检索结果-内蒙古大学图书馆

Design of an integrated actuator fault-tolerant control under robust performance requirements ⁎

IFAC-PapersOnLine 2020年第2期53卷 13745-13750页

作者： Mariusz Buciakowski Marcin Witczak Marcin Pazera Institute of Control & Computation Engineering The University of Zielona Góra ul. Szafrana 2 65-516 Zielona Góra Poland

The paper concerns a development of an integrated design of fault estimation and control scheme within an integrated actuator fault-tolerant control framework. The integrated design boils down to avoiding a standard three-step fault diagnosis (detection, isolation, identification) and replacing it by a fault estimation. Subsequently, the inaccuracies caused by fault estimation are taken into account while designing fault-tolerant controller. Contrarily to the usual framework, which extends the set of disturbances/noise by such inaccuracies, they are taken into account individually in such a way as to achieve a well-balanced final control effect. Finally, a complete fault-tolerant design procedure is provided along with its convergence analysis. The last part of the paper shows the performance of the proposed approach using a DC-servo motor benchmark example.

关键词： Fault-tolerant Observer design Robust control Fault detection diagnosis

来源：评论

学校读者我要写书评

暂无评论

Sensor Selection with Nonsmooth Design Criteria Based on Semi-Infinite Programming

引用

IFAC-PapersOnLine 2020年第2期53卷 7539-7544页

作者： Dariusz Uciński Institute of Control and Computation Engineering University of Zielona Góra ul. Szafrana 2 65-516 Zielona Góra Poland

A problem of optimal node activation in large-scale sensor networks is considered. The resulting measurements are supposed to be used to estimate unknown parameters of a spatiotemporal process described by a partial differential equation. In this setting, the sensor subset selection problem may quickly become computationally intractable when an excessively complex sensor location algorithm is employed. The is even more pronounced when the design criterion is nondifferentiable. A vital example of this criterion is the sum of an arbitrary number of smallest eigenvalues of the Fisher information matrix, being a generalization of the well-known E-optimality criterion. A simple branch-and-bound algorithm is exposed here to maximize this criterion. Its key component to produce upper bounds to the maximum of the objective function implements a relaxation procedure for solving semi-infinite programming problems. It alternates between solving a linear programming subproblem and evaluation of the eigenvalues and eigenvectors of the current information matrix, which makes it extremely easy to implement. The paper is complemented with a numerical example of computing actual sensor locations.

关键词： distributed parameter systems parameter estimation optimal experiment design sensor systems global optimization

来源：评论

学校读者我要写书评

暂无评论

Identification of Wiener models for dynamic and steady-state performance with application to solid oxide fuel cell

Identification of Wiener models for dynamic and steady-state...

引用

作者： Lawryńczuk, Maciej Institute of Control and Computation Engineering Faculty of Electronics and Information Technology Warsaw University of Technology Warsaw Poland

This work is concerned with identification of Wiener models (a linear dynamic part connected in series with a nonlinear dynamic one). A neural network with one hidden layer is used as the nonlinear block of the model, two network configurations are considered. For model identification three algorithms are described. In the first case model accuracy only in transient conditions is considered, only the dynamic data is used for model training. In the next two algorithms model accuracy in both transient and steady-state conditions is considered, dynamic and steady-state data sets are used. The steady-state model errors are taken into account by an additional term in the minimized cost-function or by additional inequality constraints. For comparison of discussed algorithms and model structures, identification of a Wiener model of a solid oxide fuel cell (SOFC) process is considered. It is shown that the best results are obtained by the algorithm 2 which minimizes at the same time both dynamic and steady-state model errors, additional constraints used in the algorithm 3 are computationally quite demanding. © 2019 Chinese Automatic control Society and John Wiley & Sons Australia, Ltd

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Kartalol: A New Deep Neural Network Framework Based on Transfer Learning for Iris Segmentation and Localization Task: New Dataset for Iris Segmentation

SSRN

引用

SSRN 2022年

作者： Khiarak, Jalil Nourmohammadi Oskouei, Amin Golzari Nasab, Samaneh Salehi Jaryani, Farhang Moafinejad, Seyed Naeim Pourmohamad, Rana Amini, Yasin Noshad, Morteza Institute of Control and Computation Engineering Warsaw University of Technology Warsaw Poland Department of Computer Engineering Faculty of Electrical and Computer Engineering University of Tabriz Iran School of Engineering Lorestan University Aleshtar Campus Aleshtar Iran Malek-Ashtar University of Technology Department of Physics Shahid Beheshti University Tehran Iran School of Computing Informatics and Decision Systems Engineering Arizona State University AZ United States Faculty of Electrical and Computer Engineering University of Kharazmi Iran Stanford University United States

Iris segmentation and localization in unconstrained environments is challenging due to long distances, illumination variations, limited user cooperation, and moving subjects. Some existing methods in the literature, each of which has somehow mitigated some of the mentioned issues. In this paper, motivated by these weaknesses, we propose a framework that employs a deep neural network-based approach to iris segmentation and localization. The proposed framework is based on a U-Net architecture that has been initialized with a pre-trained MobileNetV2 model. In addition, we have collected 1000 images to study the detectors in iris recognition scenarios better. The provided dataset (KartalOl) is available free for the research community. In the proposed framework, to better generalizability, we fine-tune the MobileNetV2 model on the provided data for NIR-ISL 2021 from the CASIA-Iris-Asia, CASIA-Iris-M1, and CASIA-Iris-Africa and our dataset. Also, data augmentation technics are applied on images. We chose the binarization threshold for the binary masks by iterating over the images in the provided dataset. The proposed framework is trained and tested in CASIA-Iris-Asia, CASIA-Iris-M1, CASIA-Iris-Africa, along the KartalOl dataset. The experimental results highlight that our method surpasses state-of-the-art methods on mobile-based benchmarks. The codes and evaluation results are publicly available at https://***/Jalilnkh/KartalOl-NIR-ISL2021031301. © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Quantum router for qutrit networks 27th

Quantum router for qutrit networks

引用

27th International Conference on Computer Networks, CN 2020

作者： Sawerwain, Marek Wiśniewska, Joanna Institute of Control and Computation Engineering University of Zielona Góra Licealna 9 Zielona Góra65-417 Poland Institute of Information Systems Faculty of Cybernetics Military University of Technology Gen. S. Kaliskiego 2 Warsaw00-908 Poland

ISBN: (纸本)9783030507183

Networks of quantum circuits or, more generally, networks transmitting quantum information will need, just like classical networks (e.g. internet), a mechanism for directing data to adequate nodes. Routing, understood as packet switching, is one of the most important processes in classical networks. The issue of routing is also present in quantum networks and an appropriate construction of a quantum router is required to transfer data to specific points in the network. We describe an implementation of a router for qutrits in this chapter. The router is four-qutrit quantum circuit (with one controlling unit). The efficiency and the accuracy of router’s work is tested by the Fidelity measure. The circuit’s dynamics is expressed by a Hamiltonian where the role of generalized Pauli operators is played by the Gell-Mann operators. © Springer Nature Switzerland AG 2020.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Fixed-point self-tuning CPU performance controller for Linux kernel

Fixed-point self-tuning CPU performance controller for Linux...

引用

2019 International Conference on High Performance Computing and Simulation, HPCS 2019

作者： Getka, Michal Karpowicz, Michal Institute of Control and Computation Engineering Warsaw University of Technology Nowowiejska 15/19 Warsaw00-665 Poland

ISBN: (纸本)9781728144849

Power saving techniques based on dynamic voltage and frequency scaling (DVFS) allow to optimize performance of processors capable of operating in more and more energy-efficient operating modes. In this paper we propose a new design of DVFS-based self-tuning CPU performance controller for the Linux kernel. The controller autonomously adapts to currently observed model of CPU load dynamics and adjusts CPU performance level to compensate for load variations while optimizing energy efficiency of performed operations. © 2019 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Health aware fault-tolerant forklift design and control in industry 4.0

Health aware fault-tolerant forklift design and control in i...

引用

Conference on control and Fault-Tolerant Systems (SysTol)

作者： Ralf Stetter Markus Till Marcin Witczak Bogdan Lipiec Steinbeis Transfer Center Automotive Systems Raueneggstraße Ravensburg Germany Department of Mechanical Engineering Ravensburg-Weingarten University (RWU) Doggenriedstrasse Weingarten Germany Institute of Control and Computation Engineering University of Zielona Gora 65-246 Zielona Gora Poland

The central objectives of the presented research work are the development of design methods and a control system which allow to incorporate knowledge concerning the health of system elements in industrial applications. The paper presents a framework combining fault-tolerant design, useful lifetime aware design, fault-tolerant control and planned condition dependent maintenance. These elements of the framework are explained and detailed investigations of some of these elements are presented. Fault-tolerant design is explained on the example of the drive modules of an industrial forklift. For useful lifetime aware design a detailed investigation concerning the health (respectively the remaining useful life (RUL)) of certain machine elements in forklifts in high storage warehouses is explained. The chosen machine elements are ball bearings due to their frequent application and enormous significance in industrial systems. For these elements, a multiple model-based Takagi-Sugeno scheme is presented that is capable to follow and predict the degradation of a technical system. Fault-tolerant control in this framework is explained through the application of a virtual fuzzy actuator for the drive system of the forklift.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Policy Evaluation in Distributional LQR

arXiv

引用

arXiv 2023年

作者： Wang, Zifan Gao, Yulong Wang, Siyi Zavlanos, Michael M. Abate, Alessandro Johansson, Karl H. Division of Decision and Control Systems School of Electrical Enginnering and Computer Science KTH Royal Institute of Technology Digital Futures StockholmSE-10044 Sweden Department of Computer Science University of Oxford OxfordOX13QD United Kingdom The School of Computation Information and Technology Technical University of Munich Munich80333 Germany The Department of Mechanical Engineering and Materials Science Duke University DurhamNC United States

Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard reinforcement learning. Meanwhile, a challenge in DRL is that the policy evaluation typically relies on the representation of the return distribution, which needs to be carefully designed. In this paper, we address this challenge for the special class of DRL problems that rely on a discounted linear quadratic regulator (LQR), which we call distributional LQR. Specifically, we provide a closed-form expression for the distribution of the random return, which is applicable for all types of exogenous disturbance as long as it is independent and identically distributed (i.i.d.). We show that the variance of the random return is bounded if the fourth moment of the exogenous disturbance is bounded. Furthermore, we investigate the sensitivity of the return distribution to model perturbations. While the proposed exact return distribution consists of infinitely many random variables, we show that this distribution can be well approximated by a finite number of random variables. The associated approximation error can be analytically bounded under mild assumptions. When the model is unknown, we propose a model-free approach for estimating the return distribution, supported by sample complexity guarantees. Finally, we extend our approach to partially observable linear systems. Numerical experiments are provided to illustrate the theoretical results. Copyright © 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

HyTract: Advancing tractography for neurosurgical planning with a hybrid method integrating neural networks and a path search algorithm

引用

Neural Networks 2025年 190卷

作者： Mateusz Korycinski Konrad A. Ciecierski Ewa Niewiadomska-Szynkiewicz Department of Artificial Intelligence Applications in Medicine and Sensitive Data Analysis NASK National Research Institute Kolska 12 Warsaw 01-045 Poland Institute of Control and Computation Engineering Warsaw University of Technology Nowowiejska 15/19 Warsaw 00-665 Poland

The advent of advanced MRI techniques has opened up promising avenues for exploring the intricacies of brain neurophysiology, including the network of neural connections. A more comprehensive understanding of this network provides invaluable insights into the human brain’s underlying structural architecture and dynamic functionalities. Consequently, determining the location of the neural fibers, known as tractography, has emerged as a subject of significant interest to both basic scientific research and practical domains, such as preoperative planning. This work presents a novel tractography method, HyTract, constructed using artificial neural networks and a path search algorithm. Our findings demonstrate that this method can accurately identify the location of nerve fibers in close proximity to the surgical field. Compared with well established methods, tracts computed with HyTract show Mean Euclidean Distance of 9 or lower, indicating a good accuracy in tract reconstruction. Furthermore, its architecture ensures the explainability of the obtained tracts and facilitates adaptation to new tasks.

关键词： Tractography Artificial neural networks DTI MRI Path search

来源：评论

学校读者我要写书评

暂无评论

Assessing the properties of a colloidal suspension with the aid of deep learning

arXiv

引用

arXiv 2021年

作者： Jakubczyk, Tomasz Jakubczyk, Daniel Stachurski, Andrzej Institute of Control and Computation Engineering Warsaw University of Technology ul. Nowowiejska 15/19 WarsawPL-00665 Poland Institute of Physics Polish Academy of Sciences al. Lotników 32/46 WarsawPL-02668 Poland

Convolution neural networks were applied to classify speckle images generated from nanoparticle suspensions and thus to recognise suspensions. The speckle images in the form of movies were obtained from suspensions placed in a thin cuvette. The classifier was trained, validated and tested on both single component monodispersive suspensions, as well as on two-component suspensions. It was able to properly recognise all the 73 classes – different suspensions from the training set, which is far beyond the capabilities of the human experimenter, and shows the capability of learning many more. The classes comprised different nanoparticle material and size, as well as different concentrations of the suspended phase. We also examined the capability of the system to generalise, by testing a system trained on single-component suspensions with two-component suspensions. The capability to generalise was found promising but significantly limited. A classification system using neural network was also compared with the one using support vector machine (SVM). SVM was found much more resource-consuming and thus could not be tested on full-size speckle images. Using image fragments very significantly deteriorates results for both SVM and neural networks. We showed that nanoparticle (colloidal) suspensions comprising even a large multi-parameter set of classes can be quickly identified using speckle images classified with convolution neural network. © 2021, CC BY-NC-ND.

关键词： Support vector machines

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：