检索结果-内蒙古大学图书馆

On Algebraically Invariant control for Tropical Dynamical Systems:Pseudo-polynomial Methods and Robustness Considerations

引用

IFAC-PapersOnLine 2024年第1期58卷 48-53页

作者： André E. de Morais Carlos Andrey Maia Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais (UFMG) Av. Ant. Carlos 6627 31270-901 Belo Horizonte MG Brasil Control and Industrial Processes area Instituto Federal de Minas Gerais IFMG campus Sabará - Rodovia MGC 262 Km 10 34564-070 Sabará MG Brasil Dpto. Engenharia Elétrica UFMG Av. Ant. Carlos 6627 31270-901 Belo Horizonte MG Brasil

Designing an invariant controller for a Tropical Linear Dynamical System involves formulating a tropical control law to ensure that the system state remains within a tropical subspace whenever the initial condition is situated within that subspace. In this paper, we explore a controller design approach that not only takes into account the invariance property but also optimizes the closed-loop system performance. Also, a preliminary discussion on control robustness is presented along with a new proposition.

关键词： Tropical Algebra Discrete Event Systems Invariant control Modeling and Simulation

来源：评论

学校读者我要写书评

暂无评论

Towards Real-Time Machining Tool Failure Forecast Approach for Smart Manufacturing Systems

引用

IFAC-PapersOnLine 2022年第2期55卷 548-553页

作者： Nicolas Nebelung Mario D.S. de Oliveira Santos Sofia T. Helena Athon F.C.S. de Moura Leite Matheus B. Canciglieri Anderson L. Szejka Control and Automation Engineering Department Pontifical Catholic University of Paraná (PUCPR) Curitiba Brazil Junior Scientific Initiation Program at the Nossa Senhora de Medianeira School and Pontifical Catholic University of Paraná Curitiba – Paraná Brazil Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Paraná (PUCPR) Curitiba Brazil

Industry 4.0 is characterized by a dynamic market that constantly looking for new methods to optimize and integrate manufacturing processes. In this context, Artificial Intelligence has gained prominence in problem-solving, such as failure prediction and decision making, thus improving product quality, and consequently bringing competitiveness to the company. Aiming to contribute to this scenario, this research develops a data treatment system that, from an intelligent tool and an interoperable ontological model, automates the prediction and detection of failures in machining machines lines. The system was developed for the prediction of faults in machining lines includes an artificial intelligence formed from prediction algorithms and inferences, it is possible to guarantee the correct treatment and communication of data at different stages of the process. For the experimental research, was used data collected from a machining line of a public dataset. The information is collected and classified by Artificial Intelligence that supports a decision system. The prediction of tool wear would enable the system to infer the type of problem that is causing this wear, a possible root cause, and the needed maintenance based on the ontological inference tool. By this classification of data, it is possible to achieve, through inferences, a reduction in the decision scope, bringing the possible problems caused by the incoming value. The semantic interoperability ensures correct data exchange and processing, which generates a more assertive view of production failures. The system may help companies to increase their productive process by helping them identify future failures in production if applied in a real scenario.

关键词： Industry 4.0 Smart System Artificial Intelligence Machine Learning Ontology Machine Failure Forecast

来源：评论

学校读者我要写书评

暂无评论

A Mixed Integer Linear programming Model for the Distribution of Transport Tasks Among Heterogeneous Robots in a Factory

A Mixed Integer Linear Programming Model for the Distributio...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Igor Pardal Latini Wilson Eduardo Barioni Marco Teixeira Flavio Neves-Jr Lucia Valeria Ramos de Arruda CPGEI-UTFPR Curitiba Parana Brazil Universidade Tecnologica Federal do Parana (UTFPR) Curitiba Parana Brazil Automation and Advanced Control System Laboratory (LASCA) Graduate Program in Electrical and Computer Engineering (CPGEI) Pontificia Universidade Catolica do Parana (PUCPR) Curitiba Parana Brazil PPGla-PUCPR Curitiba Parana Brazil

ISBN: (数字)9798350340266

ISBN: (纸本)9798350340273

The growing need for automation of factories and their processes determines a constant increase in the use of robots to carry out various tasks. Multiple robots can do different tasks simultaneously, speeding up processes. This practice raises the question of how many robots are needed to service the entire process, given all the limitations of the operation. One of these limitations is due to the navigation systems used by the several robots in the environment. Line-followers robots, for example, can only meet some tasks but are cheaper than free-movement ones. In this work, we develop an optimization model for task allocation among the available robots to minimize execution delays using mixed integer linear programming, considering their navigation systems. With the model, it is possible to obtain the best task allocation for each robot and the order to perform such tasks, thus avoiding delays as much as possible and getting zero delays for the presented case, that emulates the process of a vehicle assembler factory line.

关键词： Service robots Navigation Search problems Production facilities Delays Mixed integer linear programming Batteries

来源：评论

学校读者我要写书评

暂无评论

Predicting the compressive strength of steelmaking slag concrete with machine learning - Considerations on developing a mix design tool

引用

CONSTRUCTION AND BUILDING MATERIALS 2022年 341卷

作者： Penido, Ruben El-Katib Paixa, Rafael Christian Fonseca da Costa, Lafs Cristina Barbosa Peixoto, Ricardo Andre Fiorotti Cury, Alexandre Abrahao Mendes, Julia Castro [a]Federal University of Ouro Preto – UFOP Department of Civil Engineering Ouro Preto Minas Gerais Brazil [b]Federal University of Ouro Preto – UFOP Department of Control and Automation Engineering Ouro Preto Minas Gerais Brazil [c]Federal University of Juiz de Fora – UFJF Graduate Program in Civil Engineering (PEC) Juiz de Fora Minas Gerais Brazil

Steelmaking slag has been extensively studied as aggregate for cement-based composites. Because of the distinct properties of this residue, traditional mix design methods are not suitable to determine its target compressive strength, which hinders research studies and compromises its use on a large scale. In this context, the present work aims to develop machine learning (ML)-based models to predict the compressive strength of steel slag concretes from their mix proportion. For this purpose, a global data survey on steel slag concretes was carried out to create a benchmark dataset. Then, four ML-based models were trained and cross-validated using this dataset: Support Vector Regression (SVR), Artificial Neural Networks (ANN), Extreme Gradient Boost (XGBoost), and Gaussian Process Regression (GPR). Finally, new steel slag concrete specimens were built and tested to experi-mentally validate the adjusted models. The model that achieved the best performance using the literature dataset was the ANN, with a R2 of 0.79. However, the experimental validation was not satisfactory - the GPR, XGBoost and SVR models presented negative R2 values. These results brought light to some pivotal aspects that must be considered when using ML techniques: i) the size and homogeneity of the dataset;ii) the proper choice of input parameters;and iii) the use of cross-validation to adjust the models. Hence, although such techniques are promising and powerful, care must be taken on the generalization of their predictions, especially when the available data is limited.

关键词： Steelmaking slag Compressive strength Concrete mixture Machine learning Experimental validation

来源：评论

学校读者我要写书评

暂无评论

Real engineering Problems in an Undergraduate Course: The learning methodologies and assessment tools

Real Engineering Problems in an Undergraduate Course: The le...

引用

World engineering Education Forum - Global engineering Deans Council (WEEF-GEDC)

作者： Ricardo A. Diogo André L.A.C. Venâncio Maria Angela M. Roveredo Santos Eduardo F.R. Loures Neri dos Santos Knowledge Engineering&Management Graduate Program Federal University of Santa Catarina Florianopolis Brazil Industrial&Systems Engineering Graduate Program Pontifical Catholic University of Parana Curitiba Brazil Control and Automation Engineering/Mechatronics Engineering Pontifical Catholic University of Parana Curitiba Brazil

ISBN: (纸本)9781665424899

This paper presents the context of the Ubiquitous Computing course carried out in an Industrial engineering undergraduate program throughout 2020 and the first semester of 2021. This course took advantage of the Institutional Modernization program led by the control and automation engineering Undergraduate program, which consists in the modernization of undergraduate engineering programs at the Pontifical Catholic University of Paraná. The course aimed to help develop competencies, i.e., a set of knowledge, skills, and attributes aligned with Student Outcomes suggested by ABET. Also, the course proposal brought the productive sector very close to the academic environment, proposing real engineering problems as challenges. However, what are the methods and assessment tools for practical learning in a course with modern elements? This paper proposed the flipped learning and the Challenge-Based Learning Framework with the support of the CDIO Framework as learning methodologies to answer such question. Additionally, quizzes, tests, presentations, rubrics, and peer evaluation were applied as assessment tools to measure the student's progress. Finally, students were listened to about their perceptions during the course. The results suggested that the learning methodologies and assessment tools are suitable for the course context, although some improvements are expected for the following course offers. Moreover, students approved the initiative to bring in real challenges proposed by companies, the mentoring hours, and the feedback about the projects.

关键词： automation Companies Industrial engineering Ubiquitous computing Proposals Mentoring engineering education

来源：评论

学校读者我要写书评

暂无评论

Improved Gain-Scheduled control Design for Rational Nonlinear Discrete-Time Systems with Input Saturation

Improved Gain-Scheduled Control Design for Rational Nonlinea...

引用

European control Conference (ECC)

作者： Gabriela L. Reis Rodrigo F. Araú jo Leonardo A. B. Tô rres Reinaldo M. Palhares Department of Technological Education Graduate Program in Electrical Engineering Federal University of Minas Gerais Federal Institute of Southeast Minas Gerais Minas Gerais Brasil Department of Control and Automation Engineering Amazonas State University Amazonas Brazil Department of Aerospace Engineering California Polytechnic State University CA USA Department of Electronics Engineering Federal University of Minas Gerais Minas Gerais Brazil

ISBN: (数字)9783907144077

ISBN: (纸本)9781665497336

An improved method of control design for rational nonlinear discrete-time systems with input saturation is proposed in this paper. Using Difference-Algebraic Representation (DAR) and parameter-dependent Lyapunov functions, a novel regional stabilization condition in terms of Linear Matrix Inequalities (LMI) is presented. Two optimization problems are addressed to either obtain the largest estimated Domain of Attraction (DoA) or minimize the $\ell_{2}$ -gain from the energy-bounded disturbance input to the performance output. Numerical examples illustrate the potential of the proposed approach.

关键词： Discrete-time systems Direction-of-arrival estimation control design Finance Europe Estimation Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

AImotion Challenge Results: a Framework for AirSim Autonomous Vehicles and Motion Replication

AImotion Challenge Results: a Framework for AirSim Autonomou...

引用

Computers and automation (CompAuto), International Conference on

作者： Bruno J. Souza Lucas C. de Assis Dominik Rößle Roberto Z. Freire Daniel Cremers Torsten Schön Munir Georges Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) Curitiba Brazil Control and Automation Eng. Department Pontifical Catholic University of Parana (PUCPR) Curitiba Brazil Technische Hochschule Ingolstadt AImotion Bavaria Institute Ingolstadt Germany Department of Informatics Technical University of Munich Munich Germany

ISBN: (纸本)9781665481953

The use of simulation environments is becoming more significant in the development of autonomous cars, as it allows for the simulation of high-risk situations while also being less expensive. In this paper, we presented a framework that allows the creation of an autonomous vehicle in the AirSim simulation environment and then transporting the simulated movements to the TurtleBot. To maintain the car in the correct direction, computer vision techniques such as object detection and lane detection were assumed. The vehicle's speed and steering are both determined by Proportional-Integral-Derivative (PID) controllers. A virtual personal assistant was developed employing natural language processing to allow the user to interact with the environment, providing movement instructions related to the vehicle's direction. Additionally, the conversion of the simulator movements for a robot was implemented to test the proposed system in a practical experiment. A comparison between the real position of the robot and the position of the vehicle in the simulated environment was considered in this study to evaluate the performance of the algorithms.

关键词： Computer vision Lane detection Robot kinematics Atmospheric modeling Computational modeling Virtual environments Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Robust Current control of Three-Phase Grid-Connected Converters by Using the ADRC Method 16

Robust Current Control of Three-Phase Grid-Connected Convert...

引用

16th Brazilian Power Electronics Conference, COBEP 2021

作者： Campos De Araujo, Diana Alves Moor Neto, Joao Amin Do Brasil, Thiago Americano Gouvea, Josiel Alves Lopes Zachi, Alessandro Rosa Electrical Engineering Graduate Program Centro Fed. de Educ. Tecn. Celso Suckow da Fonseca CEFET/RJ Rio de Janeiro Brazil Centro Fed. de Educ. Tecn. Celso Suckow da Fonseca CEFET/RJ Department of Electrical Engineering Rio de Janeiro Brazil Centro Fed. de Educ. Tecn. Celso Suckow da Fonseca CEFET/RJ Department of Control Systems and Automation Rio de Janeiro Brazil

ISBN: (纸本)9781665421294

This paper addresses the control design of a current mode control for a three-phase voltage source converter. A variant of the Active Disturbance Rejection control (ADRC) scheme is proposed for comparison with the classical inner control approach. The ADRC method has a straightforward design procedure and has well-known abilities for disturbance rejection and robustness to parametric uncertainties of the system. Theoretical studies are presented and simulation results are discussed by using EMTP-RV environment considering the system Synchronous Reference Frame control, whose modeling was extracted from the analysis performed in a classical refer-ence. © 2021 IEEE.

关键词： Electric current control

来源：评论

学校读者我要写书评

暂无评论

Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Liu, Yinqiu Wang, Jiacheng Lin, Yijing Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Ai, Bo Zhou, Haibo Kim, Dong In The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Shenzhen China The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China School of Electronic Science and Engineering Nanjing University Jiangsu Nanjing210093 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of Generative Artificial Intelligence (GenAI), demonstrating their versatility and efficacy across various applications. The ability to model complex data distributions and generate high-quality samples has made GDMs particularly effective in tasks such as image generation and reinforcement learning. Furthermore, their iterative nature, which involves a series of noise addition and denoising steps, is a powerful and unique approach to learning and generating data. This paper serves as a comprehensive tutorial on applying GDMs in network optimization tasks. We delve into the strengths of GDMs, emphasizing their wide applicability across various domains, such as vision, text, and audio generation. We detail how GDMs can be effectively harnessed to solve complex optimization problems inherent in networks. The paper first provides a basic background of GDMs and their applications in network optimization. This is followed by a series of case studies, showcasing the integration of GDMs with Deep Reinforcement Learning (DRL), incentive mechanism design, Semantic Communications (SemCom), Internet of Vehicles (IoV) networks, etc. These case studies underscore the practicality and efficacy of GDMs in real-world scenarios, offering insights into network design. We conclude with a discussion on potential future directions for GDM research and applications, providing major insights into how they can continue to shape the future of network optimization. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Using Artificial Neural Networks to Estimate the Equivalent Resistivity from typical Transmission Line Towers Grounding Arrangement in a Two-Layer Soil

Using Artificial Neural Networks to Estimate the Equivalent ...

引用

International Symposium on Lightning Protection (XII SIPDA)

作者： Raphael Batista João R. Souza Graduate Program in Automation and Control Engineering IFMG Betim MG Brazil Dept. of Electroeletronics and Computing CEFET-MG Alameda das Perdizes 61 Contagem MG Brazil

This paper presents a procedure to estimate a homogeneous equivalent resistivity for typical transmission line tower ground arrangements that are immersed in a stratified soil model. This technique is based on artificial neural network training due to a dataset developed in a numerical routine to compute grounding resistance. The results obtained from Levemberg-Marquadt algorithm and Bayesian regularization show good accuracy compared to the applied dataset and to the measurement data from a 230 kV transmission line, a practical case analyzed. We note medians lower than 5% and acceptable values of standard deviation for practical cases, which suggests that the proposed procedure can be used for real-world conditions.

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：