检索结果-内蒙古大学图书馆

Comparison of game theoretical strategy and reinforcement learning in traffic light control

Periodica Polytechnica Transportation engineering 2020年第4期48卷 313-319页

作者： Guo, Jian Harmati, István Department of Control Engineering and Information Technology Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics H-1521 P. O. B. 91 Budapest Hungary

Many traffic models and control methods have already been utilized in the public transportation system due to the increasing traffic congestion. Thus, an intelligent traffic model is formalized and presented to control multiple traffic light simultaneously and efficiently according to the distribution of vehicles from each incoming link (i.e. sections) in this paper. Compared with constant strategy, two methods are proposed for traffic light control, i.e., game theoretical strategy and reinforcement learning methods. Game theoretical strategy is generated in a game theoretical framework where incoming links are regarded as players and the combination of the status of traffic lights can be regarded as decisions made by these players. The cost function is evaluated and the strategy is produced with Nash equilibrium for passing maximum vehicles in an intersection. The other one is Single-Agent Reinforcement Learning (SARL), specifically with the Q-learning algorithm in this case, which is usually used in such a dynamic environment to control traffic flow so the traffic problem could be improved. Generally, the intersection is regarded as the centralized agent and controlling signal status is considered as the actions of the agent. The performance of these two methods is compared after simulated and implemented in a junction. © 2020 Budapest University of Technology and Economics. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Finite-Set Model Predictive control Based Super Twisting Sliding Mode Speed controller for Linear Metro Applications

An Enhanced Finite-Set Model Predictive Control Based Super ...

引用

International Middle-East Power System Conference, MEPCON

作者： Mosaad M. Ali Mahmoud F. Elmorshedy Mohamed A. Gabr Haitham S. Ramadan Mostafa Wageh Lotfy Department of Electrical Engineering Faculty of Engineering Kafrelsheikh University Egypt Department of Electric Power and Machines Engineering Faculty of Engineering Tanta University Tanta Egypt Renewable Energy Laboratory College of Engineering Prince Sultan University Riyadh Saudi Arabia Electrical Power and Machines Dept. Faculty of Engineering Zagazig University Zagazig Egypt ISTHY Institut International sur le Stockage de l'Hydrogène Meroux-Moval Belfort Territory France Department of Process Control Technology Faculty of Technology and Education Beni-Suef University Beni Suef Egypt

The tracking speed issue of linear induction machines (LIMs) is addressed in this study via a nonlinear speed controller with model predictive current control (MPCC). The super twisting sliding mode controller (STSMC) controls the LIM speed instead of the traditional PI controller to provide a quick dynamic response with a smaller steady-state inaccuracy. The primary objective of the super twisting sliding mode controller (STSMC) is to regulate the q-axis primary current within the finite-set MPCC (FS-MPCC) framework. To avoid the use of an axis transformation problem and speed up the calculation process, the dynamic model of the suggested STSMC-based FSMPCC is fulfilled in the $\alpha \beta$ frame rather than the $dq$ frame. The suggested control technique is validated by simulation results based on the platform of two 3 kW arc induction motor drive systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pilot Study on Application for Analysis of Magnetic Resonance Spectroscopy Spectra

引用

IFAC-PapersOnLine 2022年第4期55卷 45-50页

作者： Justyna Tomicka Katarzyna Cichoń Wojciech Chlewicki Mariusz Holicki Mariusz Pelc Jarosław Zygarlicki Michał Podpora Aleksandra Kawala-Sterniuk West Pomeranian University of Technology in Szczecin Faculty of Electrical Engineering 70-313 Szczecin Poland West Pomeranian Oncology Center Department of Image Diagnostic Magnetic Resonance Imaging Laboratory 71-730 Szczecin Poland Opole University of Technology Faculty of Electrical Engineering Automatic Control and Informatics 45-758 Opole Poland

In this work an application for analysis of the spectrum in magnetic resonance spectroscopy is presented. For the purpose of analysis a dedicated, custom program was developed. Furthermore, the work presents the principle of operation of magnetic resonance spectroscopy and its application, mainly in oncology. We also describe an application developed to load the file in the DICOM standard using the Graphical User Interface window, determine the parameters for the appropriate metabolites necessary for the Gaussian function, estimate the concentration of metabolites and the relations between them. Some example usage Some example usage of the application is also included in the paper.

关键词： magnetic resonance spectroscopy magnetic resonance imaging metabolites

来源：评论

学校读者我要写书评

暂无评论

Reduced Network Cumulative Constraint Violation for Distributed Bandit Convex Optimization under Slater’s Condition

arXiv

引用

arXiv 2024年

作者： Zhang, Kunpeng Yi, Xinlei Ding, Jinliang Cao, Ming Johansson, Karl H. Yang, Tao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Control Science and Engineering College of Electronics and Information Engineering Tongji University Shanghai201800 China Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper studies the distributed bandit convex optimization problem with time-varying inequality constraints, where the goal is to minimize network regret and cumulative constraint violation. To calculate network cumulative constraint violation, existing distributed bandit online algorithms solving this problem directly use the clipped constraint function to replace its original constraint function. However, the use of the clipping operation renders Slater’s condition (i.e, there exists a point that strictly satisfies the inequality constraints at all iterations) ineffective to achieve reduced network cumulative constraint violation. To tackle this challenge, we propose a new distributed bandit online primal–dual algorithm. If local loss functions are convex, we show that the proposed algorithm establishes an O(T max{c,1−c})network regret bound and an O(T 1−c/2) network cumulative constraint violation bound, where T is the total number of iterations and c ∈ (0, 1) is a user-defined trade-off parameter. When Slater’s condition holds, the network cumulative constraint violation bound is reduced to O(T 1−c). In addition, if local loss functions are strongly convex, for the case where strongly convex parameters are unknown, the network regret bound is reduced to O(T1−c), and the network cumulative constraint violation bound is O(T1−c/2) and O(T1−c) without and with Slater’s condition, respectively. For the case where strongly convex parameters are known, the network regret bound is further reduced to O)(log(T)), and the network cumulative constraint violation bound is reduced to O(log(T)T) and O(log(T)) without and with Slater’s condition, respectively. To the best of our knowledge, this paper is among the first to establish reduced (network) cumulative constraint violation bounds for (distributed) bandit convex optimization with time-varying constraints under Slater’s condition. Finally, a numerical example is provided to verify the theoretical results. Copyright © 2

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancement and control of Reactive Power Sharing Utilizing Circulating Current in AC Microgrids

Enhancement and Control of Reactive Power Sharing Utilizing ...

引用

International Middle-East Power System Conference, MEPCON

作者： Ahmed Tazy Mohamed Mahmoud Samy Mohamed Ali Ghalib Electrical Engineering Department Faculty of Engineering Albaha University KSAt Dept. of Electrical Engineering University of Beni-Suef Beni-Suef Egypt Dept. of Process Control College of Technology and Education Beni-Suef University Beni-Suef Egypt

ISBN: (纸本)9781665463645

controlling frequency and voltage stability is the major objective of controlling an independent mode a difficult task since every distributed power supply Distributed energy resource (DERs). A small network can include various converters, connected in parallel to each other by lines with mismatched line resistance. The micro-grid includes both local and general loads. The conventional droop controller shows poor reactive power sharing when mismatched line impedance among DER modules is unable to ensure the stability of the microgrid, also, the reactive power sharing accuracy among inverters is not made accurate. In this study, an improved control strategy using a secondary central small network unit (SCMU), to increase the precision of power-sharing, also provides the most dynamic damping of the oscillator system. To improve the accuracy of power sharing and to improve the voltage on the bus at load, this controller is combined with sliding mode control. Two inverters connected in parallel were used to perform the simulation and the control model. The results showed the effectiveness of the proposed technique on the conventional control.

关键词： Vibrations Reactive power Microgrids Inverters Stability analysis Impedance Voltage control

来源：评论

学校读者我要写书评

暂无评论

The OPS-SAT benchmark for detecting anomalies in satellite telemetry

arXiv

引用

arXiv 2024年

作者： Ruszczak, Bogdan Kotowski, Krzysztof Evans, David Nalepa, Jakub Faculty of Electrical Engineering Automatic Control and Informatics Department of Informatics Opole University of Technology Prószkowska Str. 76 Opole45-758 Poland Faculty of Automatic Control Electronics and Computer Science Department of Algorithmics and Software Silesian University of Technology Akademicka Str. 16 Gliwice44-100 Poland KP Labs Bojkowska Str. 37J Gliwice44-100 Poland European Space Agency ESOC Robert-Bosch-Str. 5 Darmstadt64293 Germany

Detecting anomalous events in satellite telemetry is a critical task in space operations. This task, however, is extremely time-consuming, error-prone and human dependent, thus automated data-driven anomaly detection algorithms have been emerging at a steady pace. However, there are no publicly available datasets of real satellite telemetry accompanied with the ground-truth annotations that could be used to train and verify anomaly detection supervised models. In this article, we address this research gap and introduce the AI-ready benchmark dataset (OPSSAT-AD) containing the telemetry data acquired on board OPS-SAT—a CubeSat mission which has been operated by the European Space Agency which has come to an end during the night of 22–23 May 2024 (CEST). The dataset is accompanied with the baseline results obtained using 30 supervised and unsupervised classic and deep machine learning algorithms for anomaly detection. They were trained and validated using the training-test dataset split introduced in this work, and we present a suggested set of quality metrics which should be always calculated to confront the new algorithms for anomaly detection while exploiting OPSSAT-AD. We believe that this work may become an important step toward building a fair, reproducible and objective validation procedure that can be used to quantify the capabilities of the emerging anomaly detection techniques in an unbiased and fully transparent way. © 2024, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Influence of the variables describing brain signals on the performance of the Naive Bayesian Classifier

Influence of the variables describing brain signals on the p...

引用

2022 Progress in Applied electrical engineering, PAEE 2022

作者： Kawala-Sterniuk, Aleksandra Zygarlicki, Jaroslaw Lysiak, Adam Grochowicz, Barbara Pelc, Mariusz Bauer, Waldemar Baczkowicz, Dawid Krecisz, Krzysztof Dylag, Katarzyna A. Wieczorek, Wiktoria Kahankova, Radana Martinek, Radek Opole University of Technology Faculty of Electrical Engineering Automatic Control and Informatics Opole Poland University of Greenwich School of Computing and Mathematical Sciences London United Kingdom Agh University of Science and Technology Department of Automatic Control and Robotics Krakow Poland Opole University of Technology Faculty of Physical Education and Physiotherapy Opole Poland St. Louis Children Hospital Krakow Poland Jagiellonian University in Krakow-Collegium Medicum Department of Pathophysiology Krakow Poland Jagiellonian University in Krakow-Collegium Medicum Department of Bioinformatics and Telemedicine Krakow Poland Vsb - Technical University Ostrava Department of Cybernetics and Biomedical Engineering-FEECS Ostrava-Poruba Czech Republic

ISBN: (纸本)9781665455152

In this paper various variables describing brain signals such as near-infrared spectroscopy (NIRS) and electroencephalography (EEG) on the Naive Bayesian Classifier were presented. Analysis of biomedical signals is a very challenging task - therefore the authors of this work decided to analyse two types of brain signals - EEG and NIRS, which have different features, character, nature and are differently prone to various artifacts occurrence. The applied classifiers can be applied for various features extraction and pattern comparisons, which is useful in diagnostic processes. © 2022 IEEE.

关键词： Near infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Reducing the energy consumption required for the disassembly process implemented on an assembly and disassembly line

Reducing the energy consumption required for the disassembly...

引用

International Conference on control Systems and Computer Science (CSCS)

作者： Paun Marius-Adrian Dragomir Otilia Elena Dragomir Florin Iliescu Sergiu Stelian Minca Eugenia Duca Octavian Gabriel Gurgu Ion Valentin Department of Automation and Industrial Informatics University “Politehnica” of Bucharest Bucharest Romania Faculty of Electrical Engineering Electronics and Information Technology Valahia University of Targoviste Targoviste Romania Faculty of Automatic Control and Computers University “Politehnica ” of Bucharest Bucharest Romania Department of Automation and Electrical Engineering University “Dunarea de Jos ” of Galati Galati Romania Institute of Multidisciplinary Research for Science and Technology Valahia University of Targoviste Targoviste Romania

This paper proposes a method to reduce the energy consumption of an industrial disassembly process implemented on a production line by using an energy-efficient secondary disassembly process. In the case of defective products, the flow directs the simple product with priority to be disassembled in workstation (WS) 7. Therefore, all defective products are redirected to WS7. The disassembly of all simple products in WS7 is problematic for two reasons: the power consumption of WS7 is high compared to the other workstations, additionally there is an increased possibility of bottlenecks in the production line due to the high disassembly time. The proposed solution to reduce the possibility of deadlock and reduce power consumption is to redirect the defective products to the flexible cell (FC). Handling robots located in neighboring stations will participate collaboratively in the disassembly process. The control structure ensures that the two robots "meet" in the boundary plane of WS3 with WS4 and disassemble each component through collaborative tasks. Collaborative control of disassembly is thought of as a solution to the global "fluidization" of production, removing the bottleneck, from the overall flow, but also as an ingenious solution to reduce energy consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural network developed for obstacle avoidance of the four wheeled electric vehicle

Neural network developed for obstacle avoidance of the four ...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Grazia Lo Sciuto Paweł Kowol Paweł Nowak Wacław Banás Salvo Coco Giacomo Capizzi Department of Mechatronics Silesian University of Technology Gliwice Poland Department of Electrical Electronics and Informatics Engineering University of Catania Catania Italy Department of Automatic Control and Robotic Silesian University of Technology Gliwice Poland Department of Mathematics Applications and Methods for Artificial Intelligence Faculty of Applied Mathematics Silesian University of Technology Gliwice Poland

Several solutions have been proposed for vehicle navigation in unknown environments to ensure safer driving by avoiding obstacles and collisions. In this work, an electric vehicle equipped with Mecanum 4 omnidirectional holonomic wheels, analog joystick to control driving movement, LiDAR sensors and Wi-Fi able to detect obstacles is investigated based on neural network approach. By experimental tests conducted to avoid collisions by detecting the presence of obstacles, the relation between the resistance distance and speed is described by the artificial neural network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interpreting Industrial IoT Data Streams Through Fuzzy Querying With Hysteretic Fuzzy Sets on Apache Kafka

引用

IEEE Transactions on Fuzzy Systems 2024年第8期32卷 4671-4684页

作者： Bożena Małysiak-Mrozek Bartłomiej Ryba Marek Molęda Che-Lun Hung Witold Pedrycz Weiping Ding Dariusz Mrozek Department of Distributed Systems and Informatic Devices Silesian University of Technology Gliwice Poland Department of Applied Informatics Silesian University of Technology Gliwice Poland Institute of Biomedical Informatics National Yang Ming Chiao Tung University Taipei City Taiwan Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada Department of Measurements and Control Systems Silesian University of Technology Gliwice Poland Research Center of Performance and Productivity Analysis Istinye University Istanbul Türkiye School of Artificial Intelligence and Computer Science Nantong University Nantong China Faculty of Data Science City University of Macau Macau China

In industrial settings, querying data streams from Internet of Things (IoT) devices benefits from utilizing elastic criteria to enhance the interpretability of the current state of the monitored environment. Fuzzy sets provide this elasticity, enabling the aggregation and representation of similar values in a human-comprehensible manner. However, many sensor signals exhibit temporal oscillations, leading to varying interpretations of the signal based on its current trend (rising or falling). This hysteresis in signal (and subsequently of the production device) interpretation inspired us to introduce this phenomenon into data stream processing, resulting in the novel concept of hysteretic fuzzy sets. This article demonstrates how fuzzy searching and grouping can be applied to IoT sensor signals in flexible Big Data stream processing on Apache Kafka. We illustrate the impact of data stream querying with KSQL queries involving fuzzy sets (encompassing fuzzy filtering of data stream events, fuzzy transformation of data stream attributes, fuzzy grouping, and joining) on the flexibility of executed operations and computational resources utilized by the Kafka processing engine. Finally, our experiments with hysteretic fuzzy sets while analyzing sensor signals in power plants demonstrate that this novel approach effectively reduces the number of alarms while monitoring the state of the production machine.

关键词： Streams Fuzzy sets Internet of Things Big Data Monitoring Production Real-time systems

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：