检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,697 篇 会议
41 篇 期刊文献
25 册 图书

馆藏范围

1,763 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,368 篇 工学
- 541 篇 计算机科学与技术...
- 435 篇 软件工程
- 404 篇 材料科学与工程（可...
- 329 篇 机械工程
- 304 篇 力学（可授工学、理...
- 278 篇 化学工程与技术
- 227 篇 土木工程
- 205 篇 动力工程及工程热...
- 162 篇 冶金工程
- 154 篇 电气工程
- 147 篇 控制科学与工程
- 140 篇 建筑学
- 116 篇 信息与通信工程
- 98 篇 电子科学与技术（可...
- 97 篇 仪器科学与技术
- 96 篇 生物工程
- 91 篇 生物医学工程（可授...
- 77 篇 航空宇航科学与技...
- 72 篇 安全科学与工程
- 67 篇 光学工程
894 篇 理学
- 459 篇 数学
- 397 篇 物理学
- 199 篇 化学
- 105 篇 生物学
- 94 篇 统计学（可授理学、...
- 73 篇 地球物理学
220 篇 管理学
- 174 篇 管理科学与工程(可...
- 56 篇 工商管理
- 53 篇 图书情报与档案管...
56 篇 医学
31 篇 经济学
30 篇 农学
16 篇 教育学
9 篇 法学
5 篇 军事学
3 篇 文学
2 篇 艺术学

主题

105 篇 computational mo...
50 篇 computational fl...
47 篇 finite element m...
34 篇 accuracy
30 篇 deep learning
30 篇 feature extracti...
25 篇 finite element m...
22 篇 training
21 篇 mechanical engin...
20 篇 predictive model...
20 篇 mathematical mod...
20 篇 numerical models
20 篇 data models
17 篇 neural networks
17 篇 biological syste...
17 篇 numerical method...
16 篇 stress
15 篇 iterative method...
14 篇 real-time system...
13 篇 optimization

机构

10 篇 department of me...
8 篇 school of mechan...
7 篇 iet department o...
6 篇 gl bajaj inst te...
5 篇 department of ci...
5 篇 institute of inf...
5 篇 school of cyber ...
5 篇 department of me...
5 篇 department of me...
4 篇 the islamic univ...
4 篇 school of comput...
4 篇 department of me...
4 篇 department of me...
4 篇 school of mechan...
3 篇 national institu...
3 篇 college of mecha...
3 篇 naval university...
3 篇 gl bajaj inst te...
3 篇 school of mechan...
3 篇 school of energy...

作者

16 篇 dwivedi shashi p...
9 篇 manjunatha m.
8 篇 srivastava ashis...
6 篇 srivastava visha...
6 篇 kumar harish
5 篇 rastogi vikas
5 篇 husaini
5 篇 sharma rahul
5 篇 syuhada ahmad
5 篇 chaturvedi risha...
5 篇 manos george c.
5 篇 chauhan sandeep
4 篇 yadav omprakash
4 篇 maurya nagendra ...
4 篇 sharma aman
4 篇 amardeep
4 篇 saraswat manish
4 篇 gupta tarun kuma...
4 篇 reshma t.v.
4 篇 mohamed aezeden

语言

1,551 篇 英文
206 篇 其他
6 篇 中文

检索条件"任意字段=3rd International Conference on Computational and Experimental Methods in Mechanical Engineering"

共 1763 条记录，以下是431-440 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

High Temperature Oxidation Behavior of 439 Ferritic Stainless Steel at Different Temperatures 3

High Temperature Oxidation Behavior of 439 Ferritic Stainles...

引用

2023 3rd international conference on Industrial Manufacturing and Structural Materials, IMSM 2023

作者： Zhu, E.N. Xia, Dianxiu Han, Qing Chen, Peidun Wang, Xuelin Liu, Zhiheng Jiang, Kun Department of Mechanical Engineering University of Jinan Shandong Jinan250022 China Technology R&D Center Taishan Steel Shandong Jinan271100 China School of Materials Science and Engineering University of Science and Technology Beijing Beijing100083 China

In recent years, due to the installation of selective catalytic reduction (Selective Catalytic Reduction, hereinafter referred to as SCR) devices, high temperature oxidation failure has occurred frequently in automobile exhaust systems. To explore its high temperature failure mechanism, this paper takes 439 ferritic stainless steel which is often used in automobile exhaust pipes as an example and uses Xrd, SEM, and EDS experimental methods to study its oxidation behavior at 700 °C, 800 °C and 900 °C. The results show that the oxide layer becomes thicker and the failure degree increases with the increase of the working temperature of 439 stainless steel. The oxidation products at different temperatures are different. When the oxidation temperature is 700 °C, the phase structure of the oxide layer on the surface of the sample is Cr2O3 and Fe2O3, and the oxide layer is dense and uniform. As the temperature rises to 800 °C, the surface oxidation products are sintered together, and the needle-like Fe2O3 structure appears on the oxide film. When the oxidation temperature rises to 900 °C, the oxide layer appears inner and outer layers, the outer layer is Fe2O3 shell structure, the inner layer is generated FeO, Fe2O3, and other iron oxides, and oxidation is very serious. At the junction of the oxide layer and the substrate, there are particles such as SiO2, TiO2, Fe2Nb in the substrate, which has a positive effect on the high temperature oxidation. © 2023 Institute of Physics Publishing. All rights reserved.

关键词： Thermooxidation

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Invisible an In-Depth Analysis of Text Steganography Techniques, Challenges, and Advancement

Unveiling the Invisible an In-Depth Analysis of Text Stegano...

引用

Technological Advancements in computational Sciences (ICTACS), international conference on

作者： Lalit Kumar Tyagi Anish Gupta Aezeden Mohamed Department of CSE GL Bajaj Institute of Technology & Management Greater Noida Zonal Head North IT Academics iNurture Education Solutions Pvt Ltd Bengaluru Mechanical Engineering Department PNG University of Technology Papua New Guinea

Text steganography is the art and science of concealing hidden messages inside ordinary text without raising red flags. It's an intriguing field. Because of the increasing dependence on digital communication and the urgent need for secure and confidential information transfer, text steganography has attracted a lot of attention as a dependable means of establishing covert communication and data verification. This work provides a comprehensive review of the most recent results in text steganography, including a variety of approaches, challenges, and possible directions for further research. At the beginning of the article, the idea of text steganography is presented along with its significance for preserving secure communication. It looks at several text steganography methods such as alignment modification, synonym substitution, word order change, and linguistic steganography. Every method is thoroughly discussed, with a focus on the key ideas, benefits, and drawbacks of each. The challenges of text steganography are examined, emphasising resistance and detection. The study looks at comparison and statistical analysis methods for finding concealed messages and research into developing robust steganographic systems that may thwart detection attempts. It also examines the most recent advancements in text steganography, including the use of natural language processing and deep learning to enhance concealment and get around detection challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Skin Disease Classification Based on Multi-level Feature Fusion and Attention Mechanism

Skin Disease Classification Based on Multi-level Feature Fus...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), international conference on IEEE international conference on

作者： Xinhua Liu Licheng Yang Xiaolin Ma Hailan Kuang School of Information Engineering Wuhan University of Technology Wuhan China Hubei Key Laboratory of Broadband Wireless Communication and Sensor Networks

Up to now, skin cancer is one of the most common cancers with great danger, thus it is very essential to diagnose at an early state to save patients lives. Recent work has applied methods based on convolutional neural networks(CNNs) to classify images of skin lesions for diagnosis. However, most of these methods failed to work well on mobile or embedded devices due to the huge computational cost and memory requirements. Even though lightweight CNNs have been developed for mobile devices, they perform poorly on multi-classification tasks. To solve these shortcomings, we propose a method based on multi-level feature fusion and attention mechanism, MFA-MViT. The effectiveness of MFA-MViT was evaluated on the ISIC-PAD dataset built based on the ISIC2019 and PAD-UFES-20 datasets. The experimental results show that the classification effect is better than that of similar methods within a small amount of computation and parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Network Approaches for Magnetization Surface Prediction in Switched Reluctance Motors: Classical, Radial Basis Function, and Physics-Informed Models

Neural Network Approaches for Magnetization Surface Predicti...

引用

Informatics, Electronics, and Radio engineering (PIERE), international conference Problems of

作者： Galina Demidova Andrey Bogdanov Andrei Iaremenko Zhu Xirong Hao Chen Alecksey Anuchin Electric Drive Department Moscow Power Engineering Institute Moscow Russia Faculty of Control System and Robotics ITMO University Saint-Petersburg Russia School of Electrical and Power Engineering China University of Mining and Technology Xuzhou China

ISBN: (数字)9798331516321

ISBN: (纸本)9798331516338

This paper investigates the prediction of magnetization surfaces in Switched Reluctance Motors using three distinct methods: classical Neural Networks, Radial Basis Function networks, and Physics-Informed Neural Networks. The study utilizes experimental data from a 7.5 kW SRM to assess the performance of these approaches, with all methods implemented in Python. Among the methods analyzed, PINN demonstrates the highest accuracy in predicting the magnetization surfaces, effectively capturing the underlying physical behavior of the motor. The computational costs of each method are evaluated, providing insights into training times, inference speeds, and floating-point operations per sample. The findings reveal that while NN offers a reasonable balance between performance and efficiency, the RBF method excels in training speed but shows limitations in capturing the physical dynamics of the system. In contrast, the PINN not only delivers superior predictive performance but also emphasizes the significance of incorporating physical principles into machine learning frameworks. The results highlight the applicability of these methods across various types of SRMs, suggesting their potential for enhancing control strategies in electrical and power engineering applications.

关键词： Training Power engineering Electric potential Accuracy Magnetization Radial basis function networks Machine learning Artificial neural networks Switched reluctance motors computational efficiency

来源：评论

学校读者我要写书评

暂无评论

A Method of Robot Grasping Based on Reinforcement Learning 3

A Method of Robot Grasping Based on Reinforcement Learning

引用

2021 3rd international conference on Robotics, Intelligent Control and Artificial Intelligence, ICRICA 2021

作者： Lu, Liangliang Zhang, Ming He, Dingxin Gu, Qiang Gong, Dongjun Fu, Lei Artificial Intelligence and Automation College Huazhong University of Science and Technology Wuhan China Guyue Home PS-Micro Wuhan China School of Mechanical Engineering Wuhan Vocational College of Software and Engineering Wuhan China

In this paper, we propose a method for robot grasping based on reinforcement learning. A six-degree-of-freedom robot is used to execute the grasping action, and an RGB-D camera is used as a sensing module to collect the information. Different from previous model-based methods, our whole system is data-driven. In order to better grasp a bunch of randomly placed objects, the pushing action is added to spare more space for grasping. The whole process is described as a Markov decision process (MDP). The training is carried out in simulation. experimental results show that our method can complete the grasping work efficiently, especially in those complicated and difficult scenarios. At the same time, the model can be directly applied in actual grasping tasks which greatly reduce the risk of training in the physical world. © Published under licence by IOP Publishing Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Taguchi’s based approach to optimize the foundry’s green sand casting process parameters

Taguchi’s based approach to optimize the foundry’s green s...

引用

computational Modelling, Simulation and Optimization (ICCMSO), international conference on

作者： Jayant Singh Ankit Saxena Deepak Bhardwaj Pradeep Rohilla Mechanical Engineering Department Dr. Akhilesh Das Gupta Institute of Professional Studies New Delhi India

ISBN: (数字)9798350361391

ISBN: (纸本)9798350361407

The worldwide foundry industry’s development prospects have been greatly enhanced by the spike in demand for metal casting across numerous industries. For a foundry to successfully satisfy output requirements, it is essential to achieve optimal performance with low faults. For manufacturing to be effective, problems in the product must be found and fixed via methodical examination. This work illustrates how Taguchi’s design of experiments methodology may be used to optimize the sand casting process’s *** L9 orthogonal array and the Taguchi optimization technique are used to optimize the sand casting process parameters, and experimental analysis is used to verify the results. Important factors are taken into consideration, including the response variable of weight percentage inaccuracy and characteristics like moisture percentage, mould hardness number, and green compressive strength. experimental testing validates the results, which show a decrease in weight % error and, in the end, improved casting quality. The weight of the cast product noticeably increases with use of the Taguchi optimized parameters. This emphasizes how critical it is to reduce casting flaws since doing so produces more evenly and densely cast products, which improves overall quality.

关键词： Industries Casting Design methodology Moisture Metals Foundries Software

来源：评论

学校读者我要写书评

暂无评论

Augmentation of topic modeling: Comparing the traditional and their word embedding oriented approaches

Augmentation of topic modeling: Comparing the traditional an...

引用

international Symposium on Advanced Computing and Communication (ISACC)

作者： Gobind Kumar Das Panthadeep Bhattacharjee Department of Computer Science & Engineering National Institute of Technology Rourkela Rourkela India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

This paper compares the efficacy of classical topic modeling approaches namely the Latent Dirichlet Allocation (LDA) and Non-Negative Matrix Factorization (NMF) with their respective word embedding enhanced techniques. The LDA and NMF are based on word frequency and co-occurrence patterns, but ignore the semantic similarity between words. To address these limitations, the proposed methods enhance the LDA and NMF with Word2Vec embeddings by capturing the semantic relationships, and overseeing the improvement in topic coherence. This study therefore examines the comparable strengths of these approaches and shows how word embeddings can improve overall topic modeling. Our experimental results have shown that the Word2Vec enhanced LDA and NMF improve the coherence scores over their traditional counterparts.

关键词： computational modeling Semantics Coherence Resource management Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Research on turn-based war chess game based on reinforcement learning

Research on turn-based war chess game based on reinforcement...

引用

Power Electronics, Computer Applications (ICPECA), IEEE international conference on

作者： Yu Chen Ling Bai Yao Tan Yahui Liu Hai Nan School of Computer Science and Engineering Chongqing University of Technology Chongqing China

The search algorithm for turn-based war chess game is still using the traditional algorithm, and the whole war chess game needs a huge computational power, resulting in the research of turn-based war chess game in artificial intelligence is relatively backward. In this paper, we design a turn-based war chess game algorithm based on reinforcement learning, which is composed of Monte Carlo tree search (MCTS) and deep neural network. Monte Carlo tree search relies on strategy network to simulate chess several times, to choose better chess quality; The deep neural network reversely trains the strategy network through the final chess outcome. The experimental results show that there is no defeat in 10Kvs5K and 10Kvs3K game. This algorithm can improve the chess skill through self-game when there is no human knowledge and learning from scratch in turn-based war games.

关键词： Deep learning Monte Carlo methods computational modeling Neural networks Games Reinforcement learning Computer applications

来源：评论

学校读者我要写书评

暂无评论

Intracranial pressure measurement under shock wave based on physical head surrogate 3

Intracranial pressure measurement under shock wave based on ...

引用

3rd international conference on Defence Technology, ICDT 2022

作者： Xiong, Man-Man Tian, Cong-Ling An, Shuo Zang, Li-Wang Xu, Cheng Li, Feng-Xia School of Mechanical Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China Science and Technology on Transient Impact Laboratory No.208 Research Institute of China Ordnance Industries Beijing102202 China Zhiyuan Research Institute Zhejiang Hangzhou310024 China Harbin Longjiang Special Equipment Company Limited Harbin100050 China

In order to explore the intracranial pressure response under different sensor fixation modes, the experimental study on the pressure measurement based on physical head surrogate under shock wave is carried out. The influence of different sensor fixation methods on the intracranial pressure was analyzed. The results show that sensor fixation mode has little influence on the pressure test results. The deviation between the pressure peak and impulse is only 3.62% and 4.54% in the two modes of hot melt supporting and free suspension. The deviation of pressure peak value between metal supporting and free suspension is 5.59%. In comparison, hot melt supporting fixation has less influence on intracranial pressure results. The orientation of sensor sensitive surface has little influence on the pressure test results. When sensor was fixed by the metal bracket, the deviation of pressure peak is only 4.03% between sensitive surface face to impact source and sensitive surface back to shock source. © Published under licence by IOP Publishing Ltd.

关键词： Shock waves

来源：评论

学校读者我要写书评

暂无评论

Music classification with convolutional and artificial neural network 3

Music classification with convolutional and artificial neura...

引用

3rd international conference on Signal Processing and Machine Learning, CONF-SPML 2023

作者： Li, Zuge Peng, Haitao Tan, Siwei Zhu, Fangyu College of Letters and Science University of California Davis DavisCA95618 United States School of Mechanical Electrical and Information Engineering Shandong University Weihai China College of Letters and Science University of California Davis DavisCA95616 United States John Muir College University of California San Diego La Jolla CA92093 United States

Music genre classification focus on efficiently finding expected music with a similar genre through numerous melodies, which could better satisfy the tastes and expectations of the users when listening to music. This paper proposes a new method to classify different kinds of music with Artificial Neural networks (ANN) and Convolutional Neural Networks (CNNs). First, Mel Frequency Cepstral Coefficients (MFCC) are used to preprocess the Mel-frequency cepstrum (MFC). Then, we upgrade Anupam's CNN model. Since the extracted features only by MFC are not suitable for CNN to learn as a small dataset like this. Multiple features are then exacted for each audio file. The two most correlated features on the datasets are adopted as the input of an ANN. To verify the proposed method's effectiveness, we compare our method with other state-of-the-art methods on the GTZAN dataset. The experimental results show that we can get higher accuracy compared to Anupam. If using only one MFCC feature, Conv-Conv-Pool, a sub-structure that we add two convolutional layers before each max pooling layer, performs better than Conv-Pool, and Conv-Pool performs better than ANN. However, by concatenating another correlated feature, spectral centroid means, which is a measure used in digital signal processing to characterize a spectrum, a simple ANN can have much higher accuracy than the one utilizing only a single MFCC feature with an accuracy of about 94.1%. © Published under licence by IOP Publishing Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共177页 << < 40 41 42 43 44 45 46 47 48 49 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：