检索结果-内蒙古大学图书馆

American control Conference (ACC)

作者： Anantha Sai Hariharan Vinjarapu Yorick Broens Hans Butler Roland Tóth Department of Electrical Engineering Eindhoven University of Technology Eindhoven The Netherlands ASML Veldhoven The Netherlands Systems and Control Laboratory Institute for Computer Science and Control Hungary

Growing demands in today’s industry results in increasingly stringent performance and throughput specifications. For accurate positioning of high-precision motion systems, feedforward control plays a crucial role. Nonetheless, conventional model-based feedforward approaches are no longer sufficient to satisfy the challenging performance requirements. An attractive method for systems with repetitive motion tasks is iterative learning control (ILC) due to its superior performance. However, for systems with non-repetitive motion tasks, ILC is generally not applicable, despite of some recent promising advances. In this paper, we aim to explore the use of deep learning to address the task flexibility constraint of ILC. For this purpose, a novel Task Analogy based Imitation Learning (TAIL)-ILC approach is developed. To benchmark the performance of the proposed approach, a simulation study is presented which compares the TAIL-ILC to classical model-based feedforward strategies and existing learning-based approaches, such as neural network based feedforward learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a prototype of an intelligent system for predicting the quality of dairy manufacture 11

Development of a prototype of an intelligent system for pred...

引用

11th IEEE International Conference on Intelligent systems, IS 2022

作者： Smitiukh, Yaroslav Samoilenko, Yuliia Kostiuk, Yuliia Kryvoruchko, Olena Stepashkina, Kateryna National University of Food Technologies Department of Automation and Computer Technologies of Control Systems Kyiv Ukraine State University of Trade and Economics Department of Software Engineering and Cyber Security Kyiv Ukraine

ISBN: (纸本)9781665456562

The technological process of the churning process in continuous butter manufacture were considered. The qualitative indicator of the water content of butter was modeled on the basis of a set of industrial data using an artificial neural network (ANN). The prototype of an intelligent system for predicting of the water content of butter allows to increase the information support of the operator-technologist. The proposed model predicts the water content of butter with an error of less than 2%. The input variables of the forecast model prototype are cream fat content, cream ripening temperature, cream supply temperature, frequency of revolutions of the stirrer of the whipping device, and consumption of the normalizing component. Further research is aimed at the development of a decision support information system for dairy manufacture and should be integrated into the subsystem of automated control of the technological process to ensure proper functioning in real time. © 2022 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Exploring the use of deep learning in task-flexible ILC

arXiv

引用

arXiv 2023年

作者： Vinjarapu, Anantha Sai Hariharan Broens, Yorick Butler, Hans Tóth, Roland The Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands The Systems and Control Laboratory Institute for Computer Science and Control Hungary Asml Veldhoven Netherlands

Growing demands in today's industry results in increasingly stringent performance and throughput specifications. For accurate positioning of high-precision motion systems, feedforward control plays a crucial role. Nonetheless, conventional model-based feedforward approaches are no longer sufficient to satisfy the challenging performance requirements. An attractive method for systems with repetitive motion tasks is iterative learning control (ILC) due to its superior performance. However, for systems with non-repetitive motion tasks, ILC is generally not applicable, despite of some recent promising advances. In this paper, we aim to explore the use of deep learning to address the task flexibility constraint of ILC. For this purpose, a novel Task Analogy based Imitation Learning (TAIL)-ILC approach is developed. To benchmark the performance of the proposed approach, a simulation study is presented which compares the TAIL-ILC to classical model-based feedforward strategies and existing learning-based approaches, such as neural network based feedforward *** Codes 37M15 © 2023, CC BY.

关键词： Feedforward control

来源：评论

学校读者我要写书评

暂无评论

Optimizing Foundation Model Inference on a Many-Tiny-Core Open-Source RISC-V Platform

IEEE Transactions on Circuits and Systems for Artificial Int...

引用

IEEE Transactions on Circuits and systems for Artificial Intelligence 2024年第1期1卷 37-52页

作者： Viviane Potocnik Luca Colagrande Tim Fischer Luca Bertaccini Daniele Jahier Pagliari Alessio Burrello Luca Benini Integrated Systems Laboratory (IIS) of ETH Zürich ETZ Züurich Switzerland Department of Control and Computer Engineering Politecnico di Torino Turin Italy Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy

Transformer-based foundation models have become crucial for various domains, most notably natural language processing (NLP) or computer vision (CV). These models are predominantly deployed on high-performance GPUs or hardwired accelerators with highly customized, proprietary instruction sets. Until now, limited attention has been given to RISC-V-based general-purpose platforms. In our work, we present the first inference results of transformer models on an open-source many-tiny-core RISC-V platform implementing distributed Softmax primitives and leveraging ISA extensions for SIMD floating-point operand streaming and instruction repetition, as well as specialized DMA engines to minimize costly main memory accesses and to tolerate their latency. We focus on two foundational transformer topologies, encoder-only and decoder-only models. For encoder-only models, we demonstrate a speedup of up to 12.8 $\times$ between the most optimized implementation and the baseline version. We reach over 79% FPU utilization and 294 GFLOPS/W, outperforming State-of-the-Art (SoA) accelerators by more than 2 $\times$ utilizing the HW platform while achieving comparable throughput per computational unit. For decoder-only topologies, we achieve 16.1 $\times$ speedup in the Non-Autoregressive (NAR) mode and up to 35.6 $\times$ speedup in the Autoregressive (AR) mode compared to the baseline implementation. Compared to the best SoA dedicated accelerator, we achieve 2.04 $\times$ higher FPU utilization.

关键词： Frequency modulation Transformers computer architecture Computational modeling Kernel Artificial intelligence Hardware

来源：评论

学校读者我要写书评

暂无评论

Geometric Parameterized Macromodel of Uniaxial Capacitance Accelerometer Based on Modal Superposition 16

Geometric Parameterized Macromodel of Uniaxial Capacitance A...

引用

16th IEEE International Scientific and Technical Conference Actual Problems of Electronic Instrument engineering, APEIE 2023

作者： Gridchin, Aleksandr V. Koleda, Aleksei N. Barbin, Evgenii S. Nesterenko, Tamara G. Kolchuzhin, Vladimir A. Department of Semiconductor Devices and Microelectronics Novosibirsk State Technical University Novosibirsk Russia Department of Electronic Engineering National Research Tomsk Polytechnic University Tomsk Russia Laboratory of Intelligent Computer Systems Tomsk State University of Control Systems and Radioelectronics Tomsk Russia Advanced Cellular Group Qorvo Munich GmbH Munich Germany

ISBN: (纸本)9798350330885

The paper presents a piecewise geometric parameterization method and a parametric analysis of uniaxial capacitance accelerometer using a reduced model formulated on the modal superposition method. The extraction of parameters for the macromodel such as modal frequencies, modal masses, modal stiffnesses, strain energy, and capacitances are described. The reduced model consists of the two modes: torsion mode, and transversal mode, three electrodes in the electrostatic domain, and eight master nodes in the geometrical domain located at the edges of the plate. The generation of the discrete macromodels is executed using commercial software. The thickness of the plate has been selected as a design parameter. Linear piecewise interpolation is used for macromodel parameterization which have been done inside VHDL-AMS code. The accelerometer's dynamic response simulated using of parametrized macromodel considering the mechanical contact phenomena and the nonlinear electrostatic interaction are presented and discussed. The developed approach can be applied for fast system level simulations in view of the variation of the geometric parameters. © 2023 IEEE.

关键词： Capacitance

来源：评论

学校读者我要写书评

暂无评论

Visual Odometry with Depth-Wise Separable Convolution and Quaternion Neural Networks 9

Visual Odometry with Depth-Wise Separable Convolution and Qu...

引用

9th Italian Workshop on Artificial Intelligence and Robotics, AIRO 2022

作者： De Magistris, Giorgio Comminiello, Danilo Napoli, Christian Starczewski, Janusz T. Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 Rome00185 Italy Department of Information Engineering Electronics and Telecommunications Sapienza University of Rome Via Eudossiana 18 Rome00184 Italy Department of Intelligent Computer Systems Czestochowa University of Technology al.Armii Krajowej 36 Czestochowa42-200C Poland

Monocular visual odometry is a fundamental problem in computer vision and it was extensively studied in literature. The vast majority of visual odometry algorithms are based on a standard pipeline consisting in feature detection, feature matching, motion estimation and local optimization. Only recently, deep learning approaches have shown cutting-edge performance, replacing the standard pipeline with an end-to-end solution. One of the main advantages of deep learning approaches over the standard methods is the reduced inference time, that is an important requirement for the application of visual odometry in real-time. Less emphasis, however, has been placed on memory requirements and training efficiency. The memory footprint, in particular, is important for real world applications such as robot navigation or autonomous driving, where the devices have limited memory resources. In this paper we tackle both aspects introducing novel architectures based on Depth-Wise Separable Convolutional Neural Network and deep Quaternion Recurrent Convolutional Neural Network. In particular, we obtain equal or better accuracy with respect to the other state-of-the-art methods on the KITTI VO dataset with a reduction of the number of parameters and a speed-up in the inference time. © 2022 Copyright for this paper by its authors.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Classification of Images Based on a System of Hierarchical Features

引用

computers, Materials & Continua 2022年第7期72卷 1785-1797页

作者： Yousef Ibrahim Daradkeh Volodymyr Gorokhovatskyi Iryna Tvoroshenko Mujahed Al-Dhaifallah Department of Computer Engineering and Networks College of Engineering at Wadi AddawasirPrince Sattam Bin Abdulaziz UniversityAl-Kharj11991Saudi Arabia Department of Informatics Kharkiv National University of Radio ElectronicsKharkiv61166Ukraine Control and Instrumentation Engineering Department and Interdisciplinary Research Center(IRC)for Renewable Energy and Power SystemsKing Fahd University of Petroleum&MineralsDhahran31261Saudi Arabia

The results of the development of the new fast-speed method of classification images using a structural approach are *** method is based on the system of hierarchical features,based on the bitwise data distribution for the set of descriptors of image *** article also proposes the use of the spatial data processing apparatus,which simplifies and accelerates the classification *** have shown that the time of calculation of the relevance for two descriptions according to their distributions is about 1000 times less than for the traditional voting procedure,for which the sets of descriptors are *** introduction of the system of hierarchical features allows to further reduce the calculation time by 2–3 times while ensuring high efficiency of *** noise immunity of the method to additive noise has been experimentally *** to the results of the research,the marginal degree of the hierarchy of features for reliable classification with the standard deviation of noise less than 30 is the 8-bit *** costs increase proportionally with decreasing bit *** method can be used for application tasks where object identification time is critical.

关键词： Bitwise distribution computer vision descriptor hierarchical representation image classification keypoint noise immunity processing speed

来源：评论

学校读者我要写书评

暂无评论

Parameter fault estimation in distributed heating/cooling systems 7

Parameter fault estimation in distributed heating/cooling sy...

引用

7th International Conference on Sustainable Information engineering and Technology, SIET 2022

作者： Kurniawan, Wijaya Hangos, Katalin M. Marton, Lorinc Faculty of Computer Science University of Brawijaya Malang Indonesia Dept. of Electrical Engineering and Information Systems University of Pannonia Veszprem Hungary Institute for Computer Science and Control Budapest Hungary Dept. of Electrical Engineering Sapientia Hungarian University of Transylvania Targu Mures Romania

ISBN: (纸本)9781450397117

In this paper, the problem of fault estimation and localization in the connecting dynamic elements of distributed heating and cooling systems are treated. The fault represents the physical parameter change related to the heat transfer between the system and the external environment. First, based on the bi-linear dynamic state space model of the system in the presence of a fault, structural observability analysis using Signed Directed Graph (SDG) has been performed to investigate the sensor placement problem. Then, a nonlinear observer with a parameter adaptation algorithm was proposed for fault estimation. The simulation results show that it can successfully detect and estimate the fault. Fault localization along the length of the element has also been attempted, but it has been found that the localization cannot be performed using practically changeable input variables. Frequency domain analysis is presented to discuss this phenomenon. © 2022 ACM.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Efficient Coordination and Synchronization of Multi-Robot systems Under Recurring Linear Temporal Logic

arXiv

引用

arXiv 2025年

作者： Peron, Davide Fernandez-Ayala, Victor Nan Vlahakis, Eleftherios E. Dimarogonas, Dimos V. Department of Information Engineering University of Padova Padova35122 Italy Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

We consider multi-robot systems under recurring tasks formalized as linear temporal logic (LTL) specifications. To solve the planning problem efficiently, we propose a bottom-up approach combining offline plan synthesis with online coordination, dynamically adjusting plans via real-time communication. To address action delays, we introduce a synchronization mechanism ensuring coordinated task execution, leading to a multi-agent coordination and synchronization framework that is adaptable to a wide range of multi-robot applications. The software package is developed in Python and ROS2 for broad deployment. We validate our findings through lab experiments involving nine robots showing enhanced adaptability compared to previous methods. Additionally, we conduct simulations with up to ninety agents to demonstrate the reduced computational complexity and the scalability features of our work. © 2025, CC BY.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Gaussian process-based visual pursuit control with unknown target motion learning in three dimensions

引用

SICE Journal of control, Measurement, and System Integration 2021年第1期14卷 116-127页

作者： Omainska, Marco Yamauchi, Junya Beckers, Thomas Hatanaka, Takeshi Hirche, Sandra Fujita, Masayuki Department of Information Physics and Computing The University of Tokyo Tokyo Japan Department of Electrical and Systems Engineering University of Pennsylvania PennsylvaniaPA United States Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo Japan Department of Electrical and Computer Engineering Technical University of Munich Munich Germany

In this paper, we propose an observer-based visual pursuit control integrating three-dimensional target motion learning by Gaussian Process Regression (GPR). We consider a situation where a visual sensor equipped rigid body pursuits a target rigid body whose velocity is unknown but dependent on the target's pose. We estimate the pose from visual information and propose a Gaussian Process (GP) model to predict the target velocity from the pose estimate. We analyse stability of the proposed control by showing that estimation and control errors are ultimately bounded with high probability. Finally, simulations illustrate the performance of the proposed control schemes even if the visual measurement is corrupted by noise. © 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Gaussian distribution

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：