检索结果-内蒙古大学图书馆

Methodology for optimization of preload in a bolted-flange connection based on Markov theory

Journal of Physics: Conference Series 2022年第1期2174卷 012072页

作者： Yuezhen Wang Zhifeng Liu Ying Li Congbin Yang Institute of Advanced Manufacturing and Intelligent Technology Beijing University of Technology Beijing Beijing 100124 China Mechanical Industry Key Laboratory of Heavy Machine Tool Digital Design and Testing Beijing University of Technology Beijing Beijing 100124 China Key Laboratory of CNC Equipment Reliability Ministry of Education Jilin University Changchun Jilin 130012 China

The bolted-flange connection is one of the most popular detachable mechanical joints in mechanical flange connection. It is well known that bolted-flange joints need to be tightened to meet the assembly performance in practical engineering applications. However, the dispersion of the pre-tightening force caused by the elastic interaction between the bolts has a serious impact on the sealing and safety of the product, and therefore the optimization of bolt preload has always been a hot spot in the assembly research field. Combining mathematical theory and experimental data, this paper proposes an optimization model for uniformly distributed preload based on the Markov theory. The torque method was utilized to fasten the bolt-flange joint. The bolt pre-tightening force in the final state was collected and used as sample data. A state transition model was constructed to determine the state transition matrix. Ultimately, an iterative model of the preload was deduced, and the rationality of the model was verified through experimentation. The proposed optimization method of bolt preload can be applied to determine the initial preload of each bolt. This method improves the assembly efficiency and accuracy, which provides a theoretical approach to effectively guide the tightening work of bolted-flange connections.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Histopathological Image Classification Based on Deep Second-order Pooling Network

Breast Cancer Histopathological Image Classification Based o...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jiasen Li Jianxin Zhang Qiule Sun Hengbo Zhang Jing Dong Chao Che Qiang Zhang Key Lab of Advanced Design and Intelligent Computing (Ministry of Education) Dalian University Dalian China School of Computer Science and Engineering Dalian Minzu University Dalian China School of Information and Communication Engineering Dalian University of Technology Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

With the breakthrough performance in a variety of computer vision and medical image analysis problems, convolutional neural networks (CNNs) have been successfully introduced for the classification task of breast cancer histopathological images in recent years. Nevertheless, existing breast cancer histopathological image classification networks mainly utilize the first-order statistic information of deep features to represent histopathological images, failing to characterize the complex global feature distribution of breast cancer histopathological images. To address the problem, this work makes a first attempt to explore global second-order statistics of deep features for the above task. More specifically, we propose a novel deep second-order pooling network (DSoPN) for breast cancer histopatho-logical image classification, in which a robust global covariance pooling module based on matrix power normalization (MPN) is embedded into a simple yet effective CNN architecture. The given DSoPN model can capture richer second-order statistical information of deep convolutional features and produce more informative global representations for breast cancer histopatho-logical images. Experimental results on the public BreakHis dataset illuminate the promising performance of the second-order pooling for breast cancer histopathological image classification. Besides, our DSoPN achieves very competitive performance compared to the state-of-the-art methods.

关键词： Breast cancer Covariance matrices Task analysis Feature extraction Computer architecture Pathology

来源：评论

学校读者我要写书评

暂无评论

Ladle Furnace Temperature Prediction Model Based on Large-scale Data With Random Forest

引用

IEEE/CAA Journal of Automatica Sinica 2017年第4期4卷 770-774页

作者： Xiaojun Wang Key Laboratory of Advanced Design and Intelligent Computing Ministry of EducationDalian UniversityDalian 116622 China

In ladle furnace, the prediction of the liquid steel temperature is always a hot topic for the researchers. The most of the existing temperature prediction models use small sample set. Today, the precision of them can not satisfy practical production. Fortunately, the large sample set is accumulated from the practical production process. However, a large sample set makes it difficult to build a liquid steel temperature model. To deal with the issue, the random forest method is preferred in this paper, which is a powerful regression method with low complexity and can be designed very quickly. It is with the parallel ensemble structure,uses sample subsets,and employs a simple learning algorithm of sub-models. Then, the random forest method is applied to establish a temperature model by using the data sampled from the production process. The experiments show that the random forest temperature model is more precise than other temperature models.

关键词： Ladle furnace random forest regression tree temperature prediction

来源：评论

学校读者我要写书评

暂无评论

RCGA-Net: An Improved Multi-hybrid Attention Mechanism Network in Biomedical Image Segmentation

RCGA-Net: An Improved Multi-hybrid Attention Mechanism Netwo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Feng Xiao Cong Shen Yu Chen Tian Yang Shengyong Chen Zhijun Liao Jijun Tang School of Computer Science and Engineering Tianjin University of Technology Tianjin P.R.China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin P.R.China School of Basic Medical Sciences Fujian Medical University Fuzhou Fujian P.R.China College of Intelligence and Computing Tianjin University Tianjin P.R.China Key Laboratory of Systems Bioengineering Ministry of Education Tianjin P.R.China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen Guangdong P.R.China University of South Carolina Columbia SC U.S.A.

ISBN: (纸本)9781665429825

Drawing support from an effective Medical Image Segmentation (MIS) is conducive to a substantial diagnostic basis for the physicians to identify the focus lesion in the patient body and give the subsequent clinical assessment of the patient status. Although various works have tried the challenging quantitative analysis problem, it is still difficult to conduct precise automatic segmentation, especially the soft tissue organs. In this decade, with the increased amount of available datasets, deep learning-based networks have achieved remarkable performance in image processing. Inspired by the state-of-the-art deep learning works, in this paper, we propose an end-to-end multi-layer network named RCGA-Net. It consists of an encoder-decoder backbone that integrates a coordinate attention mechanism based on space and channel and a global context extraction module to highlight more valuable information. To evaluate the performance of RCGA-Net, we apply it to different kinds of clinical and experimental MIS tasks to testify its generalization ability. Extensive experiments represent that our schema has taken the outperform or compatible results among the comparison methods group. Specifically, the numeric result of RCGA-Net on the pulmonary dataset has achieved a 99.12% optimum F1-score.

关键词： Deep learning Image segmentation Statistical analysis Lung Predictive models Feature extraction Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Fused behavior recognition model based on attention mechanism

引用

Visual computing for industry, biomedicine, and art 2020年第1期3卷 7页

作者： Lei Chen Rui Liu Dongsheng Zhou Xin Yang Qiang Zhang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Dalian University Dalian 116622 China. Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Dalian University Dalian 116622 China. liurui@***. School of Computer Science and Technology Dalian University of Technology Dalian 116024 China.

With the rapid development of deep learning technology, behavior recognition based on video streams has made great progress in recent years. However, there are also some problems that must be solved: (1) In order to improve behavior recognition performance, the models have tended to become deeper, wider, and more complex. However, some new problems have been introduced also, such as that their real-time performance decreases; (2) Some actions in existing datasets are so similar that they are difficult to distinguish. To solve these problems, the ResNet34-3DRes18 model, which is a lightweight and efficient two-dimensional (2D) and three-dimensional (3D) fused model, is constructed in this study. The model used 2D convolutional neural network (2DCNN) to obtain the feature maps of input images and 3D convolutional neural network (3DCNN) to process the temporal relationships between frames, which made the model not only make use of 3DCNN's advantages on video temporal modeling but reduced model complexity. Compared with state-of-the-art models, this method has shown excellent performance at a faster speed. Furthermore, to distinguish between similar motions in the datasets, an attention gate mechanism is added, and a Res34-SE-IM-Net attention recognition model is constructed. The Res34-SE-IM-Net achieved 71.85%, 92.196%, and 36.5% top-1 accuracy (The predicting label obtained from model is the largest one in the output probability vector. If the label is the same as the target label of the motion, the classification is correct.) respectively on the test sets of the HMDB51, UCF101, and Something-Something v1 datasets.

关键词： Action recognition Attention mechanism Res34-SE-IM-net ResNet34-3DRes18

来源：评论

学校读者我要写书评

暂无评论

Cell-type composition analysis of scRNA-seq data with deep convolution neural network

Research Square

引用

Research Square 2020年

作者： Ma, He Fang, Zhihao Liu, Zongbin Chen, Yan College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang China College of Engineering Peking University Beijing China Shenzhen Zigzag Biotechnology Ltd Shenzhen518055 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

Background: With the rapid development of single-cell RNA sequencing (scRNA-seq), more large-scale single-cell sequencing data has been generated. Due to the continuous increase of single-cell sequencing data, the analysis of cell-type composition from single-cell transcriptomics has also to face huge challenges. Since the emergence of scRNA-seq technology, the size of sequencing datasets has grown more than 1 million times in just over a decade. Meanwhile, as more gene markers are discovered, the data dimension of single-cell sequencing becomes higher. All of these put forward more stringent requirements on data dimensionality reduction and clustering algorithms. Under the constraints of practical factors such as occurrence of noise and dropouts and the limitation of overhead, it is also required an effective and efficient method that can obtain accurate analysis results in a very short time, and has a competitive algorithm stability. Results: We present scCAE, an effective and efficient method based on convolution autoencoder that can accurately and rapidly analyze cell-type composition from single-cell transcriptomics datasets. Our method achieved the best results in the data sets that simulate the cell differentiation process among existing methods, which achieved the ARI of 69.64% and 68.83% at 10 and 25 clusters tasks. And, in the case of different dropouts, our method also works well. When the sparsity level of data metric is 71%, scCAE can achieved the ARI of 45.29%, which is the highest of the existing methods. In terms of algorithm overhead, our method has also achieved good results by comparing with several existing methods. It takes less time than most methods and takes up much less memory than other algorithms based neural networks. Conclusions: Our method, scCAE, has more accurate and reasonable results in the analysis of cell-types composition. And, because of the design of imputer, it can deal with a large number of dropouts in the data matrix. Becau

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Chinese Historical Term Translation Pairs Extraction Using Modern Chinese As a Pivot Language

Chinese Historical Term Translation Pairs Extraction Using M...

引用

第十八届中国计算语言学大会暨中国中文信息学会2019学术年会

作者： Xiaoting Wu Hanyu Zhao Lei Jing Chao Che State Grid Info & Telecom Group Beijing China-Power Information Technology Co. LTDBeijingChina Key Laboratory of Advanced Design and Intelligent Computing Ministry of EducationDalian University Chiping Vocational Education School LiaochengChina

ISBN: (纸本)9783030323806

Term translation of Chinese historical classics is very difficult and time-consuming work,and using term alignment methods to extract term translation pairs is of great help for historical term ***,the limited bilingual corpora resources of historical classics and special morphology of the ancient Chinese result in poor performance of term *** this end,this paper proposes a historical term alignment method using modern Chinese as a pivot *** method first identifies English terms by rules,then aligns them from English to modern Chinese and then from modern Chinese to ancient *** use of English-modern Chinese corpus and modern-ancient Chinese corpus instead of English-ancient Chinese corpus solves the shortage problem of the parallel ***,using modern Chinese as a pivot language effectively reduces the alignment errors caused by the abbreviations and the interchangeable characters of ancient *** the term alignment experiment on Shiji,our method outperformed the direct alignment method significantly,which proves the validity of our method.

关键词： Chinese Historical Classics Term Alignment Pivot Language

来源：评论

学校读者我要写书评

暂无评论

I3−/I−Redox Reaction-mediated Organic Zinc-Air Batteries with Accelerated Kinetics and Long Shelf Lives

引用

Angewandte Chemie 2023年第26期135卷

作者： Mangwei Cui Ninggui Ma Hao Lei Youfa Liu Wei Ling Sheng Chen Jiaqi Wang Prof. Hongfei Li Zhaohui Li Prof. Jun Fan Prof. Yan Huang State Key Laboratory of Advanced Welding and Joining Sauvage Laboratory for Smart Materials Shenzhen Key Laboratory of Flexible Printed Electronics Technology School of Materials Science and Engineering Harbin Institute of Technology (Shenzhen) Shenzhen 518055 China Department of Materials Science and Engineering City University of Hong Kong 83 Tat Chee Avenue Kowloon Hong Kong 999077 China Key Laboratory of Radiation Physics and Technology of Ministry of Education Institute of Nuclear Science and Technology Sichuan University Chengdu 610064 China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen 518055 China Songshan Lake Materials Laboratory Dongguan 523808 China Shenzhen China Star Optoelectronic Semiconductor Display Technology Co. Ltd. Shenzhen 518055 China

The storage time of Zn-air batteries (ZABs) for practical implementation have been neglected long-lastingly. ZABs based on organic solvents promise long shelf lives but suffer from sluggish kinetics. Here, we report a longly storable ZAB with accelerated kinetics mediated by I 3 − /I − redox. In the charge process, the electrooxidation of Zn 5 (OH) 8 Cl 2 ⋅H 2 O is accelerated by I 3 − chemical oxidation. In the discharge process, I − adsorbed on the electrocatalyst changes the energy level of oxygen reduction reaction (ORR). Benefitting from these advantages, the prepared ZAB shows remarkably improved round-trip efficiency (56.03 % vs. 30.97 % without the mediator), and long-term cycling time (>2600 h) in ambient air without replacing any components or applying any protective treatment to Zn anode and electrocatalyst. After resting for 30 days without any protection, it can still directly discharge continuously for 32.5 h and charge/discharge very stably for 2200 h (440 cycles), which is evidently superior to aqueous ZABs (only 0/0.25 h, and 50/25 h (10/5 cycles) by mild/alkaline electrolyte replenishment). This study provides a strategy to solve both storage and sluggish kinetics issues that have been plaguing ZABs for centuries, opening up a new avenue to the industrial application of ZABs.

关键词： Iodine-Containing Reaction Kinetics Redox Mediators Storage Time Zn-Air Batteries

来源：评论

学校读者我要写书评

暂无评论

A Segmentation Method of Lung Parenchyma From Chest CT Images Based on Dual U-Net

A Segmentation Method of Lung Parenchyma From Chest CT Image...

引用

IEEE International Conference on Bioinformatics and Biomedicine

作者： Wenjun Tan Jinzhu Yang Yao Liu Xiaoxia Yin Huangying Liu Yanchun Zhang Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Cyberspace Institute of Advanced Technology Guangzhou University Centre for Applied Informatics College of Engineering and Science Victoria University

ISBN: (纸本)9781728118680

Segmentation of lung parenchyma as a pretreatment step for the detection of some lung lesions requires high accuracy to provide more reliable information for lesion detection. In this paper, we proposed a segmentation method of lung parenchyma from chest CT Images by Dual U-Net algorithm based on the characteristics of different lung region. Firstly, the original lung region is extracted from the full chest CT images of patient by an automatic threshold selection method. Then, the images of the different regions of lung is obtained by calculating the area. Finally, the Dual U-Net is trained according the different lung regions. The first U-Net algorithm operates these middle chest images and other images are operated by the second U-Net algorithm to reduce the interference of other images. The experimental results shown that the segmenting results of lung parenchyma by this method are more accurate than the results by single U-Net and U-Net++ algorithm.

关键词： Lung parenchyma segmentation U-Net chest CT images Lung Tissue Chest imaging chest ct images Lung Dual lung lesion

来源：评论

学校读者我要写书评

暂无评论

Regulating Hydrogen/Oxygen Species Adsorption via Built-in Electric Field -Driven Electron Transfer Behavior at the Heterointerface for Efficient Water Splitting

引用

Angewandte Chemie 2024年第16期136卷

作者： Wenjie Zhang Prof. Lei Yang Zhi Li Guangzhi Nie Xuejie Cao Zizheng Fang Prof. Xiaojun Wang Prof. Seeram Ramakrishna Prof. Yunze Long Prof. Lifang Jiao Collaborative Innovation Center for Nanomaterials & Devices College of Physics Qingdao University Qingdao 266071 China Research Center for Smart Intelligent and Wearable Technology College of Textiles and Clothing Qingdao University Qingdao 266071 China Key Laboratory of Advanced Energy Materials Chemistry (Ministry of Education) College of Chemistry Nankai University Tianjin 300071 China College of Electromechanical Engineering Qingdao University of Science & Technology Qingdao 266061 China Center for Nanotechnology & Sustainability Department of Mechanical Engineering College of Design and Engineering National University of Singapore 9 Engineering Drive 1 Singapore 117576

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：