检索结果-内蒙古大学图书馆

Exploring deep Learning Methods for Computer Vision Applications across Multiple Sectors:Challenges and Future Trends

引用

Computer Modeling in Engineering & Sciences 2024年第4期139卷 103-141页

作者： Narayanan Ganesh rajendran Shankar Miroslav Mahdal Janakiraman SenthilMurugan Jasgurpreet Singh Chohan Kanak Kalita School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaram522502India Department of Control Systems and Instrumentation Faculty of Mechanical EngineeringVSB-Technical University of OstravaOstrava70800Czech Republic Department of Computer Science and Engineering Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering CollegeChennai600062India Department of Mechanical Engineering and University Centre for Research&Development Chandigarh UniversityMohali140413India Department of Mechanical Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyAvadi600062India

Computer vision(CV)was developed for computers and other systems to act or make recommendations based on visual inputs,such as digital photos,movies,and other *** learning(dL)methods are more successful than other traditional machine learning(ML)methods *** techniques can produce state-of-the-art results for difficult CV problems like picture categorization,object detection,and face *** this review,a structured discussion on the history,methods,and applications of dL methods to CV problems is *** sector-wise presentation of applications in this papermay be particularly useful for researchers in niche fields who have limited or introductory knowledge of dL methods and *** review will provide readers with context and examples of how these techniques can be applied to specific areas.A curated list of popular datasets and a brief description of them are also included for the benefit of readers.

关键词： Neural network machine vision classification object detection deep learning

来源：评论

学校读者我要写书评

暂无评论

High-resolution coupling of stratigraphic'sweet-spot'lithofacies and petrophysical properties:A multiscale study of Ordovician Goldwyer Formation,Western Australia

引用

Petroleum Science 2023年第3期20卷 1312-1326页

作者： Yu-jie Yuan reza rezaee Jian-Wei Gu Song-Tao Wu Emad A.Al-Khdheeawi Jun Wang Bin Pan School of Earth Sciences Yunnan UniversityKunmingYunnan650500China Western Australian School of Mines:Minerals Energy and Chemical EngineeringCurtin UniversityPerthWestern AustraliaAustralia School of Petroleum Engineering China University of Petroleum(East China)QingdaoShandong266580China Research Institute of Petroleum Exploration and Development CNPCBeijing100083China National Energy of Tight Oil and Gas R&D Center Bejing100083China Petroleum Technology Department University of Technology-IraqBaghdad10066Iraq School of Civil and Resource Engineering University of Science and Technology BeijingNo.30Xueyuan RoadBeijing10083China State Key Laboratory of Coal Mine Disaster Dynamics and Control Chongqing UniversityChongqing400044China

The identification of stratigraphic'sweet-spot'interval is significant in oil and gas formation ***,formation evaluation in macroscopic-scale merely provides low resolution and limited infor-mation,thus may lead to uncertainties in resource *** accurately identify the'sweet-spot'intervals amongst heterogeneous lithofacies,we conducted a very high-resolution and quantitative analysis from in-situ macroscopic scale to laboratory microscopic scale on the Goldwyer formation of Canning Basin,Western *** comprehensive advanced well logging and slim-compact micro imager(SCMI)technologies were synthetically applied in couple with the laboratory nanoscaled *** results unveiled an extraordinarily large lithofacies heterogeneity between different rock intervals,with distinguished features shown in Goldwyer Ⅰ,Ⅱ,and Ⅲ *** most favorable lithofacies is recognized as the laminated argillaceous thermally-matured organic matter(OM)-rich mudstone,which is widely developed in Goldwyer Ⅲ as the major attributor to'sweet-spot'*** Ⅱ is exclusively characterized by thick mudstone intervals(94.4%),interbedded with thin calcareous mudstones(5.5%),corresponding to a depositional environment of low-energy distal section of the outer ramp ***,the most favorable lithofacies in'sweet-spot'intervals develop numerous OM-/mineral nanopores for hydrocarbon ***-rich lithofacies develops abundant inter-particle pores from 2 to 17 nm that mainly contribute to pore volume for free gas storage ***-rich lithofacies with higher maturity have OM-pores with good connectivity,bearing large specific surface area that is beneficial for adsorbed gas capacity.

关键词： Shale Nanopore structure Pore characterization Lithofacies

来源：评论

学校读者我要写书评

暂无评论

Efficient predictive simulation of tool wear in face milling using an advanced 3d numerical approach

引用

Wear 2025年 570卷

作者： Methon, Grégory Courbon, Cédric Auzenat, François M'Saoubi, rachid Girinon, Mathieu rech, Joël Ecole Centrale de Lyon CNRS ENTPE LTDS UMR5513 ENISE 42023 Saint Etienne France R&D Milling and Process Seco Tools AB 22 avenue de la prospective 18020 Bourges France R&D Material and Technology Development Seco Tools AB FagerstaSE-73782 Sweden Cetim 7 rue de la Presse Saint-Etienne42952 France

Being able to predict tool life and the optimal cutting conditions for any combination of cutting tool system and workmaterial is clearly an up-to-date research issue. This work presents an innovative strategy for predicting efficiently tool wear in face milling operations. The primary objective is to develop a methodology capable of handling complex 3d geometries and tool paths within an industrially acceptable computing time. The approach involves a new 3d multi-scale numerical method based on discretizing the tool cutting edge into 2d elementary sections. A 2d Arbitrary Lagrangian-Eulerian (ALE) finite element cutting model is employed to compute local contact pressure, sliding velocity, and heat flux along each section in parallel. An elementary wear equation is applied to calculate the local wear rate after a given time increment, simulating all 2d worn profiles. These profiles are then merged to generate the updated 3d geometry of the worn tool. An iterative procedure is conducted to simulate the evolution of the cutting tool geometry over an extended cutting period. By achieving a good agreement with experimental results in a reasonable computation time, this strategy demonstrates significant potential for optimizing tool life and performance in milling operations. © 2025 Elsevier B.V.

关键词： Milling (machining)

来源：评论

学校读者我要写书评

暂无评论

dynamical Encircling of a Lock-In Area with a Combination of Fast and Slow dithering in a ring Laser Gyroscope

Dynamical Encircling of a Lock-In Area with a Combination of...

引用

2023 IEEE International Symposium on Inertial Sensors and Systems (INErTIAL)

作者： Woo-Seok Choi Jun-Eon An Cheon-Joong Kim Kyu-Min Shim The 1 R&D Institute 6th DIR. Agency for Defense Development Daejeon Republic of Korea Emerging Science and Technology DIR. Agency for Defense Development Daejeon Republic of Korea

This study proposes a combination of fast and slow dithering in a ring laser gyroscope (rLG) and analyzes the related characteristics through numerical experiments. The results of this study are significant compared to the existing methods that use sinusoidal dithering with a single frequency component. The results show that the proposed method can contribute to developing new alternatives for improving rLG performance when high static lock-in frequencies are considered.

关键词： Inertial sensors ring lasers Gyroscopes Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Single and Multi NPU Chiplet Heterogeneous Integration packaging based on Fanout rdL interposer with Silicon bridge technology

Single and Multi NPU Chiplet Heterogeneous Integration packa...

引用

Electronic Components and technology Conference (ECTC)

作者： Lewis Kang Jay Kim Bruce Lee Jade Park Han Ju Yu Sung Hyuk Lee Jacinta Aman Lim Min Ji Lee Seong Hwan Han Jae Kyung Lee Hailey Hwang SEMI R&D Center Corporate CTO Unit Nepes Corporation Republic of Korea Corporate CTO Unit Nepes Corporation Republic of Korea Advanced Technology Part SEMI R&D Center Corporate CTO Unit Nepes Corporation Republic of Korea Oversee Sales Part Business Development Div. Nepes Corporation USA

ISBN: (数字)9798350375985

ISBN: (纸本)9798350375992

A chiplet is a die that is designed to be integrated with other chiplets in some type of advanced package. That package could be a system-in-package (SiP), 2.5d (planar or vertical), or 3d-IC. Nearly all chiplets in use today are being developed with some sort of standard interconnect or protocol and re-use them across multiple designs. Logic, memory, sensors, MEMS, mixed-signal, or any one of a variety of different functions can be developed as chiplets. And a 28nm chiplet may be placed next to, and work together with, a 5nm chiplet. The concept is basically to shrink a printed circuit board and put all the pieces into a much smaller space. That increasingly exceeds the size of a reticle, which 858mm² with EUV steppers, and 429mm² with high-NA EUV *** has been developing NPU (Neuromophic Processor Unit) to be integrated together with memory(HBM) or other chiplets by 2.5d Heterogeneous Integration technology. 2.5d Heterogeneous Integration package includes Fan-out based on rdL interposer. Two types of 2.5d package were considered according to the applications, like edge computing or data center computing, kind of more complicated application. The application of edge computing would be less performance compared to the application of data center computing. Then, its NPU needs to be interconnected with memory (HBM or ddr) directly while multi NPUs need to be integrated with memories by embedded bridge technology inside rdL interposer. In case of multi NPUs packaging with memories, Silicon bridges need to be embedded inside rdL interposer as a signal interconnection between NPU and memory or between NPU and ***, single NPU packaging with memory has been developed by applying rdL interposer technology in terms of edge computing application. Single NPU was integrated with two HBM3 on an rdL organic interposer which consists of multi rdL layers (over 6 layers without UBM and pad layer) with minimum line and space of 2 um. In order to interconnect between

关键词： Heating systems Bridges System-in-package Multichip modules Integrated circuit interconnections Bridge circuits Computer architecture

来源：评论

学校读者我要写书评

暂无评论

The Non-destructive Three-dimensional Analysis of Crack in Solder Joints Employing by deep Learning Technique

引用

Journal of Japan Institute of Electronics Packaging 2024年第5期27卷 466-471页

作者： Hasegawa, Masashi Onizuka, riri Ogata, Shin Ueki, ryusuke Takahashi, Masanori R&D development Qualtec Co. Ltd. 4-230 Sambo-cho Sakai-ku Sakai-shi590-0906 Japan Quality Technology development Qualtec Co. Ltd. 4-230 Sambo-cho Sakai-ku Sakai-shi590-0906 Japan

来源：评论

学校读者我要写书评

暂无评论

Co-training Semi-supervised Learning Algorithm for Classification of Seismic Facies of Carbonate Tidal Channels 11th

Co-training Semi-supervised Learning Algorithm for Classific...

引用

11th International Field Exploration and development Conference, IFEdC 2021

作者： Wang, ru-yi Wang, Zhi-zhang Yang, Xiang-Tong Xu, Zhen-yong Guo, Fa-jun Downhole Operation Research Department CNPC Engineering Technology R&D Company Limited Beijing China College of Geosciences China University of Petroleum-Beijing Beijing China Research Institute of Petroleum Exploration and Development Beijing China Research Institute of Exploration and Development PetroChina Hua Bei Oilfield Company Shangqiu China

ISBN: (纸本)9789811921483

This primary goal of this study was to improve the accuracy of seismic identification of carbonate tidal channels and to achieve quantitative characterization of seismic facies. This paper is the first to present a co-training semi-supervised learning algorithm for use with seismic and drilling data to identify the sedimentary microfacies patterns of tidal channels within carbonate reservoirs. Co-training is a semi-supervised machine learning algorithm by which the feature dataset is split into two subsets, and a classifier is established for each feature subset. Each subset is re-trained based on the classification results of the other subset until the same classification results are obtained for most of the data in the two subsets. Taking the Mb1-3 subzone of the Mishrif Formation, West Qurna Oilfield-1 (Iraq) as an example, we employed zero-crossing-wrapping method to extract 18 seismic attributes of the target zone. The sliding window method was used to optimize 12 seismic attributes, and a hierarchical clustering algorithm based on correlation coefficients was used to group these seismic attributes. Using the two seismic attribute groups as feature data, we employed logistic regression, decision tree, and the k-nearest neighbor classifiers to conduct co-training semi-supervised learning for the classification and identification of tidal channels and lagoons. The results showed that the co-training semi-supervised learning algorithm improved the accuracy rate of each classifier, reduced background noise and clutter signals, and enhanced the continuity of the plane distribution of the tidal channel prediction results. In summary, the co-training semi-supervised learning algorithm significantly improved the efficiency of seismic facies identification of tidal channels. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Exploring the role of Natural Language Processing in Educational Chatbots: A Machine Learning Approach 7

Exploring the Role of Natural Language Processing in Educati...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： reddy, G. Swamy rizvi, Haider Ali Kochhar, Harmeet Kaur Shaikh, Ajim Udhayakumar, r. dhanraj, Joshuva Arockia Sr University School of Sciences Warangal India Shoolini University Yogananda School of Artificial Intelligence India University Institute of Media Studies Chandigarh University India Pune India Institute of Science and Technology VelTech Rangarajan Dr Sagunthala R&d Avadi TamilNadu Chennai India Lovely Professional University Research and Development Cell Jalandhar-Delhi Grand Trunk Road Punjab Phagwara144411 India

ISBN: (纸本)9798350350067

AI in the classroom instruction of languages an exciting potential effect that is altering teaching strategies and student involvement. Everything is simply achievable, including chatbots and natural-language processing (NLP) technology. Therefore, in order to verify the influence of AI on language acquisition, this study will evaluate the research, concentrating on programs like ChatGPT that provide individualized and engaged educational opportunities. Inversely, AI-driven chatbots that imitate real-world interactions, such as ChatGPT, supply very adaptable and accessible language training tools. Yet, forthcoming problems with correctness, societal prejudices, and the most suitable usage of AI stress their early promise. These demand that teachers and students improve their digital skills in order to use AI technology in a responsible and effective way. With a focus on present developments and potential futures, it highlights the crucial role artificial intelligence (AI) is playing in revolutionizing language teaching. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation on the distribution uniformity and pressure drop of perforated plate distributors for the innovative spray-type packed bed thermal storage

引用

Particuology 2022年第2期20卷 60-73页

作者： Lin Lin Liang Wang Xipeng Lin Ningning Xie Haisheng Chen Institute of Engineering Thermophysics Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Dalian National Laboratory for Clean Energy Chinese Academy of SciencesDalian 116023China National Energy Large Scale Physical Energy Storage Technologies R&D Center of Bijie High-tech Industrial Development Zone Guizhou 551712China Institute of Science and Technology China Three Gorges CorporationBeijing 100038China

As an innovative thermal energy technology,the spray-type packed bed has advantages of high efficiency and low cost.A liquid distributor is the key component for the spray-type packed bed for scattering heat-transfer liquid drops *** this study,the distribution performance and pressure drop of the perforated plate distributors of different orifice diameters were studied *** experimental results indicate that orifice diameter has a greater effect on the distribution performance compared to flow *** an increase in flow rate,the flow pattern through the distributor changes from the uncovered drop to the covered drop and then to the jet *** covered drop pattern shows the best performance with a good distribution and a small pressure drop simultaneously,which is the design and optimization principle of the distributor for a spray-type packed bed.

关键词： Spray-type packed bed Perforated plate distributor distribution Pressure drop Thermal energy storage

来源：评论

学校读者我要写书评

暂无评论

research and application of supramolecular gel plugging agent in abnormal pressure reservoir 10

Research and application of supramolecular gel plugging agen...

引用

10th Global Conference on Materials Science and Engineering, CMSE 2021

作者： Baletabieke, B. Gu, Y.X. Zhou, T. duan, d.X. Liu, J.T. Kong, X.J. Qian, F. Li, W.J. Zhong, Z. Xiang, Y. Jing, N. Li, J.Y. CNPC Engineering Technology R&D Company Limited Beijing102206 China China National Oil and Gas Exploration and Development Corporation Beijing100034 China

The Aktobe project is the largest oil and gas producing area of PetroChina in Central Asia. However, after years of exploitation, the pressure of the reservoir has dropped, making it difficult to increase the production of a single well. Both the Kenkyak block and North Troyes block of the project have induced fractured leakage, and frequent leakage affects safe and efficient drilling and completion operations and production. Therefore, the research on leakage prevention and control technology is very necessary. This article focuses on the characteristics of the cracks in the high-pressure area of the Kenkyak block and the cracks in the low-pressure area of the North Troyes block. Aiming at the fracture characteristics of the high-pressure zone in the Kenkyak block and the low-pressure zone in North Troyes block, and taking advantage of the synergistic effect of supramolecules, a supramolecular plugging-while-drilling agent was developed based on the deformable fiber composite gel. It forms a strong adhesion plugging layer on the inner wall of the leakage channel through the strong adhesion force, and it achieves a good plugging effect. The 300-500md sand disc bearing pressure could reach 700psi when adding 3% agent, and the bearing pressure of 3-5d permeability sand disc could reach above 450psi. A supramolecular static plugging agent was also developed based on the dilatant gel. It is rich in strong shear reversible gel with supramolecular structure, which guarantees its pumpability and plugging performance. The effective rate of one-time plugging is over 80%, and the viscosity is greatly reduced after the gel is broken for 72hr, which benefits the reservoir protection. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Adhesion

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：