Anais do 14º Simpósio Brasileiro de Automação Inteligente最新文献

{"title":"SINGLE LAYER PERCEPTRONS NEURAL NETWORKS FOR ONLINE EIGENSTRUCTURE ASSIGNMENT IN MIMO SYSTEMS","authors":"B. Coelho, Daniel Trovao Simoes, J. V. F. Neto, Patricia H. Moraes Rego","doi":"10.17648/sbai-2019-111153","DOIUrl":"https://doi.org/10.17648/sbai-2019-111153","url":null,"abstract":": To improve the stability performance and the response form of MIMO systems, the control of the modes is relevant to impose the design specifications. A bioinspired method for online eigenstructure assignment for the design of multivariable control systems is presented in this paper. The method is based on artificial neural networks for the execution of the control law and for training the controller gains by state feedback. Aiming at online tuning of state space controllers, the gain matrix that satisfies all the design specifications, a proposal is presented to compute the gain matrices that best meet a given operating range of MIMO dynamic systems. The proposal is evaluated in a mathematical model that represents a fourth order RLC circuit with two input voltages and two controllable voltage levels.","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117093719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uma Metodologia Baseada em Modelo para Geração de Opções de Controle do Balão Intra-Aórtico","authors":"Mateus Costa Lucena, T. R. Melo, T. Cordeiro, Antônio Marcus Nogueira Lima, Idágene A. Cestari","doi":"10.17648/sbai-2019-111339","DOIUrl":"https://doi.org/10.17648/sbai-2019-111339","url":null,"abstract":"The intra-aortic balloon pump (IABP) is a mechanical heart assist device (MHAD), temporally applicable, used to increase blood flow in the arteries of the heart muscle (coronary arteries). The main control problem associated with the BIA is the choice of actuation times that maximize his operational performance. To evaluate the operational reliability of the BIA, control systems check performance indexes. The present work proposes a methodology based on 0D models to generate control recommendations, and also evaluates the association of pulsatility indexes in the quantification of BIA physiological performance. The results obtained suggest that PP, DP and EEP pulsatility indexes can be used to generate control recommendations in accordance with the IABP clinical objectives. Resumo: O balão intra-aórtico (BIA) é um dispositivo mecânico de assistência card́ıaca (DMAC), de aplicabilidade temporária, utilizado para aumentar o fluxo de sangue nas artérias do músculo card́ıaco (artérias coronárias). O principal problema de controle associado ao BIA é a escolha de tempos de atuação que maximizem o desempenho operacional do dispositivo. Para avaliar a corretude operacional do BIA, os sistemas de controle verificam ı́ndices de desempenho. O presente trabalho propõe uma metodologia baseada em modelos 0D para geração de opções de controle, e, avalia ainda, a associação de ı́ndices de pulsatilidade na quantificação de desempenho fisiológico relativa à utilização do BIA. Os resultados obtidos sugerem que os ı́ndices de pulsatilidade PP, DP e EEP podem ser utilizados para gerar opções de controle em compromisso com os objetivos cĺınicos do BIA.","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115840941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fuzzy Maneuvering Controller Optimization Using an Optimum Differential-Drive Mobile Robot Model","authors":"Thiago de A. Ushikoshi, L. L. Carneiro, P. Coutinho, T. Chagas, L. Schnitman","doi":"10.17648/sbai-2019-111495","DOIUrl":"https://doi.org/10.17648/sbai-2019-111495","url":null,"abstract":"This paper proposes a method for improving the performance of a fuzzy controller applied to a Differential-Drive Mobile Robot. From previously recorded data, the DDMR model is improved through Particle Swarm Optimization aiming to obtain a better representation of the real system. The PSO algorithm is also applied to adjust the fuzzy controller parameters so that trajectory tracking error is minimized. The manually adjusted controller settings are compared to the optimized’s in terms of Root Mean Square Error of trajectory tracking, control effort and acceleration. The latter is useful for protecting the robot from damage caused by abrupt variations. Numerical simulations show that the optimized model can describe better the real system behavior and the optimized controller can lead the robot dynamic model to track the given trajectory more accurately, with reduced control effort, and smoother velocity variation than the non-optimized controller.","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116171378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reprodutibilidade na Simulação de um Circuito Caótico","authors":"Thalita Emanuelle Nazaré, E. G. Nepomuceno","doi":"10.17648/sbai-2019-111356","DOIUrl":"https://doi.org/10.17648/sbai-2019-111356","url":null,"abstract":"","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115488698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Utilização da Biometria em Transportes Públicos","authors":"Carlos Matheus de Souza, Adan Lúcio Pereira, Mariana Gentilia Littig Krugel Magioni, Bruno Rocha Baggieri","doi":"10.17648/sbai-2019-111189","DOIUrl":"https://doi.org/10.17648/sbai-2019-111189","url":null,"abstract":"","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124451930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classificação de Falhas em Motor de Indução Utilizando Curvas Principais","authors":"Fernando Elias de Melo Borges, Letycia M. Borges, D. Ribeiro, A. Pinto, D. Ferreira","doi":"10.17648/sbai-2019-111208","DOIUrl":"https://doi.org/10.17648/sbai-2019-111208","url":null,"abstract":": Electric motors are very important machines in any industrial plant, due to your large range of uses and robustness. Evaluate the conditions of this machines is crucial to ensure the operation with security and quality. This paper presents a methodology of fault classification using vibration analysis, the vibration signals were measured by a 3-axis accelerometer linked to un Arduino microcontroller. The front bearing was evaluated in good conditions and in two failures situations in its races. The feature extraction was realized by Higher-Order Statistics using cumulants of 2nd and 4th orders with zero lag and the classification was made using Principal Curves. Principal Curves are obtained to each motor condition and realized the classification by measure of the distances of each event to the curve. Classification results were obtained with hits rates above 95%.","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124696097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Meta-Learning Applied to the Selection of the Classification Methods in Industrial Images","authors":"Luis Fernando Marin Sepulveda, A. Silva, J. O. Diniz","doi":"10.17648/sbai-2019-111375","DOIUrl":"https://doi.org/10.17648/sbai-2019-111375","url":null,"abstract":"In industrial production, control of quality of product and analysis of state of the staff in charge are important factors, nevertheless, the collection and analysis of data imply large amounts of time and may involve a risk to health of the staff in case of quality control, to deal with these tasks, image capturing and classification tools have been used, however, there is a challenge to identify the most appropriate classification method when taking into account the type of image being studied, the challenge is greater when it is necessary for a system to process different products with different classification objectives. This paper presents a methodology based on Meta-Learning and CNN for the identification of the appropriate methods of classification of industrial images. As an object of study images of hot-rolled steel strip, shear pad of wagon train, welds x-rays, aluminum wheel x-rays and human faces were used, obtaining 96% accuracy, 99.7% AUC and 96.5% Fmeasure.","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124746194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Avaliação do Impacto da Taxa de Amostragem na Localização de Faltas em Linhas de Transmissão Baseada em Ondas Viajantes","authors":"Guilherme Fraga, Vinicius Mariano Gonçalves, Wallace do Couto Boaventura","doi":"10.17648/sbai-2019-111474","DOIUrl":"https://doi.org/10.17648/sbai-2019-111474","url":null,"abstract":"The automatic fault localization in transmission lines (TL) plays a fundamental role for both the operation of energy systems and their operational safety, since the availability of TLs can be a critical issue. A successful technique for fault localization is based on the detection of traveling waves present in the voltage and current signals of the TL shortly after the fault event. Such characterization requires the use of acquisition equipment with high acquisition rate, usually high cost and specially developed. However, digital disturbance recorders (DDRs), which operate at low acquisition rates, are generally available in power substations. In this context, this work aims to analyze the impact of the acquisition rate on the quality of detection algorithms based on traveling waves. This is done by decimation / interpolation operation in order to vary the sampling rate to be used by the algorithm. Results of simulations and comparisons between classic techniques and the proposed technique based on traveling waves are presented for validation purposes. Resumo: A localização automática de faltas em linhas de transmissão (LT) desempenha um papel fundamental para a operação dos sistemas de energia e sua segurança operacional, considerando que a disponibilidade de LTs é cŕıtica. Uma técnica bem-sucedida para a localização de faltas baseia-se na detecção das ondas viajantes presentes na tensão/corrente da LT após a falta. Tal caracterização demanda equipamentos de alta taxa de aquisição e custo, especialmente desenvolvidos. Entretanto, os registradores digitais de perturbação – RDPs, que operam em baixas taxas de aquisição, estão geralmente dispońıveis nas subestações de energia. Neste contexto, este trabalho tem por objetivo analisar o impacto da taxa de aquisição na qualidade de algoritmos de detecção baseados em ondas viajantes. Isto é feito através de operação de dizimação/interpolação de modo a variar a frequência de amostragem (FA) a ser utilizada pelo algoritmo. São apresentados resultados de simulações e comparações entre técnicas clássicas e a técnica proposta.","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122169993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Caracterização do Consumo de Água Residencial utilizando Redes Neurais Artificiais","authors":"Lucas Nunes Monteiro, Caique Vendemiatti, Alexandre da Silva Simões, I. Diniz, F. P. Marafão","doi":"10.17648/sbai-2019-111471","DOIUrl":"https://doi.org/10.17648/sbai-2019-111471","url":null,"abstract":": Water leaks in residential pipes are usually noticed only after 30 days, when the consumer receives the bill regarding the use of water and realizes that there was an atypical consumption on site. In such scenario, this article proposes the use of an artificial neural network to propose a methodology for identifying possible water leaks in residential buildings, thus allowing a better understanding and awareness of water consumption in the property. The proposed water monitoring system is based on four main stages: data acquisition; exploration and manipulation of data; data characterization and classification. Through the proposed system, from the classification / forecast of one week, it was possible to identify dates with abnormal consumption, which could be caused by excess water consumption or failures in water lines. dos dados e classificação. Por meio do sistema proposto, a partir da classificação/previsão de uma semana, foi possível identificar datas com consumos anormais, podendo ser causados por excesso de consumo de água ou avarias relacionadas a vazamentos.","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125391705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Controlador MPPT baseado em Lógica Fuzzy Aplicado a um Sistema Fotovoltaico Conectado à uma Rede","authors":"Arthur Caio Vargas e Pinto, Tiago Henrique Santa Maria, J. G. Oliveira, Andre L. M. Marcato, E. Aguiar","doi":"10.17648/sbai-2019-111205","DOIUrl":"https://doi.org/10.17648/sbai-2019-111205","url":null,"abstract":": Among the renewable energies sources, the solar have excelled from the others because its fast growning and global accept. But, photovoltaic systems have low efficiency and the cause is related with various variables, as temperature, irradiation, angle of the panels, and others. The implementation and operation of photovoltaic cells requires few controls one of them is, tracking the point of maximum potency of the panel (MPPT). This paper proposes an MPPT algorithm based on Fuzzy Logic. Fuzzy algorithms has its advantages like fast responses not dependent on variations in the system and no mathematical equations involved. The following simulations show us the fuzzy controller works efficiently. The proposed scheme was made using Matlab/Simulink. de geradores fotovoltaicos requerem a utiliza¸c˜ao de um sistema Seguidor de M´axima Transferˆencia de Potˆencia - MPPT. Este trabalho prop˜oe o desenvolvimento de um algoritmo MPPT baseado em l´ogica fuzzy, capaz de fazer com que o sistema opere no ponto de m´axima potˆencia mesmo sob condi¸c˜oes variadas de trabalho, aumentando a eficiˆencia. Um algoritmo fuzzy tem como vantagem a r´apida resposta `a varia¸c˜oes nas condi¸c˜oes do sistema e a n˜ao necessidade de modelagem matem´atica do sistema, como ocorre em outros m´etodos. Os resultados das simula¸c˜oes indicam que o controlador fuzzy opera de forma eficiente na manuten¸c˜ao da gera¸c˜ao da m´axima potˆencia pelo sistema. O sistema proposto foi criado e analisado utilizando a ferramenta Matlab/Simulink.","PeriodicalId":130927,"journal":{"name":"Anais do 14º Simpósio Brasileiro de Automação Inteligente","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125546686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}