检索结果-内蒙古大学图书馆

TEPEN International Workshop on Fault Diagnostics and Prognostics, TEPEN-IWFDP 2024

作者： Zhou, Zewen Gong, Xue Zhong, Kunzuo Chen, Bingyan Feng, Guojin Hu, Zhifeng Gu, Fengshou Ball, Andrew Centre for Efficiency and Performance Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom Department of Mechanics Tianjin University Tianjin300350 China State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong University Chengdu610031 China School of Mechanical Engineering Hebei University of Technology Tianjin300401 China

ISBN: (纸本)9783031694820

Rolling bearings, critical in various rotating machinery, significantly influence system performance including reliability. However, the impact of lubricating properties on bearing vibration characteristics remains inadequately explored despite its crucial importance in improving the performance and elucidating fault mechanisms. This paper introduces a dynamic model that incorporates lubrication effects, time-varying friction forces between rollers and raceways, as well as contact and friction forces between rollers and the cage. The model includes self-rotation and revolution of the roller, along with the revolution of the cage, enabling analysis of the bearing's slippage behaviour. Through a series of simulations involving various viscosity pressure coefficients, the study explores the effect of lubricant viscosity on oil film thickness, internal forces, dynamic responses and slip properties of the bearing. It has found that increasing viscosity leads to lower characteristic frequencies and more pronounced slippage. Moreover, higher viscosity levels result in more significant deviations between simulated characteristic frequencies and their theoretical values. This research offers new insights into bearing tribo-dynamics, offering a theoretical basis for bearing condition monitoring and fault diagnosis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Rollers (machine components)

来源：评论

学校读者我要写书评

暂无评论

GPR-AI Master: GPR Data Analysis Utilizing Deep Learning and ECS for Backfill Grouting Detection in Shield Tunnels

GPR-AI Master: GPR Data Analysis Utilizing Deep Learning and...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Li, Kang Xie, Xiongyao Zhou, Biao Huang, Changfu Zhang, Zhuqing Lin, Honglin Zeng, Li Tongji University Department of Geotechnical Engineering College of Civil Engineering Shanghai200092 China Civil Engineering Tongji University State Key Laboratory of Disaster Reduction Shanghai200092 China China Railway 15th Bureau Group Co. Ltd. Shanghai200070 China Xiamen Rail Transit Group Co. Ltd. Xiamen361004 China

ISBN: (纸本)9798350375909

The quality of backfill grouting behind the shield tunnel is crucial for the structural support of the tunnel lining and tunnel excavation alignment. The actual grouting condition cannot be visually observed directly in the tunnel construction due to the presence of segmental linings. Ground-penetrating radar (GPR), due to its portability and excellent penetration of tunnel linings, is a promising method for non-destructive assessment of grouting quality. However, traditional GPR data processing suffers from subjectivity and lack of quantifiability. Therefore, utilizing artificial intelligence techniques for GPR data analysis holds significant importance. Based on experimental model data, we have developed a deep learning model using residual networks ResNet-18, enabling rapid and quantitative processing for GPR grouting thickness detection. The model's performance on the test dataset demonstrates that the deep learning model based on experimental data exhibits favorable results in the identification of grouting thickness. To address the portability of data analysis, we propose a model deployment method based on Elastic Cloud Servers. Users can access this system through an interactive interface, allowing them to directly upload GPR data and obtain visual results. The visual results include GPR raw data, grouting thickness distribution, and grouting thickness assessment. This application not only ensures the objectivity of GPR data analysis but also overcomes the closed nature of traditional data processing and transmission. Finally, we have explored and envisioned the applications of automated GPR data collection and intelligent data analysis, which hold significant reference value for the safety and automation of shield tunnel construction projects. © 2024 IEEE.

关键词： Grouting

来源：评论

学校读者我要写书评

暂无评论

Attribute Information Extracting Method for Air Quality Assessment of Buildings 7

Attribute Information Extracting Method for Air Quality Asse...

引用

7th Annual International Conference on Network and Information Systems for Computers, ICNISC 2021

作者： Du, Xiaozhi Duan, Yurong Huang, Wei State Key Laboratory of Rail Transit Engineering Information China School of Software Engineering Xi'an JiaoTong University Xi'an Shaanxi China

ISBN: (纸本)9781665402323

Extracting architectural elements from Industry Foundation Classes (IFC) files plays an important role on indoor air quality assessment. However, the traditional methods may extract useless instances and miss some necessary information, which results in poor air quality assessment. To address the above issues, this paper proposes an attribute extraction method for air quality assessment from IFC files, called as IFC-AAE. First the instances of the IFC file are preprocessed to remove the redundancies. Next the entity instances related to air quality assessment are extracted and then classified based on floors. Finally, the attribute information of these entities is extracted according to their reference relationship. The experimental results show that the IFC-AAE method is superior than the previous methods. Compared with the IFC file analyzer, the IFC-AEE method generates fewer invalid data. Compared with the Map-based extract method, the IFC-AEE method has an improvement by 4.78% on the precision rate on average. © 2021 IEEE.

关键词： Architectural design

来源：评论

学校读者我要写书评

暂无评论

A GAN-based Deep Learning Model for the Object Detection of Autonomous High-Speed Trains

A GAN-based Deep Learning Model for the Object Detection of ...

引用

2023 China Automation Congress, CAC 2023

作者： Wang, Xinghe Yin, Jiateng Pu, Fan Chen, Xing D'Ariano, Andrea Tang, Tao Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation Beijing100044 China Texas A&m University Zachry Department of Civil and Environmental Engineering TX77843 United States Nanchang Rail Transit Group Limited Corporation Jiangxi Nanchang China Universitàdegli Studi Roma Tre Department of Civil Computer Science and Aeronautical Technologies Engineering Rome Italy

ISBN: (纸本)9798350303759

With the development of autonomous trains that are operated without human labor in high-speed railways, the realtime detection of objects with computer vision techniques, including signals, falling rocks, and the infrastructure that collapses near the railroad, has received increased attention. Although existing studies have proposed different deep learning-based models, the critical issue is the lack of real-world data samples since the accidents caused by these objects seldom happen in the practical operations of high-speed trains. In this paper, we propose a deep-learning-based Generative Adversarial Network (GAN) framework for the realtime detection of objects with cameras in front of the running train. In particular, our GAN framework employs two connected deep-learning networks. The first network adopts a pix2pix scheme to automatically extend the few-shot data, i.e., data samples with objects (signals, obstacles, etc.) and noises. Our second network, i.e., the detection network, aims to detect and classify these objects precisely. We conduct experiments and compare our GAN with a few benchmarks on real-world data sets. The results reveal that our proposed GAN model significantly outperforms the commonly used deep learning models in detecting objects. © 2023 IEEE.

关键词： railroads

来源：评论

学校读者我要写书评

暂无评论

Probabilistic power forecasting for wind farm clusters using Moran-Graph network with posterior feedback attention mechanism

引用

Energy 2025年 328卷

作者： Qu, Zhijian Hou, Xinxing Huang, ShiXun Li, Di He, Yang Meng, Yan State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure East China Jiaotong University Jiangxi 330013 China College of Electrical and Automation Engineering East China Jiaotong University Jiangxi 330013 China

Predicting wind power generation precisely is key to optimizing wind energy use. This paper proposes a novel hybrid probabilistic forecasting model for wind farm cluster power output. First, to address the complex spatiotemporal interdependencies among multiple wind farms, a Moran-Graph network is proposed to extract synergistic features across wind farm clusters. To address the high volatility and non-stationarity of wind power, a hybrid decomposition method integrating sequential Variational Mode Decomposition (SVMD) and Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) is proposed. The Refined Composite Multi-scale Weighted Permutation Entropy (RCMWPE) is then employed to quantify the complexity of each subsequence for optimal signal reconstruction. Finally, a Feedback Attention-based Multi-Stacking model (FAMM-Stacking) is developed, which integrates Hybrid Kernel Density Estimation (HKDE) to generate probabilistic forecasting results for wind farm cluster power output. Case studies on wind farm clusters in Northwest China demonstrate that, at identical confidence levels, the proposed model achieves superior prediction interval coverage probability (PICP) with narrower average bandwidth, outperforming benchmark models. © 2025 Elsevier Ltd

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Effect of brazing temperature on microstructure and tensile strength ofγ-TiAl joint vacuum brazed with micro-nano Ti−Cu−Ni−Nb−Al−Hf filler

引用

Transactions of Nonferrous Metals Society of China 2024年第8期34卷 2563-2574页

作者： Li LI Yu-tong CHEN Lei-xin YUAN Fen LUO Zhi-xue FENG Xiao-qiang LI School of Materials Science and Engineering East China Jiaotong UniversityNanchang 330013China State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure East China Jiaotong UniversityNanchang 330013China National Engineering Research Center of Near-net-shape Forming for Metallic Materials South China University of TechnologyGuangzhou 510640China

A novel micro-nano Ti−10Cu−10Ni−8Al−8Nb−4Zr−1.5Hf filler was used to vacuum braze Ti−47Al−2Nb−2Cr−0.15B alloy at 1160−1220℃ for 30 *** interfacial microstructure and formation mechanism of TiAl joints and the relationships among brazing temperature,interfacial microstructure and joint strength were emphatically *** show that the TiAl joints brazed at 1160 and 1180℃ possess three interfacial layers and mainly consist of α_(2)-Ti_(3)Al,τ_(3)-Al_(3)NiTi_(2) and Ti_(2)Ni,but the brazing seams are no longer layered and Ti_(2)Ni is completely replaced by the uniformly distributed τ_(3)-Al_(3)NiTi_(2) at 1200 and 1220℃ due to the destruction of α_(2)-Ti_(3)Al barrier *** transformation at 1200℃ obviously improves the tensile strength of the joint and obtains a maximum of 343 ***,the outward diffusion of Al atoms from the dissolution of TiAl substrate dominates the microstructure evolution and tensile strength of the TiAl joint at different brazing temperatures.

关键词： γ-TiAl alloy micro-nano filler vacuum brazing interfacial microstructure tensile strength

来源：评论

学校读者我要写书评

暂无评论

A Text Classification Method of Network Public Opinion Based on Information Fusion

A Text Classification Method of Network Public Opinion Based...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Lei Zhu Miaoqing Wen Tong Zhang Yichuan Wang Jing Wang Mingsong Yang Bing Ma State Key Laboratory of Rail Transit Engineering Information (FSDI) Xi'an China School of computer science and engineering Xi'an University of technology Xi'an China

With the widespread use of mobile networks and intelligent terminal devices, a large amount of public opinion text has been generated from Microblogs, posting bars, and other platforms, resulting in the difficulty of public opinion management. More and more researchers use text classification methods to identify law-related public opinion information. However, the existing text classification methods rely on labor-intensive feature engineering, and their performance mainly depends on information fusion and classification algorithms, which is unsuitable for rapidly developing fields. This paper extracts the user comments of a hunting forum to analyze the semantic information of argot and employs the Word2vec model to represent the argot feature. Combining the multi-layer information of the pre-trained BERT on the user comments, we propose a text classification method BERT_W2V_CRF to improve the classification efficiency of massive law-related public opinion texts. Specifically, we first build a terminology dictionary of Chinese hunting forum to identify the argot features in expert-marked data using the Word2vec model. Then the BERT model is pretrained and the representation of fused information is generated by combining the Word2vec and optimized BERT. Finally, the recognized result is obtained by using Softmax. Experiments are conducted on the user comment dataset to evaluate the proposed text classification method, and the results show that the information fusion approach can be used to improve the classification efficiency of the deep learning-based method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tube Design of Integrated EDS Evacuated Tube Transportation System

Tube Design of Integrated EDS Evacuated Tube Transportation ...

引用

2023 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD 2023

作者： Shi, Hong-Fu Zheng, Jun Chen, Yang He, Shi-Cheng Southwest Jiaotong University School of Information Science and Technology Chengdu China Southwest Jiaotong University State Key Laboratory of Rail Transit Vehicle System Chengdu China Neijiang Power Supply Company Neijian China Southwest Jiaotong University School of Electrical Engineering Chengdu China

ISBN: (纸本)9798350301571

In this work, the superconducting electrodynamic suspension integrated with the evacuated tube is proposed. Taking the Maglev MLX01-02 as an exemplary design, the structure specifications of tube are determined based on electromagnetic interaction among the induced current generated in tube and onboard superconducting magnets. The results reveal that the radius and thickness of metal tube are customed to 3.5 m and 40 mm, adopting stainless steel. This work can newly guide design and application of evacuated tube transportation system. © 2023 IEEE.

关键词： evacuated tube transportation Superconducting electrodynamic suspension tube radius tube thickness

来源：评论

学校读者我要写书评

暂无评论

Sliding mode robust control based on HJI theory and RBFNN for high-speed train

Sliding mode robust control based on HJI theory and RBFNN fo...

引用

2022 International Conference on Automation Control, Algorithm, and Intelligent Bionics, ACAIB 2022

作者： Fu, Yating Hu, Dongliang Yang, Hui Zhan, Tianhua School Electrical and Automation Engineering East China Jiaotong University Jiangxi province Nanchang330013 China State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure Jiangxi province Nanchang330013 China

ISBN: (纸本)9781510655072

In view of the complex operating environment of high-speed trains, this paper considers the additional resistance of complex lines and the influence of random external disturbances. Aiming at this problem, a sliding mode robust control algorithm for high-speed trains is proposed based on Hamilton-Jacobi Inequality (HJI) theory and radial basis function neural network (RBFNN). On the other hand, the introduced RBFNN can be used to reduce the dependence of the controller on train model parameters, and HJI theory can be used to ensure the anti-jamming ability of the system. The Lyapunov function proves that both the displacement tracking error and the velocity tracking error can be converged and stable under the method proposed in this paper. The parameters of the CRH380A high-speed train are used for simulation, and the given target speed and target displacement curve are tracked to verify the feasibility of the proposed control algorithm. The simulation results show that the proposed control algorithm has better tracking accuracy for a given speed and displacement than the traditional robust adaptive control method (TRAC) and can meet the requirements of punctual operation and fixed-point parking required by high-speed trains. It has a better control effect when dealing with complex road conditions changes and also has the more vital anti-interference ability for random external interference. © 2022 SPIE.

关键词： Robust control

来源：评论

学校读者我要写书评

暂无评论

Asynchronous mechanochemical atomic attrition behavior of heterogeneous polysilicon surface

引用

Wear 2025年 570卷

作者： Dang, Shehui Xiao, Chen Zhang, Xinyu Li, Jie Wang, Yang Qian, Linmao Chen, Lei Tribology Research Institute State Key Laboratory of Rail Transit Vehicle System School of Mechanical Engineering Southwest Jiaotong University Chengdu610031 China Research Institute of Frontier Science Southwest Jiaotong University Chengdu610031 China

Using an atomic force microscope, the nanowear tests of polycrystalline silicon (poly-Si) against a single SiO2 microsphere were conducted to investigate the atomic attrition mechanism in practical poly-Si chemical mechanical polishing/planarization (CMP) processes. The material removal of poly-Si was dominated by stress-assisted mechanochemical reactions and exhibited a lower removal rate compared to monocrystalline silicon (mono-Si). By combining load-dependent nanowear results with a mechanically-assisted Arrhenius-type kinetics model, it was revealed that the energy barrier for mechanochemical reactions in poly-Si is higher than that in mono-Si, due to the relatively stronger surface chemical inertness of oxides within the intercrystallite boundaries. On this basis, an optimized polishing procedure for poly-Si was proposed, involving strong oxidation to achieve effective synchronous removal across the heterogeneous poly-Si surface, resulting in an atomically smooth surface. The results provide new mechanistic insights into the role of crystal structure in the mechanochemical material removal process and the regulating strategy based on nanowear tests offers a new perspective for optimizing poly-Si CMP in IC industry. © 2025

关键词： Monocrystalline silicon

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：