检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Kulhánek, Jonáš Derner, Erik de Bruin, Tim Babuška, Robert Cognitive Robotics Faculty of 3mE Delft University of Technology Delft2628 CD Netherlands Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague16636 Czech Republic Department of Control Engineering Faculty of Electrical Engineering Czech Technical University in Prague Prague16627 Czech Republic

— Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target given by an image. To achieve this, we have extended the batched A2C algorithm with auxiliary tasks designed to improve visual navigation performance. We propose three additional auxiliary tasks: predicting the segmentation of the observation image and of the target image and predicting the depth-map. These tasks enable the use of supervised learning to pre-train a large part of the network and to reduce the number of training steps substantially. The training performance has been further improved by increasing the environment complexity gradually over time. An efficient neural network structure is proposed, which is capable of learning for multiple targets in multiple environments. Our method navigates in continuous state spaces and on the AI2-THOR environment simulator outperforms state-of-the-art goal-oriented visual navigation methods from the literature. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Robust cooperative synchronization of homogeneous agents with delays on directed communication graphs

arXiv

引用

arXiv 2019年

作者： Alikoc, Baran Hengster-Movric, Kristian Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague160 00 Czech Republic Department of Control Engineering Faculty of Electrical Engineering Czech Czech Technical University in Prague Prague166 36 Czech Republic

This study deals with analysis and control of cooperative synchronization for identical agents interacting on a directed graph topology. The agents are considered to have general continuous linear time-invariant dynamics with homogeneous communication and/or control delays. An LMI approach based on a Lyapunov-Krasovskii functional is proposed, together with the synchronizing region concept, which decouples the single-agent dynamics from the detailed graph topology. Moreover, the conventional notion of synchronizing region is here extended by an LMI relaxation utilizing quasi-convex characteristic of the problem. This leads to less conservative results for the region of graph matrix eigenvalues in the complex domain, where the synchronization is guaranteed. The proposed method to calculate the allowable delay bound for synchronization is also less conservative as compared to the results from the literature. Furthermore, two designs for distributed state-feedback control are suggested. The precise delay value and the detailed graph topology need not be known for their application;it suffices only to know the upper bound on the delay and the approximate region where the Laplacian eigenvalues lie. Specific improvements over the results existing in the literature are demonstrated by a numerical example, which validates the proposed approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Skill Assessment Using Kinematic Signatures: Geomagic Touch Haptic Device

Skill Assessment Using Kinematic Signatures: Geomagic Touch ...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： N. S. Hojati M. Motaharifar H. D. Taghirad A. Malekzadeh Advanced Robotics and Automated Systems (ARAS) Industrial Control Center of Excellence (ICCE) Faculty of Electrical Engineering K.N. Toosi University of Technology Tehran Iran Faculty of Mathematics K.N. Toosi University of Technology Tehran Iran

ISBN: (数字)9781728166049

ISBN: (纸本)9781728166056

The aim of this paper is to develop a practical skill assessment for some designed experimental tasks, retrieved from Minimally Invasive Surgery. The skill evaluation is very important in surgery training, especially in MIS. Most of the previous studies for skill assessment methods are limited in the Hidden Markov Model and some frequency transforms, such as Discrete Fourier transform, Discrete Cosine Transform and etc. In this paper, some features have been extracted from time-frequency analysis with the Discrete Wavelet Transform and temporal signal analysis of some kinematic metrics which were computed from Geomagic Touch kinematic data. In addition, the k-nearest neighbors classifier are employed to detect skill level based on extracted features. Through cross-validation results, it is demonstrated that the proposed methodology has annrouriate accuracy in skill level detection.

关键词： Feature extraction Measurement Discrete wavelet transforms Haptic interfaces Surgery Microsoft Windows

来源：评论

学校读者我要写书评

暂无评论

Investigation of the diagnostic properties of sensors and features in a multiphase flow facility case study ⁎

引用

IFAC-PapersOnLine 2019年第1期52卷 772-777页

作者： Anna Stief James R. Ottewill Jerzy Baranowski ABB Corporate Research Center ul. Starowislna 13a 31-038 Krakow Poland Department of Automatic Control and Robotics Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering AGH University of Science and Technology Al. A. Mickiewicza 30 30-059 Krakow Poland

Feature design and selection is one of the first steps towards successful fault detection and diagnosis. Data from different sources can contain complimentary information about a monitored system. Hence methods which fuse features from multiple sources can often detect and diagnose a greater number of fault modes with higher confidence. However, solutions that require data from multiple sensors as inputs can be susceptible to failure if one or more of those sensors cease to function. Optimally a solution will fuse data from a sufficient number of sensors so that the advantages of sensor fusion are realized, while the robustness of the system is retained. In this paper the authors investigate how the best subset of features might differ for fault detection and fault severity diagnosis in a multiphase flow facility case study. ReliefF, which is a K-nearest neighbors-based feature selection filter, is used to rank the features for different problems. The dataset used for the analysis contains data from various operating conditions and induced faults with various severities. It was found that the optimal subset of features varied for different monitoring problems. It was also shown that including features that are ranked as being uninformative into a fault classifier can also impact the robustness of the classifier to sensor failures.

关键词： Signal processing Feature extraction Feature selection Process monitoring

来源：评论

学校读者我要写书评

暂无评论

Performance comparison of optimization techniques in EHS system using sliding mode controller

引用

IOP Conference Series: Materials Science and engineering 2020年第1期834卷

作者： M S Chai R Ghazali S H Chong C C Soon J Too Y M Sam Centre for Robotics and Industrial Automation Faculty of Electrical Engineering Universiti Teknikal Malaysia Melaka Hang Tuah Jaya 76100 Durian Tunggal Melaka Malaysia. Control & Mechatronics Engineering Faculty of Electrical Engineering Universiti Teknologi Malaysia 81310 Skudai Johor Bahru Malaysia

Electro-Hydraulic Servo (EHS) system is a well-known nonlinear system in various types of industries due to its outstanding characteristics over other actuators. Despite its wide applications in industries, this system also suffering from nonlinearities and parameter uncertainties. Sliding Mode controller (SMC) has been proven by many researchers to be effective in positioning control of the nonlinear system. However, SMC controller parameters must be tuned in appropriate ways to control the EHS system. In this research, an SMC strategy which combines with an enhanced PSO called Multi-Objective Particle Swarm Optimization (MOPSO) is proposed in positioning control of the EHS system. The conventional PSO is design as well for comparison purpose. The output performance is analysed and verified using different performance indexes such as rise time, settling time, overshoot percentage, and root mean square error. The results show that the MOPSO is better in tuning the controller parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Electro-Hydraulic Servo with Intelligent control Strategy

An Electro-Hydraulic Servo with Intelligent Control Strategy

引用

2017 Malaysian Technical Universities Conference on engineering and Technology, MUCET 2017

作者： Mohammed, Saeed Chee Soon, Chong Ghazali, Rozaimi Yusof, Ahmad Anas Md Sam, Yahaya Mau Shern, Chai Centre for Robotics and Industrial Automation Faculty of Electrical Engineering Universiti Teknikal Malaysia Melaka Hang Tuah Jaya Durian Tunggal Melaka76100 Malaysia Faculty of Mechanical Engineering Universiti Teknikal Malaysia Melaka Hang Tuah Jaya Durian Tunggal Melaka76100 Malaysia Department of Control and Mechatronic Engineering Faculty of Electrical Engineering Universiti Teknologi Malaysia Skudai Johor81310 Malaysia

Versatile engineering applications have been developed to assist, reduce, and avoid human being from any heavy or harmful manufacturing processes. The gradually increased demand in force and position controls have simultaneously increased the usage of Electro-Hydraulic Servo (EHS) system. However, the time varying characteristics such as high-speed, outburst starting and stopping dynamic have led the EHS system to suffer from uncertainties and nonlinearities effects. Therefore, in order to enhance the performance of an EHS to surmount the uncertain and nonlinear effects, a hybrid Fuzzy-PID control strategy is developed which particularly improve the accuracy of the system by enhancing the control performance during the positioning tracking. By measuring the performance of the proposed control approach, the transient response and steady-state analysis will be performed which taking linear and intelligent control strategies as the references in the assessment process. The finding indicates the capability of a hybrid Fuzzy-PID controller in reducing the control effort applied to the EHS system. © The Authors, published by EDP Sciences, 2018.

关键词： Position control

来源：评论

学校读者我要写书评

暂无评论

RF chain reduction for MIMO systems: A hardware prototype

arXiv

引用

arXiv 2019年

作者： Gong, Tierui Shlezinger, Nir Ioushua, Shahar Stein Namer, Moshe Yang, Zhijia Eldar, Yonina C. State Key Lab of Robotics Key Lab of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot Israel School of Electrical Engineering Tel Aviv University Tel Aviv Israel Faculty of Electrical Engineering Technion Haifa Israel

RF chain circuits play a major role in digital receiver architectures, allowing passband communication signals to be processed in baseband. When operating at high frequencies, these circuits tend to be costly. This increased cost imposes a major limitation on future multiple-input multiple-output (MIMO) communication technologies. A common approach to mitigate the increased cost is to utilize hybrid architectures, in which the received signal is combined in analog into a lower dimension, thus reducing the number of RF chains. In this work we present a hardware prototype implementing analog combining for RF chain reduction. The prototype consists of a specially designed configurable combining board as well as a dedicated experimental setup. Our hardware prototype allows to evaluate the effect of analog combining in MIMO systems using actual communication signals. The experimental study, which focuses on channel estimation accuracy in MIMO channels, demonstrates that using the proposed prototype, the achievable channel estimation performance is within a small gap in a statistical sense from that obtained using a costly receiver in which each antenna is connected to a dedicated RF chain. Furthermore, in the considered scenarios, this gap becomes negligible when the reduction rate, i.e., the ratio of the number of RF chains to the number of antennas, is above 62.5%. Copyright © 2019, The Authors. All rights reserved.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

On applying a generalized Padé approximation to stability analysis - experimental results

On applying a generalized Padé approximation to stability a...

引用

MECHATRONIKA International Symposium

作者： Dariusz Horla Faculty of Electrical Engineering Institute of Control Robotics and Information Engineering Poznan University of Technology Poznan Poland

ISBN: (纸本)9781538643648;9788021455429

The paper verifies by means of experiments the applicability of the generalized Padé approximation of the dead time to stability analysis (estimation of stability margins of the closed-loop system). Initial research carried on the topic revealed that there is a range of fractional orders of the generalized approximators, where the results obtained from fractional-order analysis give conservative results, and the approach is comparable to standard Padé approximation. In the paper, author aims at verifying this on the basis of experiments conducted with the use of FOMCON toolbox to implement fractional-order operators, and the Inteco Modular Servo System, comparing the identified model of the servo drive with added artificial open-loop delay, and the behaviour of the real closed-loop system. The analysis of the use of the generalized approximation, as well as application to a hardware-in-the-loop control problem, is the main novelty of the paper, since all prior approaches of various authors concentrated on time-domain analysis of the generalized approximator, not on stability issues.

关键词： Delays Closed loop systems Standards Servomotors Optimization Stability criteria

来源：评论

学校读者我要写书评

暂无评论

New Grid for Particle Filtering of Multivariable Nonlinear Objects

New Grid for Particle Filtering of Multivariable Nonlinear O...

引用

Federated Conference on Computer Science and Information Systems

作者： Piotr Kozierski Jacek Michalski Talar Sadalla Wojciech Giernacki Joanna Zietkiewicz Szymon Drgas Faculty of Computing Institute of Automation and Robotics Division of Signal Processing and Electronic Systems Poznan University of Technology Faculty of Electrical Engineering Institute of Control Robotics and Information Engineering Division of Control and Robotics Poznan University of Technology

ISBN: (纸本)9781538623718

In the paper a new grid (potentially linear, nonlinear and even semi-Markovian jump system) was presented. All transition and measurement functions were proposed. Moreover, the transition functions of two types were considered - dependent on one and many different state variables. Also 10 types of measurements were proposed for both nodal and branch cases. Based on the obtained results one can see, which measurement functions are "easy", and which are "hard" for state estimation task.

关键词： Measuring Function Particle filters grids Grid State variable Multivariable nonlinearity

来源：评论

学校读者我要写书评

暂无评论

Heat Transfer Optimization of end Winding Rotor Generator by the Use of Modified Axial Spacer: A Case Study

引用

Journal of Physics: Conference Series 2021年第1期1845卷

作者： Y Baskoro I Jaya A Glowacz M Sulowicz W Caesarendra PT Indonesia Power Indonesia Department of Automatic Control and Robotics AGH University of Science and Technology 30-059 Kraków Poland Institute of Electromechanical Energy Conversion Faculty of Electrical and Computer Engineering Cracow University of Technology Warszawska 24 31-155 Cracow Poland Faculty of Integrated Technologies Universiti Brunei Darussalam Jalan Tungku Link Gadong BE1410 Brunei Darussalam

This paper presents a case study of a rotor fault occurring in the rotor generator of a steam power plant located in Lontar, Banten Province, Indonesia. The steam power plant has 3 x 315 MV capacity and uses hydrogen in the cooling system. The issue arising during the operation was caused by heat transfer exceeding the normal level. The grounding of the rotor occurred through rising vibration and temperature, tripping the generator unit. During repairs, the axial spacer was replaced with a new model, where it is longer than the original, adding a bar spacer at a previously unavailable position and creating a cooling track profile. This is a case study on the replacement of the axial spacer model aimed at preventing the expansion of the winding, so as not to touch with each other, through the installation of a longer axial spacer and the addition of the spacer bar, and lastly adding the track profile to the cooling hydrogen gas flow thereby maximizing the cooling process from the end winding rotor generator. Heat transfer is an analysed parameter related to the model change of the axial spacer. The addition of a track cooling gas flow has been able to maximize the heat transfer process, which is simulated in this paper. The performance of the rotor generator increased through several parameters after the replacement of the axial spacer model.

关键词：

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：