检索结果-内蒙古大学图书馆

2024 International Conference on electrical Machines, ICEM 2024

作者： He, Tianran Leng, Xiaokun Sun, Yangyu Wu, Yucong School of Electronics and Information Engineering Tongji University Shanghai China School of Computer Science and Technology Harbin Institute of Technology Harbin China University of Sheffield Department of Electrical and Electronic Engineering Sheffield United Kingdom Southern University of Science and Technology Department of Mechanical and Energy Engineering Shenzhen China

ISBN: (纸本)9798350370607

Recently, bipedal robots that utilize electric rotary actuators have attracted much attention since they can walk on any kind of path or terrain and can jump or step over obstacles. In addition, bipedal robots are designed to pick up and put down various types of heavy objects for industrial applications. To achieve the specified functions, the electric rotary actuators, as the core driving unit of bipedal robots, need to possess characteristics of high power density and large output torque. This paper presents the design of an electric rotary actuator based on an outer rotor permanent magnet motor for bipedal robots. The proposed electric rotary actuator includes a 36-slot/42-pole permanent magnet motor, a 10:1 planetary gearbox, and an integrated gear shaft. The electromagnetic performances and overload capability of the proposed 36-slot/42-pole outer rotor permanent magnet motor are analyzed by the finite element method. Finally, a prototype of the proposed electric rotary actuator is tested by a customed high-torque testing bench. The experimental results are in good agreement with the finite element analysis results. © 2024 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Tangentially Aligned Integrated Gradients for User-Friendly Explanations 32

Tangentially Aligned Integrated Gradients for User-Friendly ...

引用

32nd Irish Conference on Artificial Intelligence and Cognitive science, AICS 2024

作者： Simpson, Lachlan Costanza, Federico Millar, Kyle Cheng, Adriel Lim, Cheng-Chew Chew, Hong Gunn School of Electrical and Mechanical Engineering The University of Adelaide Australia School of Computer and Mathematical Sciences The University of Adelaide Australia Information Sciences Division Defence Science and Technology Group Australia

Integrated gradients is prevalent within machine learning to address the black-box problem of neural networks. The explanations given by integrated gradients depend on a choice of base-point. The choice of base-point is not a priori obvious and can lead to drastically different explanations. There is a longstanding hypothesis that data lies on a low dimensional Riemannian manifold. The quality of explanations on a manifold can be measured by the extent to which an explanation for a point lies in its tangent space. In this work, we propose that the base-point should be chosen such that it maximises the tangential alignment of the explanation. We formalise the notion of tangential alignment and provide theoretical conditions under which a base-point choice will provide explanations lying in the tangent space. We demonstrate how to approximate the optimal base-point on several well-known image classification datasets. Furthermore, we compare the optimal base-point choice with common base-points and three gradient explainability models. © 2024 Copyright for this paper by its authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

ELASTIC CONSTANTS INVERSION OF ZIRCONIUM TUBE BASED ON THE LONGITUDINAL MODE OF GUIDED WAVE 18

ELASTIC CONSTANTS INVERSION OF ZIRCONIUM TUBE BASED ON THE L...

引用

18th Symposium on Piezoelectricity, Acoustic Waves, and Device Applications, SPAWDA 2024

作者： Ji, Haoshuai Liu, Hongye Sun, Maoxun Chen, Xiaorong Shen, Liang Qiu, Chongpeng Tian, Zhenhua School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Department of Mechanical Engineering Virginia Polytechnic Institute State University 1145 Perry Street BlacksburgVA24061 United States

ISBN: (纸本)9798331523732

Estimating elastic constants in materials is markedly important in engineering and technology. Ultrasonic guided wave non-destructive testing provides an effective means for accurately assessing material properties. This paper presents a method for inverting the elastic constants of hollow pipes using the longitudinal mode of ultrasonic guided waves combined with a genetic algorithm (GA). The Legendre orthogonal polynomial expansion (LOPE) method serves as the forward model for analyzing the dispersion curves of axisymmetric guided wave modes, while the GA performs the inversion. A carefully designed finite element (FE) model generates pseudo-experimental data, which is transformed into the frequency-wave number domain for input into the GA. The comparison between simulation results and theoretical analysis confirms the validity of the FE model and the accuracy of the detected modes. The results demonstrate that the proposed method effectively inverts the elastic constants of isotropic hollow cylindrical structures, with an inversion error of less than 2% based on pseudo-experimental data. © 2024 IEEE.

关键词： Nondestructive examination

来源：评论

学校读者我要写书评

暂无评论

Research on Optimization Methods for Industrial Model Retrieval 5

Research on Optimization Methods for Industrial Model Retrie...

引用

5th International Conference on Natural Language Processing, ICNLP 2023

作者： Wang, Peng Hu, Chunhui Xi'an University of Posts and Telecommunications School of Computer Science Xi'an China Xi'an University of Electronic Science and Technology School of Electrical and Mechanical Engineering Xi'an China

ISBN: (纸本)9798350302219

In the retrieval process of industrial models, the traditional database retrieval can no longer meet their needs in terms of efficiency and precision because of their multi-source heterogeneous, complex types and large information scale. This paper optimizes the Elasticsearch search engine in three aspects: the underlying index of the search engine, keyword search and sorting algorithm;and verifies the feasibility of the method through experiments. © 2023 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Deployment of Large Language Models to Control Mobile Robots at the Edge

arXiv

引用

arXiv 2024年

作者： Sikorski, Pascal Schrader, Leendert Yu, Kaleb Billadeau, Lucy Meenakshi, Jinka Mutharasan, Naveena Esposito, Flavio AliAkbarpour, Hadi Babaiasl, Madi Computer Science Department Aerospace & Mechanical Engineering Department Science Department Robotics Aerospace & Mechanical Engineering Department Saint Louis University Saint Louis United States

This paper investigates the possibility of intuitive human-robot interaction through the application of Natural Language Processing (NLP) and Large Language Models (LLMs) in mobile robotics. This work aims to explore the feasibility of using these technologies for edge-based deployment, where traditional cloud dependencies are eliminated. The study specifically contrasts the performance of GPT-4-Turbo, which requires cloud connectivity, with an offline-capable, quantized version of LLaMA 2 (LLaMA 2-7B.Q5 K M). These results show that GPT-4-Turbo delivers superior performance in interpreting and executing complex commands accurately, whereas LLaMA 2 exhibits significant limitations in consistency and reliability of command execution. Communication between the control computer and the mobile robot is established via a Raspberry Pi Pico W, which wirelessly receives commands from the computer without internet dependency and transmits them through a wired connection to the robot’s Arduino controller. This study highlights the potential and challenges of implementing LLMs and NLP at the edge, providing groundwork for future research into fully autonomous and network-independent robotic systems. For video demonstrations and source code, please refer to: https://***/MobileRobotGPT4LLaMA2024. © 2024, CC BY.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Algebraic Adversarial Attacks on Integrated Gradients 23

Algebraic Adversarial Attacks on Integrated Gradients

引用

23rd International Conference on Machine Learning and Cybernetics, ICMLC 2024

作者： Simpson, Lachlan Costanza, Federico Millar, Kyle Cheng, Adriel Lim, Cheng-Chew Chew, Hong Gunn School of Computer and Mathematical Sciences The University of Adelaide Australia School of Electrical and Mechanical Engineering The University of Adelaide Australia Defence Science & Technology Group Information Sciences Division Australia

ISBN: (纸本)9798331528041

Adversarial attacks on explainability models have drastic consequences when explanations are used to understand the reasoning of neural networks in safety critical systems. Path methods are one such class of attribution methods susceptible to adversarial attacks. Adversarial learning is typically phrased as a constrained optimisation problem. In this work, we propose algebraic adversarial examples and study the conditions under which one can generate adversarial examples for integrated gradients. Algebraic adversarial examples provide a mathematically tractable approach to adversarial examples. © 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

Efficient Steady-State Tissue Simulation for Surgical Robotics: A First-Order Position-Based Method

Efficient Steady-State Tissue Simulation for Surgical Roboti...

引用

International Symposium on Medical Robotics (ISMR)

作者： Samuel Tobin Yufei Wu Fei Liu Caleb Rucker Department of Mechanical Aerospace & Biomedical Engineering University of Tennessee Knoxville TN USA Department of Electrical Engineering & Computer Science University of Tennessee Knoxville TN USA

ISBN: (数字)9798331599003

ISBN: (纸本)9798331599010

Soft tissue simulation can play an essential role in the automation of robotic surgery by providing contextual information during surgery and generating datasets for training. Any time tissue deformations are simulated, computational speed, accuracy, and stability are key concerns. State-of-theart tissue simulation resolves inertial dynamics solutions using position-based computational methods. However, existing methods fail to efficiently resolve steady-state solutions at surgical size scales because of transient inertial dynamics and the small time step required for stability at such size scales. We propose a position-based tissue simulation framework which is based on large-deformation Neo-Hookean elasticity and enables fast resolution to steady-state for efficient simulation. Our method replaces the inertial terms in the model with a virtual viscous damping term. This enables realistic tissue motion while eliminating the transient vibrations that require more computation. It also enables smooth and stable dynamic transitions between disparate static states. We detail the selection of parameters and step sizes for efficient steady-state simulation. We further compare our approach to a state-of-the-art position-based method and show significant improvements in stability and realtime performance at surgical size scales.

关键词： Vibrations Training Medical robotics Deformation Dynamics Surgery Elasticity Stability analysis Steady-state Transient analysis

来源：评论

学校读者我要写书评

暂无评论

WAVEFIELD CHARACTERIZATION OF LAMB WAVE PROPAGATION IN COMPOSITE PLATES BASED ON GUIDED WAVE OMNIDIRECTIONAL WAVENUMBER SIMULATION 18

WAVEFIELD CHARACTERIZATION OF LAMB WAVE PROPAGATION IN COMPO...

引用

18th Symposium on Piezoelectricity, Acoustic Waves, and Device Applications, SPAWDA 2024

作者： Wang, Lei Liu, Hongye Sun, Maoxun Chen, Xiaorong Shen, Liang Qiu, Chongpeng Tian, Zhenhua School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Department of Mechanical Engineering Virginia Polytechnic Institute State University 1145 Perry Street BlacksburgVA24061 United States

ISBN: (纸本)9798331523732

With the growing application of composite materials in sectors such as aerospace, automotive, and wind energy, accurately assessing their mechanical properties is critical for effective non-destructive testing (NDT) and structural health monitoring (SHM). In this paper, a three-dimensional finite element model was developed to generate the fundamental A0 Lamb wave mode within an 8-layer orthotropic laminate, addressing the complexities associated with the anisotropic behavior of composites. Utilizing the Legendre Orthogonal Polynomial Expansion (LOPE) method, we characterized the wave number profile, revealing significant directional dependence in wave propagation across multilayer laminates. The results demonstrated strong agreement between the analytical predictions from the LOPE method and the finite element simulations, confirming the robustness of our modeling approach. Additionally, we introduced an innovative omnidirectional wavefield representation method, effectively mitigating the influence of phase and group velocity steering angles. These findings enhance our understanding of guided wave dynamics in composite materials, offering valuable insights for the development of more effective detection strategies and assessments of structural integrity in complex composite systems. © 2024 IEEE.

关键词： Gravity waves

来源：评论

学校读者我要写书评

暂无评论

Fatigue crack propagation across grain boundary of Al-Cu-Mg bicrystal based on crystal plasticity XFEM and cohesive zone model

引用

Journal of Materials science & Technology 2022年第31期126卷 275-287页

作者： Qi Zhao Magd Abdel Wahab Yong Ling Zhiyi Liu School of Materials Science and Engineering Hubei University of Automotive TechnologyShiyan 442002China Faculty of Mechanical-Electrical and Computer Engineering School of Engineering and TechnologyVan Lang UniversityHo Chi Minh CityVietnam Soete Laboratory Faculty of Engineering and ArchitectureGhent UniversityTechnologiepark Zwijnaarde 903B-9052 ZwijnaardeBelgium School of Materials Science and Engineering Central South UniversityChangsha 410083China

In this paper,a methodology integrating crystal plasticity(CP),the eXtended finite element method(XFEM)and the cohesive zone model(CZM)is developed for an Al-Cu-Mg alloy to predict fatigue crack propagation(FCP)across grain boundary(GB)of Al-Cu-Mg alloy during stageІІ.One GB model is incor-porated into FCP constitutive law to describe grain interaction at GB.A bicrystal containing GB is built up to simulate FCP behavior through L participated *** features including GB characteristic,cumulative plastic strain(CPS)distribution and crystal slipping evidence can be *** numer-ical results are compared with published experimental data to check the accuracy of *** work demonstrates that the combination of CP containing GB constitutive laws,XFEM and CZM is a promising methodology in predicting twist angle-controlled crack deflection through GBs.

关键词： Grain boundary Twist angle Crystal plasticity Extended finite element method Fatigue crack propagation Cumulative plastic strain

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Personalization of E-Therapy Interventions for Anxiety, Stress, and Depression 18

AI-Driven Personalization of E-Therapy Interventions for Anx...

引用

18th International Conference on Open Source Systems and Technologies, ICOSST 2024

作者： Ramzan, Hafiz Arslan Abdulah, Fatima Ahmad, Muddaber Ramzan, Sadia Ashraf, Munazza School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad Pakistan School of Mechanical and Manufacturing Engineering National University of Sciences and Technology Islamabad Pakistan National University of Computer and Emerging Sciences Department of Computer Science Chiniot Faisalabad Pakistan GIFT University Department of Humanities and Social Sciences Gujranwala Pakistan

ISBN: (纸本)9798331508692

This study explores the use of artificial intelligence (AI) to personalize e-therapy interventions for anxiety, stress, and depression. Leveraging machine learning models, including K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Decision Trees, we analyze a dataset of depression, anxiety, and stress scales responses to develop predictive models that tailor therapeutic interventions. The accuracy and efficacy of proposed models vary, indicating that AI has the potential to improve the level of personalization of mental health therapies. The results indicate that AI-driven techniques can significantly improve the effectiveness and efficiency of e-therapy platforms. © 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

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：