检索结果-内蒙古大学图书馆

Short-term creep behavior in P91 heat-resistant steel at low stress

Short-term creep behavior in P91 heat-resistant steel at low...

Chinese Materials Congress on Methods of design and Characterization of Materials, Research and Development of Technological Processes, 2015

作者： Zhao, Pengshuo Shen, Junjie Zhang, Hui Tianjin key Laboratory of the Design and Intelligent Control of the Advanced Mechatronical System School of Mechanical Engineering Tianjin University of Technology 391 Binshui Road Xiqing District Tianjin China Tianjin Entry-Exit Inspection and Quarantine Bureau China

ISBN: (纸本)9783038357629

P91 heat-resistant steel is widely used in the high temperature of piping components of thermal power plants and nuclear power plants. In these conditions, the typical failure of P91 is mainly caused by creep at low stress. In this investigation the short-term creep behavior in P91 at low stress was investigated by helicoid spring creep test due to its high strain-sensitivity. The helicoid spring creep was based on the assumption of pure torsion. The mechanics field was firstly studied by ANSYS finite-element simulation to find the establishing conditions of pure torsion. Secondly, the creep properties of P91 were studied under the conditions of the temperatures of 0.38Tmm and the stresses of 14.6 MPa, 25 MPa, 34 MPa, respectively. The ANSYS finite-element simulation shows that the creep deformation is considered to be pure torsion when the pitch spacing of coil is between 2mm to 4mm. The creep curves show "Normal type ", and "the stress exponent" is n=0.9. © 2016 Trans Tech Publications, Switzerland.

关键词： Creep

来源：评论

学校读者我要写书评

暂无评论

A Protein Embedding Model for Drug Molecular Screening

A Protein Embedding Model for Drug Molecular Screening

引用

International Conference on Big Data and Smart computing (BIGCOMP)

作者： Chao Che Min Zhu Yongjun Zhu Qiang Zhang Dongsheng Zhou Bin Wang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian China Department of Library and Information Science Sungkyunkwan University Seoul Republic of Korea

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

Application of machine learning method in new drug development can greatly shorten the process of experimental discovery and reduce the risk of clinical failure. However, the feature extraction of proteins sequence is very difficult due to the large dimension. To this end, we propose a Protein Embedding Model(PEM) for drug molecular screening to predict the interaction between proteins and small molecules. Specifically, PEM first classifies 20 kinds of amino acids into 6 categories to reduce the dimension and learns the representation of protein borrowing the idea of word embedding. Then the model uses multiple imputation to fill the physical and chemical properties of small molecule compounds. Finally, the model uses LightGBM model to predict the affinity value Ki between proteins and small molecules. Experiments show that the model can effectively extract the features of proteins and small molecules and outperforms other traditional methods on the data provided by a drug discovery and development company.

关键词： Amino acids Feature extraction Drugs Protein sequence Chemicals Compounds

来源：评论

学校读者我要写书评

暂无评论

UWB Non-Line-of-Sight Recognition and Suppression Methodology 15

UWB Non-Line-of-Sight Recognition and Suppression Methodolog...

引用

15th International Conference on Communication Software and Networks, ICCSN 2023

作者： Ni, Zhengshuai Zhou, Haibo Zhang, Guozheng Xu, Wangbei Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin China School of Mechanical Engineering Tianjin University Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin China

ISBN: (纸本)9798350329360

Ultra-Wide Band (UWB) positioning system has become the main research object in indoor positioning field due to its superior positioning performance. Accuracy at the scale of centimeters is achievable in an ideal positioning scenario. Nonetheless, the intricate and changeable indoor surroundings may cause UWB signals to propagate beyond the line-of-sight (LOS) and weaken in signal strength, resulting in a considerable reduction in the precision of positioning. In this paper, methods for identifying non-line-of-sight (NLOS) errors, alleviating NLOS errors, and integrating multi-sensor information are analyzed and studied to provide reference for improving the NLOS positioning accuracy of UWB. © 2023 IEEE.

关键词： alleviate identify multi-sensor NLOS UWB

来源：评论

学校读者我要写书评

暂无评论

design, Analyze, and Simulation of a Bionic Swept-Back Wing Scheme with Force Amplification Mechanism 3

Design, Analyze, and Simulation of a Bionic Swept-Back Wing ...

引用

3rd International Symposium on Aerospace Engineering and Systems, ISAES 2024

作者： Wu, Jiangpeng Du, Huixiang Ma, Xinmeng Li, Manhong Zhao, Libin Hu, Ning Shenyang Aircraft Design and Research Institute Shenyang China School of Mechanical Engineering Hebei University of Technology Tianjin China Key Laboratory of Advanced Intelligent Protective Equipment Technology Ministry of Education Hebei University of Technology Tianjin China

ISBN: (纸本)9798350350418

Compared with traditional aircraft, the variant aircraft can change the shape of its fuselage or wing to adapt to the needs of different flight conditions. Among them, the variable swept-back wing can provide excellent aerodynamic characteristics for the morphing aircraft by adjusting the swept back angle of the wing. Aiming at the problem of the existing variable swept-back wings encroach on the belly space. Based on the principles of mechanism and bionics, this paper innovatively puts forward a design scheme of wing root bending variable swept-wing without encroaching on the belly space and designs a force amplification mechanism, which is reasonable according to the principle of virtual work. It is verified to be able to amplify the force by 130% through a set of eigenvalues. It provides certain references for the design of the variable swept-back wing. © 2024 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Based on Image Enhancement

Speech Emotion Recognition Based on Image Enhancement

引用

International Conference on intelligent System and Knowledge Engineering, ISKE

作者： Dongyan Wang Jing Dong Dongsheng Zhou Xiaopeng Wei Qiang Zhang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (数字)9781728123486

ISBN: (纸本)9781728123493

The performance of an emotion recognition system is determined by the quality of emotional features. In this paper, we propose a feature optimization algorithm based on image enhancement and present a convolutional recurrent model to realize emotional recognition of natural speech. For three-dimensional (3-D) log-Mel spectrum and 3-D spectrogram features, the fast gamma transformation with an adaptive threshold is adopted for feature enhancement to make full use of the dynamic characteristics of non-stationary speech signals. Meanwhile, the model combining Convolutional Neural Network (CNN) with the rectangular kernels and Long Short-Term Memory (LSTM) is used to complete speech emotion recognition tasks. Experiments are carried out on two public emotional datasets, and results demonstrate the good generalization ability and recognition performance of our proposed model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cooperative Diving of Multi-AUV System with Self-triggered Mechanism

Cooperative Diving of Multi-AUV System with Self-triggered M...

引用

2022 IEEE International Conference on Unmanned Systems, ICUS 2022

作者： Zhang, Junjie Yang, Jingxin Bian, Yougang Cui, Qingjia Qin, Xiaohui Hu, Manjiang Shen, Da Gao, Hongbo Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha China Institute of Hunan University Wuxi Intelligent Control Research Wuxi China University of Science and Technology of China The Department of Automation Hefei China

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

A self-triggered distributed model predictive control (DMPC) approach is proposed in this paper for the cooperative diving of a multi-autonomous underwater vehicle (AUV) system. In order to realize cooperative diving of the multi-AUV system, we design a basic DMPC mechanism with a stability condition which is easy to be realized. Then, a self-triggering mechanism is introduced into the basic DMPC approach which saves communication and computation resources. In the self-triggered mechanism, the maximum time instant that is inside the terminal region decides the triggering interval. The triggering interval is decided after solving the optimization problem, therefore helps reduce the computation burden at each control loop. Lastly, numerical examples are provided to verify the effectiveness of the proposed method. © 2022 IEEE.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

A Facile Surface Passivation of Hematite Photoanodes with Molybdate Overlayers for Efficient PEC Water Oxidation

引用

Chinese Journal of Chemical Physics 2018年第6期31卷 833-842,734页

作者： Qi Zhang Quan-ping Wu Yue Zhang Ji-tong Yan Song Xue Hong-yan Wang Tianjin Key Laboratory of the Design and Intelligent Control of the Advanced Mechanical System School of Mechanical Engineering Tianjin University of Technology Tianjin 300384 China Tianjin Key Laboratory of Organic Solar Cells and Photochemical Conversion School of Chemistry & Chemical Engineering Tianjin University of Technology Tianjin 300384 China

α-Fe2O3 thin films have been synthesized and used as photoanodes for photo-electrochemical (PEC) water oxidation. Molybdate was introduced to mediate hematite thin films via two synthesis routes (namely in situin situ mediation and ex situ modification). Through the in situ mediation process, the morphology and film thickness could be changed significantly due to the addition of MoO42-, while for the ex situ modification, the PEC performance of the hematite has been greatly improved without changing the nanorod morphology. Various characterizations such as UV-Vis absorption, transmission electronic microscopy, scanning electronic microscopy, Mott-Schottky, electrochemical impedance spectroscopy were conducted and the PEC performances were investigated.

关键词： Hematite film Molybdate Passivation Water splitting Photocurrent

来源：评论

学校读者我要写书评

暂无评论

Efficient Hierarchical Exploration with An Active Subgoal Generation Strategy

Efficient Hierarchical Exploration with An Active Subgoal Ge...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Xu, Xin Zuo, Guoyu Li, Jiangeng Huang, Gao The Faculty of Information Technology Beijing University of Technology Beijing100124 China The Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China Faculty of Information Beijing University of Technology Beijing100124 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing100081 China

ISBN: (纸本)9781665481090

Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach in long-horizon and complex tasks. It has been successfully used by decomposing tasks via subgoals. However, the existing goal-conditioned HRL methods often suffer from training inefficiency in the long-horizon tasks with sparse external rewards. For this problem, this paper proposes a novel framework that can train high-level policy efficiently with an effective sub goal generation method. The key component of the framework is an active subgoal generation strategy which consists of (a) an efficient high-level policy learning mechanism and (b) two measures of novelty and coverage for filtering effective subgoals. We also introduce the HER mechanism to the framework to solve the problem of sparse reward in the environment. Building upon the proposed framework, this paper develops an active hierarchical exploration strategy with an efficient subgoal generation method. We test our method on a variety of continuous control tasks. Experimental results demonstrate that the strategy outperforms the state-of-the-art HRL approaches. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

keyword mask pre-training model for the review of standard declaration

Keyword mask pre-training model for the review of standard d...

引用

International Conference on Computer Engineering and Applications (ICCEA)

作者： Chuang Feng Chao Che Qiang Zhang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

The review of standard declaration of import and export commodities refers to the evaluation of whether the declaration information of the commodities filled in by enterprises conforms to the customs filling standards according to the standardized declaration catalogue The manual review method cannot meet the actual work needs. Therefore, using text classification algorithm to conduct this task is necessary. The classification method based on the pre-training model would rely on the keywords. However, for the review of standard declaration task, excessive reliance on keywords will reduce the classification effect because of ignoring the overall information of the text. keyword mask pre-training model is proposed. In the fine-tuning stage, the model designs a keyword masking strategy and a keyword blinding strategy. The keyword masking strategy regularizes the BERT model with a mask mechanism, that is, the keywords are reconstructed with other text information except keywords, so that the model focuses on non-keywords information; keyword blinding strategy makes the model unable to distinguish the categories of text information without contextual text information, which can eliminate the influence of keywords on model decision-making. The experimental results on the real customs declaration data set showing that the method in this thesis exceeds the baseline method in terms of precision and true negative rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Medical image registration and its application in retinal images:a review

引用

Visual computing for Industry,Biomedicine,and Art 2024年第1期7卷 142-164页

作者： Qiushi Nie Xiaoqing Zhang Yan Hu Mingdao Gong Jiang Liu Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Singapore Eye Research Institute Singapore 169856Singapore State Key Laboratory of Ophthalmology Optometry and Visual ScienceEye HospitalWenzhou Medical UniversityWenzhou 325027China

Medical image registration is vital for disease diagnosis and treatment with its ability to merge diverse informa-tion of images,which may be captured under different times,angles,or *** several surveys have reviewed the development of medical image registration,they have not systematically summarized the existing med-ical image registration *** this end,a comprehensive review of these methods is provided from traditional and deep-learning-based perspectives,aiming to help audiences quickly understand the development of medical image *** particular,we review recent advances in retinal image registration,which has not attracted much *** addition,current challenges in retinal image registration are discussed and insights and prospects for future research provided.

关键词： Computer-aided diagnosis Medical image registration Deep learning Generative model Transformer Retina

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：