检索结果-内蒙古大学图书馆

COMPUTATIONAL FLUID-STRUCTURE INTERACTION FRAMEWORK FOR SIMULATING CHARACTERISTIC DEFORMATIONS IN INSECT FLAPPING WINGS 9

COMPUTATIONAL FLUID-STRUCTURE INTERACTION FRAMEWORK FOR SIMU...

引用

9th International Conference on Computational Methods for Coupled Problems in Science and Engineering, COUPLED PROBLEMS 2021

作者： Onishi, Minato Ishihara, Daisuke Department of Computer Science and System Engineering Kyushu Institute of Technology 680-4 Kawazu Iizuka Fukuoka820-8502 Japan Department of Intelligent and Control Systems Kyushu Institute of Technology Kyushu Institute of Technology 680-4 Kawazu Iizuka Fukuoka820-8502 Japan

In this study, a computational fluid-structure interaction (FSI) framework for characteristic deformations in insect's wings is proposed. The proposed framework consists of a pixel wing model using a structured shell finite element mesh, a projection method for the monolithic FSI monolithic equations using an algebraic splitting, and the FSI dynamic similarity law to measure dynamic similarity between model's and actual insect's flights. It is shown that the proposed framework can directly simulate passive feathering and cambering in insect's wings caused by the FSI, whose magnitudes are very close to those of actual insects. © 2021 9th International Conference on Computational Methods for Coupled Problems in Science and Engineering, COUPLED PROBLEMS 2021. All rights reserved.

关键词： Fluid structure interaction

来源：评论

学校读者我要写书评

暂无评论

Stackelberg games with dynamic spanning trees

Stackelberg games with dynamic spanning trees

引用

第35届中国控制与决策会议

作者： Wantong Cheng Min Cheng Qirui Sun Xuanping Fan Yin Li Faculty of Applied Mathematics and Control Processes St.Petersburg State University Department of Mathematics and Computer Science Yan'an University School of Mathematics Harbin Institute of Technology

This article considers a Stackelberg game with dynamic spanning *** leader will identify the edges between some of the followers,which will be shown in *** the followers will play a two-stage spanning tree game with "shock",which means that after the first stage,a specific follower will leave the game with a certain probability,which depends on the behavior of all the followers in the first *** equilibrium of the Stackelberg game with dynamic spanning tree is defined,and correlative conclusions are given.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evolving temporal convolutional neural networks for modeling turntable servo systems

引用

Applied Soft Computing 2025年 172卷

作者： Xie, Cheng Xue, Bing Zhang, Mengjie Chen, Songlin Liu, Yang Control and Simulation Center School of Astronautics Harbin Institute of Technology Heilongjiang Harbin150001 China Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand Shenyang Institute of Automation Chinese Academy of Sciences Liaoning Shenyang110169 China

Turntable servo systems are important experimental equipment used for semi-physical simulation and testing of aircraft, which have very strict requirements for tracking performance. To achieve high-precision servo performance, some advanced model-based control methods have been used recently, but the control performance is greatly influenced by the accuracy of the model. Therefore, this paper proposes evolving temporal convolutional networks (TCNs) for accurately modeling turntable servo systems. Considering the advantages of TCNs in capturing local dependencies in sequence data and parallel computing, a TCN is adopted to compensate the unmodeled dynamics to significantly improve the accuracy of the existing dynamics model. Then, an evolutionary algorithm (EA) based architecture optimization algorithm for the above TCN model is proposed, and the network performance is continuously improved by simulating the population evolution in nature. Finally, the weight inheritance method is utilized to evaluate the performance of individuals during the evolution process to effectively improve the execution efficiency of the whole algorithm. In addition, the subnets inherited from the supernet meet the real-time requirements of the actual tasks by setting real-time constraints on the supernet. The experimental results demonstrate the superiority of the proposed model against the peer competitors in terms of the prediction performance. In addition, the proposed optimization algorithm also shows higher execution efficiency as verified by ablation experiments. © 2025 Elsevier B.V.

关键词： Evolutionary algorithms (EAs) System identification and modeling Temporal convolutional networks (TCNs) Turntable servo systems

来源：评论

学校读者我要写书评

暂无评论

Contemporary Approach of Additive Manufacturing for Sustainable Products in the Era of Circular Economy 8th

Contemporary Approach of Additive Manufacturing for Sustaina...

引用

8th EAI International Conference on Management of Manufacturing Systems, MMS 2023

作者： Knapčíková, Lucia Behúnová, Annamária Tauberová, Rebeka Kaščak, Jakub Husár, Jozef The Technical University of Košice Faculty of Manufacturing Technologies with a seat in Prešov Department of Industrial Engineering and Informatics Prešov Slovakia Technical University of Kosice Faculty of Mining Ecology Process Control and Geotechnologies Institute of Earth Resources Kosice Slovakia The Technical University of Košice Faculty of Manufacturing Technologies with a seat in Prešov Department of Computer Aided Manufacturing Technology Prešov Slovakia

ISBN: (纸本)9783031531606

Considering the need for mass customization in Industry 4.0, it is necessary to develop non-traditional production methods. Therefore, additive manufacturing can become a key technology for the production of customized products thanks to its ability to create irregular objects or shapes. In addition to enabling new design possibilities, the additive manufacturing method holds promise for increasing social, economic, and environmental sustainability. It also has the potential to reduce energy consumption and lower polymer material consumption. Additive manufacturing contrasts with conventional processes, as it consists in applying materials layer by layer. Conventional manufacturing operations produce polymer waste that is difficult to reintroduce into manufacturing processes. The aim of the contribution is the possibility of using additive manufacturing in the design and processing of new effective use of the product with regard to the environmental aspect. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Machine Translation via Dependency Subtree Swapping

arXiv

引用

arXiv 2023年

作者： Nagy, Attila Lakatos, Dorina Petra Barta, Botond Nanys, Patrick Ács, Judit Department of Automation and Applied Informatics Budapest University of Technology and Economics Hungary Institute for Computer Science and Control Eötvös Loránd Research Network Hungary

We present a generic framework for data augmentation via dependency subtree swapping that is applicable to machine translation. We extract corresponding subtrees from the dependency parse trees of the source and target sentences and swap these across bisentences to create augmented samples. We perform thorough filtering based on graph-based similarities of the dependency trees and additional heuristics to ensure that extracted subtrees correspond to the same meaning. We conduct resource-constrained experiments on 4 language pairs in both directions using the IWSLT text translation datasets and the Hunglish2 corpus. The results demonstrate consistent improvements in BLEU score over our baseline models in 3 out of 4 language pairs. Our code is available on GitHub1 © 2023, CC BY.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm for Block Relocation in Automated Warehouse 5

Genetic Algorithm for Block Relocation in Automated Warehous...

引用

5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Wang, Gang Lian, Mingchang Ding, Wei Chen, Songhang Chen, Hao Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou362200 China College of Computer and Cyber Security Fujian Normal University Fujian Fuzhou350001 China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fujian Fuzhou350108 China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou362200 China

ISBN: (纸本)9781643684840

This paper is based on the research background of block relocation in the automated warehouse and proposes a solution utilizing AGV to relocate goods within the warehouse. Building upon the automated warehouse layout and block relocation process, we formulate a mathematical model to minimize the the number of AGV moving goods and the total travel distance of the AGV. To solve the model, we develop an enhanced genetic algorithm, which zones the block relocation process into multiple stages. Each stage integrates conventional heuristic algorithms to enhance the efficiency of the solution process. The improved genetic algorithm can effectively solve the problem, significantly enhancing the automation level of the warehouse. © 2024 The Authors.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Integral Reinforcement Learning-Based Angular Acceleration Autopilot for High Dynamic Flight Vehicles

SSRN

引用

SSRN 2023年

作者： Liu, Yingxin Hu, Yuhui Shen, Kai Qiu, Jiatai Neusypin, Konstantin A. School of Automation Beijing Institute of Technology Beijing100081 China Faculty of Computer Science and Control Systems Bauman Moscow State Technical University Moscow105005 Russia

In the synthesis of acceleration autopilot for high dynamic flight vehicle (HDFV), the full perception of system states, such as the angle of attack, is usually unavailable. Autopilots with feedback of angular acceleration (AFAA) have become more perspective for HDFV with stringent requirements on response speed and high maneuverability, compared with autopilot with feedback of angular rate (AFAR). Although classical optimal control methodology has validated its great vitality during the synthesis of autopilots both in theory and practice while this approach requires complete knowledge of the system dynamics. Reinforcement learning (RL) method has now proved to be an effective technique for adaptive optimal control of partially unknown nonlinear systems. In this paper, a novel data-driven integral RL algorithm with feedback of angular acceleration was proposed for the synthesis of HDFV’s autopilot. And numerical simulation was carried out to validate the effectiveness of proposed online integral RL-based angular acceleration autopilot for HDFVs. Besides, the tracking performance under different wave commands, the robustness against parameter uncertainties and the noise attenuation capacity between classical optimal tracking approach and proposed integral RL method were analyzed for AFAR and AFAA, respectively. Simulation results showed, angular acceleration autopilot with proposed integral RL algorithm possessed better tracking performance against various disturbances. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Speech Recognition of Vedic Sanskrit using Deep Learning Algorithm

Speech Recognition of Vedic Sanskrit using Deep Learning Alg...

引用

International Conference on Information Systems and computer Networks (ISCON)

作者： Mrinal Pandey Rashmikiran Pandey Alexey Nazarov Department of Radio Engineering and Cybernetics Moscow Institute of Physics and Technology Moscow Russia Federal Research Center Computer Science and Control Russian Academy of Sciences Moscow Russia

In this study, we examined the use of computational techniques for accurately processing acoustic signals of human speech using digital media. Specifically, we focused on the Sanskrit language and applied a language modeling approach to improve recognition by machines. Our implementation of this approach for Sanskrit speech represents a novel approach in the field and has the potential to extract valuable information through automated processing. The ability to accurately process speech is crucial for effective human communication, and our research contributes to the development of more efficient and effective methods for achieving this goal..

关键词： Deep learning Computational modeling Natural languages Speech recognition Media computer networks Acoustics

来源：评论

学校读者我要写书评

暂无评论

Diagnosing and Repairing Feature Representations Under Distribution Shifts

Diagnosing and Repairing Feature Representations Under Distr...

引用

IEEE Conference on Decision and control

作者： Inês Lourenço Andreea Bobu Cristian R. Rojas Bo Wahlberg Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Department of Electrical Engineering and Computer Sciences University of California Berkeley Berkeley CA USA

Robots have been increasingly better at doing tasks for humans by learning from their feedback, but still often suffer from model misalignment due to missing or incorrectly learned features. When the features the robot needs to learn to perform its task are missing or do not generalize well to new settings, the robot will not be able to learn the task the human wants and, even worse, may learn a completely different and undesired behavior. Prior work shows how the robot can detect when its representation is missing some feature and can, thus, ask the human to be taught about the new feature; however, these works do not differentiate between features that are completely missing and those that exist but do not generalize to new environments. In the latter case, the robot would detect misalignment and simply learn a new feature, leading to an arbitrarily growing feature representation that can, in turn, lead to spurious correlations and incorrect learning down the line. In this work, we propose separating the two sources of misalignment: we propose a framework for determining whether a feature the robot needs is incorrectly learned and does not generalize to new environment setups vs. is entirely missing from the robot's representation. Once we diagnose the source of error, we show how the human can initiate the realignment process for the model: if the feature is missing, we follow prior work for learning new features; however, if the feature exists but does not generalize, we use data augmentation to expand its training and, thus, complete the repair process. We demonstrate the proposed approach in experiments with a simulated 7DoF robot manipulator and physical human corrections.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Template Learning for Top-Level computer Management Using Bayesian Optimization 3

Dynamic Template Learning for Top-Level Computer Management ...

引用

3rd International Conference on Advancement in Electronics and Communication Engineering, AECE 2023

作者： Zebari, Rizgar R. Majeed, Maryam Ghassan Mohammed, Mohammed Q. Abdulhussain, Zahraa N. Kosimov, Latifjon Alchilibi, Haider Knowledge University Computer Science Dept. Erbil Iraq Al-Kunooze University College Computer Engineer Department Basra Iraq Al-Esraa University College Forensic Sciences Department Baghdad Iraq National University of Science and Technology Dhi Qar Iraq Fergana Polytechnic Institute Department of Education Quality Control Fergana Uzbekistan Al-Farahidi University Medical Laboratory Techniques Department Baghdad10022 Iraq

ISBN: (纸本)9798350330724

Computing system administration is a difficult undertaking, particularly in complicated and shifting situations. Classical static methods often fall short of efficiently adjusting for shifting circumstances. In this study, we offer Dynamic Template Learning (DTL), a new method for automating top-level administration of computers that makes use of Bayesian optimization. The aim is to employ continuous performance evaluation and user-defined optimizations targets to constantly alter the system's settings and utilization of resources. The DTL architecture includes a feedback process that continually gathers performance information, evaluates the condition of the entire system, and draws lessons from the past in order to make wise choices. To effectively simulate system behavior while investigating the setting space, Bayesian optimizations is used. In order to find the best layouts, DTL uses probability modelling and acquisition procedures to dynamically examine choices. We experimented on a modelled machine with various strain conditions to assess the efficacy of DTL. The findings show that DTL performs better than conventional static techniques in aspects of system sales, usage of resources, and environmental adaption. Finding near-optimal solutions and quickly scanning the set-up field are both largely dependent on the Bayesian optimizations element. Additionally, we illustrate possible uses in real-world computing settings and talk about the advantages and disadvantages of the DTL technique. DTL's flexibility and adaptability makes it appropriate for a variety of infrastructure, including dispersed systems, data centers, and cloud computing systems. Organizations may increase system effectiveness, decrease staff involvement, and improve success overall by automated managerial processes. © 2023 IEEE.

关键词： Human resource management

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：