检索结果-内蒙古大学图书馆

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Zhenjie Liu Yong Deng Jun Li Javier Plaza Antonio Plaza Hubei Key Laboratory of Intelligent Geo-Information Processing and School of Computer Science China University of Geosciences Wuhan China Changjiang Institute of Survey Planning Design and Research Wuhan China Hyperspectral Computing Laboratory University of Extremadura Caceres Spain

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Global climate change leads to increasing frequency and severity of urban flood disasters, which restricts human sustainable development. So far, many studies have explored the potential of fusing remote sensing images and social media data for monitoring urban flood disasters. However, the SAR flooded characteristics of different land cover in complex urban environment are generally ignored. In this paper, we develop a new method for the fusion of heterogeneous SAR images and social media data by using domain adaptation and land cover information. The 2017 Houston flood event is taken as a case study for evaluation. According to our experiments, compared with traditional methods of optimal transport and geographic optimal transport, the proposed method can align the geo-tagged tweets with location uncertainty to nearby flooded areas of low-, medium-, and high-intensity developed areas with more remarkable performance.

关键词： Uncertainty Social networking (online) Disasters Urban areas Land surface Radar polarimetry Floods

来源：评论

学校读者我要写书评

暂无评论

Simulation of Nuclear Reactor Accident Scenarios using Physics-Informed Neural Networks and Transfer-Learning 4

Simulation of Nuclear Reactor Accident Scenarios using Physi...

引用

4th International Conference on Electronic Information Engineering and Computer Science, EIECS 2024

作者： Yu, Yang Xie, Yufei Wang, Wenlin Wu, Guohua Lan, Haitao Lin, Enbo An, Ping Sun, Zibin Zhang, Haichuan Wu, Yixian National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing Changsha China Nuclear Power Institute of China Science and Technology on Reactor System Design Technology Laboratory Chengdu China School of Automation Wuhan University of Technology Wuhan China Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen China Institute of Automotive Engineers Hubei University of Automotive Technology Shiyan China Nuclear Power Institute of China Chengdu China

ISBN: (纸本)9798331531409

In a Loss of Coolant Accident (LOCA), reactor core temperatures can rise rapidly, leading to potential fuel damage and radioactive material release. This research presents a groundbreaking method that combines the power of Monte Carlo Sampling and Physics-Informed Neural Networks (PINNs) to simulate and effectively address the challenging Loss of Coolant Accidents (LOCA) in nuclear reactors. In the event of a LOCA, reactor core temperatures can soar rapidly, posing a significant threat to fuel integrity and potentially leading to the release of radioactive materials. By leveraging the strengths of both Monte Carlo Sampling and PINNs, this approach aims to provide a comprehensive and accurate simulation framework for assessing and mitigating the consequences of such accidents. The method yields high prediction accuracy (MAE: 0.033, RMSE: 0.098, R2: 0.814) and demonstrates robustness through transfer learning, maintaining strong performance (MAE: 0.064, RMSE: 0.163, R2: 0.735). © 2024 IEEE.

关键词： Coolants

来源：评论

学校读者我要写书评

暂无评论

Development of completion tool pressure test control system 10

Development of completion tool pressure test control system

引用

2023 10th International Conference on advanced Manufacturing Technology and Materials Engineering, AMTME 2023

作者： Sun, Zhiyu Zhao, Lianyu Wang, Chenglin Zhao, Xiaolei Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology China Offshore Oil Engineering Co. Ltd. Tianjin300461 China

In oil exploitation, the completion tool is the key point to ensure the effective development of oil wells, and it must undergo strict pressure testing. Due to the high test pressure, there are potential safety hazards in the manual operation process. To improve safety and test efficiency, the automatic precision test system is developed. The detection system must realize the pressure detection process, provide feedback on the key data, give the corresponding curve reference, and generate the detection report. Through the PID algorithm, the precise control of the motor is realized. The system safety is guaranteed, and the detection accuracy is improved. The test results show that the completion tool pressure test control system can greatly improve detection efficiency. It can also fully reflect the entire detection process, accurately calculate some key parameters such as pressure drop, and obtain accurate results. The detection error is kept within 0.5%, ensuring the reliability of the detection process. © Published under licence by IOP Publishing Ltd.

关键词： Control systems

来源：评论

学校读者我要写书评

暂无评论

Exploration and Practice of Blended Teaching in the Course of Engineering Drawing Empowered by Knowledge Graph

Exploration and Practice of Blended Teaching in the Course o...

引用

International Conference on Educational and Information Technology (ICEIT)

作者： Yahong Xue Haozhi Mu Lijun Xue Tianjin Key Laboratory of the Design and Intelligent Control of the Advanced Mechatronical System National Demonstration Center for Experimental Mechanical and Electrical Engineering Education (Tianjin University of Technology) Tianjin University of Technology Tianjin China

ISBN: (数字)9798350372663

ISBN: (纸本)9798350372670

Under the current blended learning mode, students' ability to process, organize, and integrate knowledge is insufficient, and the ability to construct a complete knowledge system for autonomous learning is slightly weak. Taking the national first-class undergraduate course “Engineering Drawing” at Tianjin University of Technology as an example, this study explores and practices the teaching of online and offline hybrid courses based on knowledge graphs, and conducts a comprehensive effectiveness analysis. Practice has proven that the hybrid teaching empowered by knowledge graphs enables visualization of knowledge points and analysis of learning situations, allows for planned learning paths, intelligent resource recommendations, and can achieve targeted integration of data and teaching of key and difficult issues. It has reference significance for the construction of an open, personalized, and precise intelligent education system.

关键词： Federated learning Engineering drawings Education Knowledge based systems Data visualization Knowledge graphs Hybrid learning

来源：评论

学校读者我要写书评

暂无评论

Dual-axial self-attention network for text classification

引用

Science China(Information Sciences) 2021年第12期64卷 80-90页

作者： Xiaochuan ZHANG Xipeng QIU Jianmin PANG Fudong LIU Xingwei LI State Key Laboratory of Mathematical Engineering and Advanced Computing Shanghai Key Laboratory of Intelligent Information Processing Fudan University School of Computer Science Fudan University

Text classification is an important task in natural language processing and numerous studies aim to improve the accuracy and efficiency of text classification models. In this study, we propose an effective and efficient text classification model which is based on self-attention solely. The recently proposed multidimensional self-attention significantly improved the performance of self-attention. However, existing models suffer from two major limitations:(1) the previous multi-dimensional self-attention models are quite timeconsuming;(2) the dependencies of elements along the feature axis are not taken into account. To overcome these problems, in this paper, a much more computational efficient multi-dimensional self-attention model is proposed, and two parallel self-attention modules, called dual-axial self-attention, are applied to capture rich dependencies along the feature axis as well as the text axis. A text classification model is then *** experimental results on eight representative datasets show that the proposed text classification model can obtain state-of-the-art results and the proposed self-attention outperforms conventional self-attention models.

关键词： text classification dual-axial self-attention feature-axial dependency

来源：评论

学校读者我要写书评

暂无评论

Research on Fault Diagnosis Method Based on Structural Causal Model in Tennessee Eastman Process 7th

Research on Fault Diagnosis Method Based on Structural Causa...

引用

7th International Conference on computing, Control and Industrial Engineering, CCIE 2023

作者： Pu, Haoyuan Liu, Jie Chen, Zhi Yang, Xiaohua Ren, Changan Xu, Zhuoran Jian, Yifan School of Computer Science University of South China Hengyang China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China Intelligent Equipment Software Evaluation Engineering Technology Research Center of Hunan Hengyang China CNNC Key Laboratory on High Trusted Computing Hengyang China School of Nuclear Science and Technology University of South China Hengyang China

ISBN: (纸本)9789819927296

In the practical application of fault diagnosis in large-scale chemical systems, due to the danger of faults, the machine learning diagnosis methods used in current research often face the problem of scarcity of fault samples. This makes it difficult for the model to be trained effectively, thus affecting the fault detection rate of the model. Therefore, for the fault diagnosis of chemical system with small sample data, this paper proposes a diagnostic method that uses structural causal model to further combine the diagnostic results of the two machine learning methods, thereby improving global diagnostic performance. With the help of powerful system description ability of structural causal model, we can establish a causal graph for diagnostic process of the chemical system, and accurately construct the corresponding structural equations for the various diagnostic results of the two machine learning methods to combine them, thus improve the fault detection rate. The global results make up for the shortcomings of single machine learning method in small sample chemical system fault diagnosis. The verification on the chemical system simulation platform Tennessee Eastman process shows that, compared with the diagnosis results of the selected Gaussian Naive Bayes method and the K-nearest neighbour method, the results obtained by our method are effectively improved in fault detection rate of each fault in TEP. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

design and Research on Flapping Mechanism of Biomimetic Albatross 2

Design and Research on Flapping Mechanism of Biomimetic Alba...

引用

2022 2nd International Conference on advanced Materials and Mechatronics, ICAMM 2022

作者： Zhang, Haiming Liu, Zhenzhong Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology China

In order to solve the problems of low flying efficiency, poor aerodynamic performance of wing and short flying time distance existing in the research of flapping wing aircraft, a kind of albatron-like flapping wing structure with higher flying efficiency is proposed in this paper. The functions of bird wing flutter, folding and gliding are realized by two degrees of freedom control respectively. First, the flying characteristics of albatross are analyzed and the flying characteristics suitable for albatross are summarized. Propose design requirements for bionic design objectives;The bionic structure design is carried out by referring to the physical structure of wing and the flight motion law, and the key parameters such as the size and angle of connecting rod mechanism are analyzed, calculated and optimized. A clamping mechanism is designed to achieve gear stuck in order to achieve gliding kinetic energy. The three-dimensional model of the flapping wing mechanism is built by solid works, and the motion analysis is carried out by using Motion plug-in. The analysis results of key-point parameters are output, which verifies the movement law and requirements of the mechanism to achieve the design objectives. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Wings

来源：评论

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning 24

Towards High-resolution 3D Anomaly Detection via Group-Level...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798400706868

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3D-AD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Windowed Visibility Graph Fourier Transform and its Application in Gearbox Composite Fault Diagnosis

SSRN

引用

SSRN 2024年

作者： Gao, Yiyuan Chen, Mang Yu, Dejie Du, Wenliao Gong, Xiaoyun Henan Provincial Key Laboratory of Intelligent Manufacturing of Mechanical Equipment Zhengzhou University of Light Industry Zhengzhou450002 China Henan International Joint Laboratory of Complex Mechanical Equipment Intelligent Monitoring and Control Zhengzhou University of Light Industry Zhengzhou450002 China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China

The essence of gearbox composite fault diagnosis lies in the effective isolation of distinct fault components. Building upon this, the windowed visibility graph Fourier transform (WVGFT) is incorporated into the analysis of gearbox vibration signals. Since the gear and bearing fault components are respectively projected onto the low-order and high-order regions by WVGFT, they can be reconstructed by the corresponding vertex-graph spectrum coefficients. For a more effective extraction of fault components in gearboxes, the low-order threshold of the extracted gear fault component is optimized using the artificial fish swarm, and the high-order threshold of the extracted bearing fault component is optimized by the change rate of signal kurtosis. Finally, the Hilbert envelope demodulation analysis is applied for diagnosing the gear and bearing faults in gearboxes. The validity of our presented approach is fully confirmed through the simulation and experimental signals. © 2024, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Mapping Method for OPGW Tower Based on M-OTDR 22

Fast and Accurate Mapping Method for OPGW Tower Based on M-O...

引用

22nd International Conference on Optical Communications and Networks, ICOCN 2024

作者： Ruofan, Wang Hongren, Li Xinying, Zhao Shuai, Tong Ningmu, Zou Xuping, Zhang Huanhuan, Liu Fei, Xiong Yixin, Zhang College of Engineering and Applied Sciences Nanjing University Nanjing210023 China Nanjing University Key Laboratory of Intelligent Optical Sensing and Manipulation Nanjing210093 China School of Information Science and Engineer Shandong University Qingdao266237 China Shcnzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Inner Mongolia DT Electric Power Design Hohhot010010 China

ISBN: (纸本)9798350367652

This paper describes how distributed optical fiber sensing (DOFS) technology, combined with dark optical fibers within the current optical fiber composite overhead ground wire (OPGW), enables online monitoring and early warning of abnormalities in high-voltage overhead transmission lines. Achieving this goal requires an accurate mapping of the optical cable length to the actual GPS coordinates of the tower. The current tower positioning techniques have drawbacks like low identification rates, high positioning variation, and long calibration times. They are also restricted by particular weather conditions. This study presented a multi-parametric optical time domain reflectance sensing (M-OTDR) system that synchronizes the monitoring of temperature, strain, vibration, and other physical parameters along the fiber optic cable in order to address these problems. Additionally, the study proposed four reference positioning functions. An in-field test was carried out on a 220kV high-voltage transmission line in Fujian Province, PRC. The results showed that the proposed method could guarantee speedy and accurate placement of high-voltage overhead transmission line towers. © 2024 IEEE.

关键词： Optical fibers

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：