检索结果-内蒙古大学图书馆

2024 American Control Conference, ACC 2024

作者： Keivan, Darioush Seiler, Peter Dullerud, Geir Bin, H. University of Illinois at Urbana-Champaign Department of Mechanical Science & Engineering United States University of Michigan Department of Electrical Engineering and Computer Science United States University of Illinois at Urbana-Champaign Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798350382655

Policy optimization has gained renewed attention from the control community, serving as a pivotal link between control theory and reinforcement learning. In the past few years, the global convergence theory of direct policy search on state-feedback linear control benchmarks has been developed. However, it remains difficult to establish the global convergence of policy optimization on the linear quadratic Gaussian (LQG) problem, marked by the presence of suboptimal stationary points and the lack of cost coerciveness. In this paper, we revisit the policy optimization intricacies of LQG via a case study on first-order single-input single-output (SISO) systems. For this case study, while the issue related to suboptimal stationary points can be easily fixed via parameterizing the policy class more carefully, the non-coerciveness of the LQG cost function still poses a substantial obstacle to a straightforward global convergence proof for the policy gradient method. Our contribution, within the scope of this case study, introduces an approach to construct a positive invariant set for the policy gradient flow, addressing the non-coerciveness issue in the global convergence proof. Based on our analysis, the policy gradient flow can be guaranteed to converge to the globally optimal full-order dynamic controller in this particular scenario. In summary, although centered on a specific case study, our work broadens the comprehension of how the absence of coerciveness impacts LQG policy optimization, highlighting inherent complexities. © 2024 AACC.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

PREDICTIVE MACHINE LEARNING MODELS FOR LIDAR SENSOR RELIABILITY IN AUTONOMOUS VEHICLES

PREDICTIVE MACHINE LEARNING MODELS FOR LIDAR SENSOR RELIABIL...

引用

ASME 2024 International Technical Conference and Exhibition on Packaging and Integration of Electronic and Photonic Microsystems, InterPACK 2024

作者： Farahani, Saba A. Lee, Jae Yun Kim, Hunjae Won, Yoonjin Department of Electrical Engineering and Computer Science University of California Irvine United States Department of Mechanical and Aerospace Engineering University of California Irvine United States Hyundai Motor Company Seoul Korea Republic of

ISBN: (纸本)9780791888469

The emergence of autonomous vehicles marks a transformative moment in the transportation sector, significantly propelled by the integration of Light Detection and Ranging (LiDAR) technology. LiDAR revolutionizes how vehicles perceive their environment, emitting laser beams to measure distances to objects and creating highly accurate three-dimensional maps. This innovation is pivotal for enhancing the operational efficiency and safety of autonomous vehicles by providing instantaneous and detailed environmental mappings. However, the efficacy of LiDAR sensors is compromised by environmental factors such as dust, dirt, snow, and rain, which can severely affect their accuracy and, consequently, the safety of the vehicles they guide. Despite the importance of this issue, the research field has shown a notable lack of investigation into predicting LiDAR sensor contamination and its reliability. This gap underscores a critical need for dedicated research efforts to ensure the reliability and safety of autonomous driving technologies, making it a pressing challenge for researchers and developers alike. Therefore, it is imperative to develop a novel way to detect LiDAR sensors'reliability like contamination level. In response to the urgent need to address LiDAR sensor contamination, our team have initiated a comprehensive data collection journey, spanning from California's diverse climates to Michigan's variable weather conditions. This dataset contains multi-level features such as contamination levels on multiple sensors, environmental factors, and sensor images across varying weather conditions and geographical locales. The dataset is a groundbreaking contribution to the field, playing a vital role in developing our machine learning models and offering novel insights that could dramatically advance research and practical applications. In this work, our framework employs machine learning methods across two distinct but complementary strategies: sensor data analysis and imag

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Human autonomy teaming-based safety-aware navigation through bio-inspired and graph-based algorithms

引用

Biomimetic Intelligence & Robotics 2024年第4期4卷 76-91页

作者： Timothy Sellers Tingjun Lei Chaomin Luo Zhuming Bi Gene Eu Jan Department of Electrical and Computer Engineering Mississippi State UniversityStarkville 39762USA Department of Civil and Mechanical Engineering Purdue University Fort WayneFort Wayne 46805USA Department of Computer Science Asia UniversityTaichung 413305TaiwanChina

In the field of autonomous robots,achieving complete precision is challenging,underscoring the need for human intervention,particularly in ensuring *** Autonomy Teaming(HAT)is crucial for promoting safe and efficient human-robot collaboration in dynamic indoor *** paper introduces a framework designed to address these precision gaps,enhancing safety and robotic interactions within such *** to our approach is a hybrid graph system that integrates the Generalized Voronoi Diagram(GVD)with spatio-temporal graphs,effectively combining human feedback,environmental factors,and key *** integral component of this system is the improved Node Selection Algorithm(iNSA),which utilizes the revised Grey Wolf Optimization(rGWO)for better adaptability and ***,an obstacle tracking model is employed to provide predictive data,enhancing the efficiency of the *** insights play a critical role,from supplying initial environmental data and determining key waypoints to intervening during unexpected challenges or dynamic environmental *** simulation and comparison tests confirm the reliability and effectiveness of our proposed model,highlighting its unique advantages in the domain of *** comprehensive approach ensures that the system remains robust and responsive to the complexities of real-world applications.

关键词： Human autonomy teaming(HAT) Robot path planning Generalized Voronoi diagram(GVD) Spatio-temporal graphs Bio-inspired algorithms

来源：评论

学校读者我要写书评

暂无评论

Impact of Environmental Conditions on the Remaining Useful Lifetime of SiC MOSFET

Impact of Environmental Conditions on the Remaining Useful L...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Hasan, Md Zakir Amin, Ashik Moniruzzaman, Md Choi, Seungdeog Singh, Prashant Liu, Chun-Hung Mississippi State University Department of Electrical and Computer Engineering Starkville United States University of Tennessee Department of Mechanical Aerospace & Biomedical Engineering Knoxville United States

ISBN: (纸本)9798350376067

Silicon carbide (SiC) power MOSFETs are widely applied to critical infrastructure in modern energy systems. Thus, accurately predicting its remaining useful lifetime (RUL) in real-world applications has become crucial. State-of-the-art explored its RUL through a power cycling test mostly considering constant environmental conditions (e.g., fixed temperature and humidity), which has resulted in considerable RUL prediction errors in real-world applications. This study directly integrates environmental factors into the RUL modeling to address this issue. Specifically, the junction temperature (Tj), on-state voltage (Vds,on), on-state resistance (Rds,on), and case temperature (TC) have been explored in various environmental conditions to understand their tight correlations with the RUL in the real world. Time series statistics models Autoregressive (AR) and Autoregressive Integrated Moving Average (ARIMA) have been used to predict SiC MOSFET RUL to gain new insights systematically. © 2024 IEEE.

关键词： Power MOSFET

来源：评论

学校读者我要写书评

暂无评论

Advancing sustainable casting through cryogenic gradient forming of frozen sand molds:Design,error control,and experimental validation

引用

Journal of Materials science & Technology 2024年第36期203卷 211-226页

作者： Jianpei Shi Zhongde Shan Haoqin Yang Shijie Dong Qinjiang Liu College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and AstronauticsNanjing 210016China College of Material Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 210016China Department of Mechanical Engineering Tsinghua UniversityBeijing 100084China

Owing to its exceptional casting performance,substantial utilization of recycled sand,and environmen-tally sustainable characteristics,frozen sand mold casting technology has found extensive application across diverse sectors,including aerospace,power machinery,and the automotive *** focus of the present study was on the development of frozen sand mold formulations tailored for efficient machin-ing,guided by the performance and cutting fracture mechanism of frozen sand molds.A regional tem-perature control device was developed for the purpose of conducting cryogenic cutting experiments on frozen sand molds with varying geometrical characteristics and molding *** impact of milling process parameters on the dimension accuracy of both sand molds and castings,as well as castings’surface roughness,were systematically investigated by a whole-process error flow control *** findings indicate that precise and efficient processing of complicated sand molds was achievable by using sand particles with sizes ranging from 106 to 212μm,and water content between 4 and 5 wt.%,freezing temperature below-25℃,and cutting temperature within the range of-5 to 0℃.Through the frozen-casting of representative components,it was validated that the machining error of the frozen sand mold was within±0.25 ***,the dimensional accuracy of the flywheel shell casting conformed to the CT8 *** study provides theoretical guidance for the selection of frozen-casting sand formulations and close-loop control of process size chains for complex metal parts,as well as an overall solution for the realization of sustainable development of green casting.

关键词： Frozen sand mold Cryogenic machining Dimensional accuracy Surface roughness Green casting

来源：评论

学校读者我要写书评

暂无评论

Optimized Design of Bio-Inspired Wind Turbine Blades

引用

Fluid Dynamics & Materials Processing 2024年第7期20卷 1647-1664页

作者： Yuanjun Dai Dong Wang Xiongfei Liu Weimin Wu School of Mechanical Engineering Shanghai DianJi UniversityShanghai201306China School of Information Engineering Yinchuan University of Science and TechnologyYinchuan750000China School of Mechanical and Power Engineering Chongqing University of Science and TechnologyChongqing401331China School of Aeronautical Mechanical and Electrical Engineering Chongqing Aerospace PolytechnicChongqing400021China

To enhance the aerodynamic performance of wind turbine blades,this study proposes the adoption of a bionic airfoil inspired by the aerodynamic shape of an *** on the blade element theory,a non-uniform extraction method of blade elements is employed for the optimization design of the considered wind turbine ***,Computational Fluid Dynamics(CFD)is used to determine the aerodynamic performances of the eagle airfoil and a NACA2412 airfoil,thereby demonstrating the superior aerodynamic performance of the ***,a mathematical model for optimizing the design of wind turbine blades is introduced and a comparative analysis is conducted with respect to the aerodynamic performances of blades designed using a uniform extraction *** is found that the blades designed using non-uniform extraction exhibit better aerodynamic performance.

关键词： Airfoil wind turbines blade design CFD

来源：评论

学校读者我要写书评

暂无评论

Hybrid Simulation of a Wave Energy Converter Power Take Off for Flicker and Power Quality Studies

Hybrid Simulation of a Wave Energy Converter Power Take Off ...

引用

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Boller, Michael Carapellese, Fabio Brekken, Ted Cotilla-Sanchez, Eduardo Oregon State University School of Electrical Engineering and Computer Science CorvallisOR United States Politecnico di Torino Department of Mechanical and Aerospace Engineering Turin Italy

ISBN: (纸本)9798350316445

This paper presents a hybrid numerical-physical simulation of a point-absorber wave energy converter (WEC) for grid connected power quality studies. The simulated WEC is connected to a laboratory grid through a standard induction generator, with a weak grid simulated by added series impedance between the generator and the laboratory grid connection. Specifically, this paper presents the experimental demonstration of this system to measure power quality metrics including flicker and harmonics and compares the measured results from the hybrid numerical-physical WEC to existing research. © 2023 IEEE.

关键词： Flicker Hybrid-Simulation Power Quality Wave Energy Converter

来源：评论

学校读者我要写书评

暂无评论

Gravity-Based Kinetostatic Modeling of Parallel Manipulators Using Screw Theory

引用

Chinese Journal of mechanical engineering 2023年第6期36卷 73-86页

作者： Chao Yang Fengli Huang Wei Ye Qiaohong Chen College of Mechanical and Electrical Engineering Jiaxing UniversityJiaxing 314001China National and Local Joint Engineering Research Center of Reliability Analysis and Testing for Mechanical and Electrical Products Zhejiang Sci-Tech UniversityHangzhou 310018China School of Computer Science and Technology Zhejiang Sci-Tech UniversityHangzhou 310018China

The pose accuracy of parallel manipulators(PMs)is a key index to measure their *** the grav-ity-based kinetostatic model of a parallel robot provides an important basis for its error composition and accuracy *** this paper,a kinetostatic modeling approach that takes real gravity distribution into consideration is proposed to analyze the influence of gravity on the infinitesimal twist and actuator forces of ***,the duality of the twist screw and constraint wrenches are used to derive the gravity-attached constraint wrenches independent of the external load and the limb stiffness matrix corresponding to the kinematics-based constraint ***-ond,the gravity model of the mechanism is established based on the screw theory and the principle of virtual ***,the analytical formulas of the infinitesimal twist and the actuator force of PMs are obtained,and the influences of the external load,platform gravity,and rod gravity on the stiffness of the mechanism are *** non-overconstrained 3RPS and overconstrained 2PRU-UPR PMs are taken as examples to verify the proposed *** research proposes a methodology to analyze the infinitesimal deformation of the mechanism under the influence of gravity.

关键词： Parallel manipulator Kinetostatic model Gravity Screw theory

来源：评论

学校读者我要写书评

暂无评论

Design of electric powertrains to achieve NVH performance using autoencoders and a physical meaningful latent space

引用

Neural Computing and Applications 2025年 1-22页

作者： Ricardo Souza, Marcos Offner, Guenter Soltoggio, Andrea Mohammadpour, Mahdi Theodossiades, Stephanos Wolfson School of Mechanical Electrical and Manufacturing Engineering Loughborough University Loughborough United Kingdom AVL List GmbH Graz Austria Computer Science Department School of Science Loughborough University Loughborough United Kingdom

One of the fundamental differences in the perception of electric (e-) vehicles is how their radiated noise is perceived with respect to classic internal combustion engines. Even though e-vehicles are usually quieter, the tonal content of the radiated noise can be more annoying. This paper proposes a novel approach that starts from the assumed radiated noise spectrum profile as input to a neural network that can return powertrain design parameters that would lead to generation of that specific noise profile. The proposed network acts as an autoencoder where the latent space is forced to have a physical meaning. As diverse combinations of powertrain parameters can result in similar noise profiles, a variational autoencoder is used to learn a structured latent representation, ensuring continuity and smooth transitions between possible solutions. The network predictions are validated against results of a three-dimensional CAE e-powertrain model. Overall, the mean absolute error is around 5 dBA for this feasibility study, which aims to demonstrate the concept. This work takes an inverse approach to the optimisation problem by starting from the user-perceived noise to predict the parameters required to achieve that. Although this study focuses solely on gear teeth microgeometry changes and bearing preloads, additional powertrain parameters could be incorporated as needed. © The Author(s) 2025.

关键词： Internal combustion engines

来源：评论

学校读者我要写书评

暂无评论

DEVELOPMENT OF AUGMENTED REALITY SYSTEM FOR ADDITIVE MANUFACTURING 4

DEVELOPMENT OF AUGMENTED REALITY SYSTEM FOR ADDITIVE MANUFAC...

引用

4th IEEE International Conference on Smart Information Systems and Technologies, SIST 2024

作者： Rysbek, Yelnaz Jyeniskhan, Nursultan Hazrat Ali, Md. Shehab, Essam Computer Science Department Nazarbayev University Astana Kazakhstan Mechanical & Aerospace Engineering Department Nazarbayev University Astana Kazakhstan

ISBN: (纸本)9798350374865

Additive Manufacturing (AM) is becoming increasingly prevalent in diverse industries due to its ability to manufacture intricate and unique components at lower production costs. Despite its advantages in design flexibility and waste reduction, AM presents new challenges in real-time visibility, control mechanisms, and user interfaces. While existing web interfaces like OctoPrint offer partial solutions for monitoring the 3D printing process, Augmented Reality (AR) interfaces hold promise in enhancing real-time control and monitoring by overlaying computer-generated information onto the physical manufacturing environment. However, research on utilizing AR for remote collaboration and control of AM machines remains limited. This paper addresses this gap by proposing designing and developing an application that integrates an AR interface with a Fused Deposition Modeling (FDM) printer, enabling remote monitoring and control using Microsoft's AR headset, HoloLens2. The proposed system incorporates the usage of open-source projects such as OctoPrint for retrieving data from 3D printer, Printerface for establishing communication between 3D printer and desktop server, Mixed Reality Toolkit (MRTK) for the development of AR interface, and enterprise Photon Unity Networking 2 (PUN2) to establish the connection and achieve real-time communication with minimum latency close to 937 milliseconds. The measured time for data transmission between Octoprint and Unity Desktop Server is 0.01569 milliseconds and 936 milliseconds between Unity Desktop Server and AR client. © 2024 IEEE.

关键词： Fused Deposition Modeling

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：