检索结果-内蒙古大学图书馆

Optimization of wear properties on AA7075/Sic/Mos 2 hybrid metal matrix composite by response surface methodology

学校读者我要写书评

暂无评论

Materials Today: Proceedings 2021年 46卷 4019-4024页

作者： K. Umanath K. Palanikumar Veeramalai Sankaradass K. Uma Deaprtment of Mechanical Engineering Acadamy of Maritime Education and Training Chennai 603112 India Sri SairamInstitute of Technology Chennai 600044 India Department of Computer Science and Engineering ISL Engineering College Hyderabad Telangana 500005 India Department of Software and Systems Engineering School of Information Technology and Engineering VIT University Vellore 632014 India

Nowadays, composites are profoundly thriving as the replacement of ferrous alloys . The Aluminum manifested into a great substitute due to its properties like lightweight, low density, high strength, and corrosion resistance . The process of fusing the non-ceramics reinforcement like Silicon carbide , Boron carbide , Aluminum oxide , Titanium diboride with a non-metal like Graphite, Molybdenum disulfide or with other non-ceramic to form a hybrid metal matrix composite . In the present paper, an investigation carried out on Aluminum 7075 material by the process of stir casting where the Silicon Carbide (SiC) with three different weight % (i.e., 3%, 6%, 9%) and Molybdenum Disulphide (MoS 2 ) with 1% constant weight % added to the base material. The tensile test and hardness test were then done on a UTM and Rockwell Hardness testing machine, respectively, for all three prepared materials. As the percentage of SiC increases in the material, the hardness value and tensile strength are increasing. The Al7075 + 9%SiC + 1%MoS 2 is the highest of all.

关键词：

A Novel 6dof Pose Estimation Method Using Transformer Fusion

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Wang, Huafeng Zhang, Haodu Liu, Wanquan Hu, Zhimin Gao, Haoqi Lv, Weifeng Gu, Xianfeng School of Information Technology North China University of Technology Beijing100122 China School of Software Beihang University Beijing100191 China School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou510335 China University of Wisconsin Madison United States Department of Computer Science Stony Brook University NY11794-2424 United States

Integrating heterogeneous information in multimodal tasks presents challenges in effectively leveraging complementary information. This is particularly evident in the context of 6D pose estimation, where the effective utilization of RGB-D data is crucial for extracting supplementary information that complements 2D and 3D data. Another challenge is aligning modalities implicitly to obtain robust estimation results. To tackle these challenges, we propose a Transformer-based fusion module that facilitates hierarchical fusion across modalities at different stages. This approach effectively combines disparate features and complements global information in a non-convolutional manner. Additionally, we employ an attentional residual structure to address two primary challenges. Firstly, it mitigates information loss that may occur due to the stacking depth of layers. Secondly, it leverages attention weights to adapt the output of the preceding layer, thereby enhancing modal alignment. We validate our approach on two benchmark datasets: LineMOD [1] and YCB-Video [2]. Our method outperforms most existing methods on the LineMOD dataset and achieves state-of-the-art results on the YCB-Video dataset, showcasing its superior generalization ability. © 2023, The Authors. All rights reserved.

关键词：

Sample-Efficient and Surrogate-Based Design Optimization of Underwater Vehicle Hull

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Vardhan, Harsh Hyde, David Timalsina, Umesh Volgyesi, Peter Sztipanovits, Janos Department of Computer Science Vanderbilt University 1400 18th Ave. S. NashvilleTN37212-2846 United States Institute for Software Integrated Systems Vanderbilt University 1025 16th Ave. S. NashvilleTN37212-2328 United States Department of Electrical and Computer Engineering Vanderbilt University 400 24th Ave. S. NashvilleTN37212 United States

Physics simulations are a computational bottleneck in computer-aided design (CAD) optimization processes. Hence, in order to make accurate (computationally expensive) simulations feasible for use in design optimization, one requires either an optimization framework that is highly sample-efficient or fast data-driven proxies (surrogate models) for long-running simulations. In this work, we leverage recent advances in optimization and artificial intelligence (AI) to address both of these potential solutions, in the context of designing an optimal unmanned underwater vehicle (UUV). We first investigate and compare the sample efficiency and convergence behavior of different optimization techniques with a standard computational fluid dynamics (CFD) solver in the optimization loop. We then develop a deep neural network (DNN) based surrogate model to approximate drag forces that would otherwise be computed via direct numerical simulation with the CFD solver. The surrogate model is in turn used in the optimization loop of the hull design. Our study finds that the Bayesian Optimization—Lower Condition Bound (BO-LCB) algorithm is the most sample-efficient optimization framework and has the best convergence behavior of those considered. Subsequently, we show that our DNN-based surrogate model predicts drag force on test data in tight agreement with CFD simulations, with a mean absolute percentage error (MAPE) of 1.85%. Combining these results, we demonstrate a two-orders-of-magnitude speedup (with comparable accuracy) for the design optimization process when the surrogate model is used. To our knowledge, this is the first study applying Bayesian optimization and DNN-based surrogate modeling to the problem of UUV design optimization, and we share our developments as open-source software. © 2023, The Authors. All rights reserved.

关键词： Computational fluid dynamics

Sample-Efficient and Surrogate-Based Design Optimization of Underwater Vehicle Hulls

学校读者我要写书评

暂无评论

arXiv 2023年

Physics simulations like computational fluid dynamics (CFD) are a computational bottleneck in computer-aided design (CAD) optimization processes. To overcome this bottleneck, one requires either an optimization framework that is highly sample-efficient, or a fast data-driven proxy (surrogate model) for long-running simulations. Both approaches have benefits and limitations. Bayesian optimization is often used for sample efficiency, but it solves one specific problem and struggles with transferability;alternatively, surrogate models can offer fast and often more generalizable solutions for CFD problems, but gathering data for and training such models can be computationally demanding. In this work, we leverage recent advances in optimization and artificial intelligence (AI) to explore both of these potential approaches, in the context of designing an optimal unmanned underwater vehicle (UUV) hull. For first approach, we investigate and compare the sample efficiency and convergence behavior of different optimization techniques with a standard CFD solver in the optimization loop. For the second approach, we develop a deep neural network (DNN) based surrogate model to approximate drag forces that would otherwise be computed via the CFD solver. The surrogate model is in turn used in the optimization loop of the hull design. Our study finds that the Bayesian Optimization—Lower Condition Bound (BO-LCB) algorithm is the most sample-efficient optimization framework and has the best convergence behavior of those considered. Subsequently, we show that our DNN-based surrogate model predicts drag force on test data in tight agreement with CFD simulations, with a mean absolute percentage error (MAPE) of 1.85%. Combining these results, we demonstrate a two-orders-of-magnitude speedup (with comparable accuracy) for the design optimization process when the surrogate model is used. To our knowledge, this is the first study applying Bayesian optimization and DNN-based surrogate modelin

关键词： Computational fluid dynamics

SUMMARY ON THE ICASSP 2022 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION GRAND CHALLENGE

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yu, Fan Zhang, Shiliang Guo, Pengcheng Fu, Yihui Du, Zhihao Zheng, Siqi Huang, Weilong Xie, Lei Tan, Zheng-Hua Wang, DeLiang Qian, Yanmin Lee, Kong Aik Yan, Zhijie Ma, Bin Xu, Xin Bu, Hui Speech Lab Alibaba Group China Speech Lab Alibaba Group Singapore AISHELL Foundation China Beijing Shell Shell Technology Co. Ltd. Beijing China Department of Electronic Systems Aalborg University Aalborg Denmark Department of Computer Science and Engineering Center for Cognitive and Brain Sciences The Ohio State University United States SpeechLab Department of Computer Science and Engineering Shanghai Jiao Tong University China Aural and Language Intelligence Department Institute for Infocomm Research A*STAR Singapore

The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic speech recognition (ASR) (track 2). Along with the challenge, we released 120 hours of real-recorded Mandarin meeting speech data with manual annotation, including far-field data collected by 8-channel microphone array as well as near-field data collected by each participants’ headset microphone. We briefly describe the released dataset, track setups, baselines and summarize the challenge results and major techniques used in the submissions. © 2022, CC BY-SA.

关键词： Speech recognition

Generation and search for the shortest path in two-dimensional labyrinths as a model for optimizing routing processes in the packet switching network 4

学校读者我要写书评

暂无评论

Generation and search for the shortest path in two-dimension...

4th International Conference on Future Networks and Distributed systems, ICFNDS 2020

作者： Dagaev, Alexander Borodyansky, Yuriy Pomogalova, Albina Department of Software Engineering and Computer Science The Bonch-Bruevich State University of Telecommunications St. Petersburg Russia Department of Protected Information Systems The Bonch-Bruevich State University of Telecommunications St. Petersburg Russia

ISBN: (纸本)9781450388863

The algorithms for generating and finding the shortest path in two-dimensional labyrinths and their characteristics are considered. The aim of the study is to determine the dependence of the working time of the shortest path search algorithms on the characteristics of mazes. This may allow these algorithms to be used to optimise routing processes in packet switching networks. All of the characteristics of the algorithms under consideration are described in detail. These search algorithms also allow for paralleling, so they can be used when creating games or any special applications. Such generation algorithms have been selected, the resulting mazes of which have different characteristics, thus making it possible to determine the required dependence. The peculiarity of applying the result of this research is that the fastest search algorithm can be selected for the generation algorithm or for specific characteristics of an already generated maze. The search algorithms can be improved to find paths in mazes in N-dimensional spaces. This search extension possibility can be widely used not only for working with mazes, but also with any other structure of a given coordinate system. © 2020 ACM.

关键词： Packet switching

Machine Learning-based Energy-Aware Offloading in Edge-Cloud Vehicular Networks 18

学校读者我要写书评

暂无评论

Machine Learning-based Energy-Aware Offloading in Edge-Cloud...

18th International Conference on Mobile systems and Pervasive Computing, MobiSPC 2021, The 16th International Conference on Future Networks and Communications, FNC 2021 and the 11th International Conference on Sustainable Energy Information Technology, SEIT 2021

作者： Ismail, Leila Materwala, Huned Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates National Water and Energy Center United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates

A vehicular network underpinned by the 3-tier vehicle-edge-cloud infrastructure enables an efficient and safer travel experience. The compute-intensive vehicular applications are often offloaded to the edge and/or cloud servers to enhance the applications' Quality of Services (QoS). The underlying edge-cloud servers consume a high among of energy. Consequently, it becomes crucial to optimizing energy consumption in the offloading process. Current energy-efficient offloading strategies in 2-tier vehicle-edge infrastructure, do not account for cloud computing energy consumption. In this paper, we address this void by proposing a machine learning-based energy-aware offloading algorithm, which optimizes the energy of the edge-cloud computing platform. The offloading strategy is enabled by the Support Vector Machine (SVM) regression model machine learning algorithm used for the edge-cloud power prediction. The experimental results show that the proposed algorithm is a promising approach in energy savings. © 2021 Elsevier B.V.. All rights reserved.

关键词： Energy efficiency

Deep Vision in Analysis and Recognition of Radar Data: Achievements, Advancements and Challenges

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Qi Yang, Zhiyun Ji, Ru Zhang, Yonghong Bilal, Muhammad Liu, Xiaodong Vimal, S. Xu, Xiaolong The Wuxi University 333 Xishan Avenue Wuxi214105 China The School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China The Division of Computer and Electronic Systems Engineering Hankuk University of Foreign Studies Korea Republic of The School of Computing Edinburgh Napier University EdinburghEH10 5DT United Kingdom The Department of Artificial Intelligence & DS Ramco Institute of Technology Tamilnadu India

Radars are widely used to obtain echo information for effective prediction, such as precipitation nowcasting. In this paper, recent relevant scientific investigation and practical efforts using Deep Learning (DL) models for weather radar data analysis and pattern recognition have been reviewed;particularly, in the fields of beam blockage correction, radar echo extrapolation, and precipitation nowcast. Compared to traditional approaches, present DL methods depict better performance and convenience but suffer from stability and generalization. In addition to recent achievements, the latest advancements and existing challenges are also presented and discussed in this paper, trying to lead to reasonable potentials and trends in this highly-concerned *** Codes I.2, I.4, I.5 © 2023, CC BY-NC-SA.

关键词： Extrapolation

HURWITZ SERIES RINGS SATISFYING A ZERO DIVISOR PROPERTY

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Mosallaei, Behrooz Afrouzmehr, Moein Abshari, Danial Farivar, Sepideh The Klipsch School of Electrical and Computer Engineering New Mexico State University Las CrucesNM88003 United States Department of Economics Applied Statistics and International Business New Mexico State University Las CrucesNM88003 United States Software and Information Systems Department University of North Carolina at Charlotte CharlotteNC28223 United States Department of Computer Science University of Nevada Las Vegas 4505 S. Maryland Parkway Las VegasNV89154-4030 United States

In this paper, we study zero divisors in the Hurwitz series rings and the Hurwitz polynomial rings over general non-commutative rings. We first construct Armendariz rings that are not Armendariz of the Hurwitz series type and find various properties of (the Hurwitz series) Armendariz rings. We show that for a semiprime Armendariz of the Hurwitz series type (so reduced) ring R with a.c.c. on annihilator ideals, HR (the Hurwitz series ring with coefficients over R) has finitely many minimal prime ideals, say B1, . . ., Bm such that B1 · . . . · Bm = 0 and Bi = HAi for some minimal prime ideal Ai of R for all i, where A1, . . ., Am are all minimal prime ideals of R. Additionally, we construct various types of (the Hurwitz series) Armendariz rings and demonstrate that the polynomial ring extension preserves the Armendarizness of the Hurwitz series as the Armendarizness. © 2023, CC0.

关键词： Algebra