially the precision at the ***,the ultra-high printing precision of FSS was achieved through DIW by the uniformly dispersed graphene sheets to deeply modify the rheological behavior and the steric hindrance ***,the highly precision of the printed filament width as thin as67μm with a space of only 42μm were achieved,which is difficult for conventional DIW,and no structural distortion is found after 3D printing,no matter it was 2D printed on a flat surface or the sharply skewed hook face,or even 3D printed to architectural *** to the highly improved precision,the electromagnetic performance matching between the designed model and the printed physical FSS device was perfectly achieved,reducing the center frequency error less than 0.3 GHz,and the transmission coefficient error less than *** work promises an effective and easy preparation of high-quality FSS from the aid of graphene.

关键词： Graphene 3D printing Rheological Precision Frequency selective surface

来源：评论

学校读者我要写书评

暂无评论

Polydopamine-mediated phosphoric acid functionalized carbon nano-onions/sulfonated poly (aryl ether sulfone) composite membrane with enhanced proton transport capacity and chemical durability for fuel cell at low humidity

引用

International Journal of Hydrogen Energy 2025年 144卷 262-274页

作者： Liu, Lili Tian, Yijia Hu, Yujie Wu, Zexin Yang, Pei Yan, Wei Zhang, Yuanyuan Hu, Zhaoxia Chen, Shouwen Shi, Linxing Jiangsu Key Laboratory of Function Control Technology for Advanced Materials School of Science Jiangsu Ocean University Lianyungang222005 China School of Environmental and Biological Engineering Nanjing University of Science and Technology Nanjing210094 China

In this work, phosphorylated carbon nano-onions (PD-CNOs), serving as a preeminent proton-conduction accelerator, are constructed by performing the phosphorylation on polydopamine (PDA) deposited CNOs. The optimized PD-CNOs are subsequently introduced into sulfonated poly (aryl ether sulfone) (SPAES) to obtain high-performance membranes. The characteristic nanosized PD-CNOs possess abundant functional groups, which confer the particles with good hydrophilicity and dispersivity. A series of flexible, tight, and homogeneous SPAES/PD-CNOs membranes are fabricated and evaluated for their microstructure, physicochemical-electrochemical properties and durability. The composite membranes exhibit improved mechanical properties, physicochemical stability, and proton conductivity due to better filler-matrix compatibility, stronger interfacial interactions and more consecutive proton transport pathways. Benefitting from the low zero-point energy, large hydration energy, and amphoteric character of -PO3H2 groups, the low-energy-barrier channels and hydrogen-bonding water bridges could be readily built, which translates into fast proton hopping/diffusion at low relative humidity (RH). SPAES/PD-CNOs-1.5 exhibits excellent proton conductivities of 222 mS cm−1 (90 °C, hydrous state) and 75 mS cm−1 (80 °C, 65 % RH), approximately 1.5 times and 2.0 times than that of SPAES, respectively. The power output values of SPAES/PD-CNOs-1.5 in H2/O2 fuel cells reach 760 mW cm−2 (80 °C, 100 % RH) and 550 mW cm−2 (80 °C, 60 % RH), surpassing those of SPAES (535 and 293 mW cm−2) and Nafion® 112 (722 and 501 mW cm−2);it also demonstrates high enough cell performance stability at 80 °C/60 % RH for 144 h. This work provides an effective proposal for the construction of composite membranes with outstanding proton conductivity and durability at low RH. © 2025 Hydrogen Energy Publications LLC

关键词： Composite membranes

来源：评论

学校读者我要写书评

暂无评论

A new vacuum-assisted low-pressure investment casting process for K446 alloy

引用

China Foundry 2024年第6期21卷 702-708页

作者： Lan-bo Ma Wen-jin Cheng Xin-li Guo Bing-zheng Fan Yang Guan Yi-peng Li Lei Jin Guo-yan Shui Yi-zhong Jiang Xun Sun Shenyang Research Institute of Foundry Co. Ltd.CAMState Key Laboratory of Advanced Casting TechnologiesShenyang 110022China Xi'an XAE Flying Aviation Manufacturing Technology Co. Ltd.Xi'an 710021China

Non-metallic inclusions and zyglo indications frequently occur in the superalloy castings produced through the traditional vacuum gravity investment casting process,particularly in components with thin-walled and complex structural *** vacuum-assisted low-pressure casting(VLC),a type of counter-gravity casting(CGC)method,has been developed to minimize non-metallic inclusions and zyglo indications in superalloy *** frames for gas turbines made from K446 alloy were produced semi-continuously using the VLC process and subsequently evaluated through tensile testing,chemical composition analysis,X-ray diffraction,and zyglo penetrant *** results indicate a roughly 10%improvement in tensile strength at 800℃ compared to gravity ***,no significant changes are observed in the chemical composition of the alloys from the beginning to the end of a casting campaign,indicating that the developed VLC process is viable for the engineering-scale production of superalloy *** to traditional vacuum gravity casting(GC)method,the application of VLC can reduce the numbers of non-metallic inclusions and Zyglo indications in the castings by over 80%.At the same time,it significantly shortens the production time by 3 to 5 days.

关键词： K446 alloy rectifying frame investment casting vacuum-assisted low-pressure casting process

来源：评论

学校读者我要写书评

暂无评论

Suppression of axial vibration of satellite antennas using the self-resetting frictional damper 2

Suppression of axial vibration of satellite antennas using t...

引用

2023 2nd International Conference on Materials Engineering and Applied Mechanics, ICMEAAE 2023

作者： Zhang, Yunfei Wang, Min Gao, Xiangsheng Gao, Peng Wang, Guicheng Che, Changjia Beijing Key Laboratory of Advanced Manufacturing Technology Faculty of Materials and Manufacturing Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Electrical Discharge Machining Technology Beijing100191 China

In order to solve the problems of low-profile accuracy and poor control stability of the satellite antenna due to axial coupling vibration, in this paper, a self-resetting friction damper is proposed to suppress axial vibration. Firstly, a self-resetting friction damper, with a lightweight, wide frequency band, and high energy consumption, is designed. The principle of dry friction energy loss of metal rubber (MR) and the effect of self-resetting of shape memory alloy (SMA) are used. Secondly, the vibration reduction mechanism model of the self-resetting friction damper is established, and the principle of damping energy dissipation is analysed. Finally, sinusoidal excitation tests of the components of the satellite antennas with self-resetting friction dampers are carried out. The axial vibration loss factor of the components of the satellite antenna with the self-resetting friction damper is calculated, and the vibration resistance performance of the damper is verified. Theoretical analysis and experimental results show that the self-resetting friction damper has a significant effect on suppressing the axial vibration of the components of the satellite antenna. It is feasible to install a self-resetting friction damper in the components of the satellite antenna to suppress the axial vibration. © Published under licence by IOP Publishing Ltd.

关键词： Energy dissipation

来源：评论

学校读者我要写书评

暂无评论

Intelligent Mould Design Through Knowledge-Based Recommendation System 1

引用

6th International Conference on Mechanical Engineering and Applied Composite Materials, MEACM 2023

作者： Qin, Hao Guangdong Key Laboratory of Modern Control Technology Institute of Intelligent Manufacturing Guangdong Academic of Sciences Guangzhou510070 China

ISBN: (数字)9789819716784

ISBN: (纸本)9789819716777

The efficiency and quality of a complex aluminium extrusion mould design can be largely improved based on reusing the relevant design knowledge recommended based on design context. This kind of design knowledge is embedded in engineering designers’ brain, supporting design tasks like requirement analysis, embodiment design, simulation result evaluation, which is significant in achieving intelligent design. However, it is a kind of tacit knowledge that is difficult to capture and reuse, in a way of intelligent recommendation. To fill this gap, this paper proposed a method on capturing this kind of tacit design knowledge for efficient reuse. Firstly, a knowledge representation model is built in terms of the requirement, function, behaviour, structure, and design evolution of the extrusion mould design, guiding the capture and representation of design knowledge. Then, the design context for the design knowledge is studied and constructed for the effective reuse of design knowledge. Finally, a recommendation system based on design context is designed and developed for the implementation of design reuse. The evaluation results on this method have shown its feasibility and effectiveness on design knowledge representation and reuse. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Knowledge representation

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：