EMC - Escola de Engenharia Elétrica, Mecânica e da Computação
URI Permanente desta comunidade
Navegar
Navegando EMC - Escola de Engenharia Elétrica, Mecânica e da Computação por Por Unidade Acadêmica "Escola de Engenharia Elétrica, Mecânica e de Computação - EMC (RMG)"
Agora exibindo 1 - 8 de 8
Resultados por página
Opções de Ordenação
Item Modelagem e implementação de uma planta didática de manufatura robótica inspirada em planejamento automático(Universidade Federal de Goiás, 2023-06-30) Alves, Weslley da Silva; Fonseca, João Paulo da Silva; http://lattes.cnpq.br/5217261758266411; Fonseca, João Paulo da Silva; Tavares, José Jean Paul Zanlucchi de Souza; Soares, Anderson da SilvaCurrent manufacturing systems have been undergoing significant technological advancements, particularly in the field of production planning and automation. The Fourth Industrial Revolution, or Industry 4.0, has already begun to enable technological innovations across various domains, especially in the manufacturing and services industries. There has been a noticeable surge in research on artificial intelligence techniques involving manufacturers seeking efficiency and speed. To achieve 'intelligent' behavior, it is inevitable to implement techniques for automated problem-solving, enabling some decision-making by the equipment and devices themselves. Automated planning, also known as 'automated planning' or 'AI Planning' in English, defines a specific type of state transition problem in which the goal is to find an admissible sequence of actions to bring the system from a certain initial state to a desired final state. The use of automated planning applied to manufacturing processes is gaining prominence in the academic sphere due to the potential to expand the use of techniques in real-world applications in modern industry. This work aims to primarily analyze data from the integration of automated planning solutions into real systems and describe a practical example based on a didactic plant that simulates a production line in a factory composed of individual cells. For the project's implementation, a programmable logic controller (PLC) was used as a model of real systems used in industrial automation, and the assembly and description steps of each station are presented. The language used for modeling the planning domain was the 'Planning Domain Definition Language' (PDDL), through the online platform 'PDDL Editor,' which is part of a set of online tools for AI Planning called 'Planning.Domains.' The modeling was distributed across five stations to facilitate solving the proposed problem for each station, thus generating five solution plans, one for each station. The results achieved from the domain modeling method in manufacturing using an online automated planning tool included the generation of solution plans for the proposed scenarios and practical implementation on the didactic bench using the 'Sequential Function Chart' (SFC) programming language. The proposed approach was compared with the classical approach, which concentrated programming logic on the PLC and used the Ladder programming language, highlighting the potential of using automated planning for Industry 4.0-related topics.Item Contribuições à modelagem, controle e integração de dispositivos fotovoltaicos a sistemas elétricos de potência(Universidade Federal de Goiás, 2023-11-03) Corrêa, Henrique Pires; Vieira, Flávio Henrique Teles; http://lattes.cnpq.br/0920629723928382; Vieira, Flávio Henrique Teles; Palhares, Reinaldo Martinez; Kopcak, Igor; Negrete, Lina Paola Garcés; Belchior , Fernando NunesThe prominence attained by photovoltaic (PV) power generation among the various available renewable energy resources has led to the need of analyzing and engineering such technology at a wide range of implementation scales, beginning from the electrical characteristics of PV cells, passing through the local control of PV generation systems, up to the massive integration of PV resources to wider electrical power systems, such as the distribution grid. This thesis is divided into three parts, each of which presents novel contributions to the study of PV systems in the three aforementioned scales of analysis. In the first part, analytical modeling of PV cell current-voltage (I-V) characteristics by means of explicit closed-form equations is addressed. A new piecewise quadratic model is proposed, which is shown to perform either better or comparably, for different solar cells, to state-of-the-art models in terms of accuracy. Two methods are established for computing the model parameters: the first one is analytical and only requires datasheet information, whereas the second one uses linear-complexity optimization with respect to I-V samples in order to further improve accuracy. In the second part, the problem of maximum power point tracking (MPPT) in two-stage PV systems is considered. First, a new hybrid MPPT method which uses direct duty cycle control for enhanced tracking efficiency is developed for grid-tied systems. Then, an analytical MPPT approach for single-phase off-grid variable-voltage systems is presented and subsequently generalized to consider current harmonics and three-phase loads. Both proposed MPPT methods are shown, by means of simulation, to perform better than existing methods with similar implementation complexities. In the third part, voltage control of distribution systems with photovoltaic penetration by means of PV inverter reactive power support is studied. Three novel decentralized methods for controlling the inverter reactive power setpoints are proposed. The first method considers voltage measurements are available at each PV inverter and consists in the heuristic specification of a cooperative decentralized Markov decision process (MDP), whose offline solution yields voltage control policies to be carried out by the grid zone controllers. On the other hand, the second method assumes voltage measurement and computational resources are scarce and establishes a decentralized strategy which only uses two voltage measurements per control zone and is directly compatible with droop-type controls usually found in PV inverters. At last, a third method is presented which combines cooperative MDP, droop control and a switching mechanism for achieving a compromise between voltage regulation and reduction of active power losses. All methods are compared to similar existing approaches, via simulations with real irradiance profiles in a large distribution grid, yielding favorable performances.Item Sistema de comunicação alternativa para pessoas com distúrbios neuromotores severos usando redes neurais artificiais(Universidade Federal de Goiás, 2023-12-15) Floriano, Carolina Souza; Silva, Adson Rocha; http://lattes.cnpq.br/4116708456419800; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Gomide, Renato de Sousa; Rocha, Adson SilvaCommunication difficulties are frequent for many people with severe motor disabilities, making it difficult for them to interact with their families, caregivers and society in general. Augmentative and Alternative Communication (AAC) then aims to compensate for the communication deficit of these people, providing the individual with a better quality of life. However, these individuals with severe neuromotor disorders who have severe movement restrictions find great challenges in the use of several current assistive technologies. In this context, the objective of this research is to present an Alternative Communication System based on Artificial Neural Networks with a user-centered approach and their needs, for use by this public. The input and signal processing are carried out by reading facial landmark points, using the MediaPipe FaceMesh library. The development of the gesture/facial expression classifier is performed through the implementation and comparison of two different models: a Convolutional Neural Network (CNN) model and a Recurrent Neural Network model using Long Short-Term Memory (LSTM) units and dense layers. Dynamic challenges were implemented to conduct a more in-depth analysis of the models’ performance in various contexts, varying parameters such as the quantity of samples and the inclusion of similar gestures. Real-time overall results indicate a consistent performance of the proposed system, suggesting that, in both approaches, the Convolutional Neural Network (CNN) stands out significantly compared to the Long Short-Term Memory Recurrent Neural Network (LSTM) in gesture recognition.Item Análise da aplicação de revestimento duro em aço carbono com o processo FCAW com e sem injeção de arame não energizado(Universidade Federal de Goiás, 2023-08-17) Marques, Vitória Ferreira de Oliveira; Souza, Daniel; http://lattes.cnpq.br/2132578584168482; Ferraresi, Valtair Antonio; http://lattes.cnpq.br/0727420392683160; Ferraresi, Valtair Antonio; Souza, Daniel; Lima, Aldemi Coelho; Contin, AndreBrazil is the world’s largest producer and exporter of sugar. One of the factors that directly impact the productivity of the sugarcane and alcohol industry is the maintenance of many equipment pieces that are subject to wear mechanisms. The application of hardfacing aims to reduce the wear of these equipment pieces and, consequently, increase their lifespan, reduce downtime, and production costs. To ensure the quality of the hardfacing, a proper selection of the deposited material and process parameters must be made. The objective of this study is to evaluate the resistance to abrasive wear of hardfacings using the FCAW (Flux-Cored Arc Welding) process, both self-shielded and with the addition of non-energized wire, while also assessing two interpass temperatures between weld beads (50°C and 200°C). The goal is to improve wear resistance and reduce the occurrence of solidification cracks. Three types of consumables (FeCrC, FeCrC+Nb, and FeCrC+Ti) with a diameter of 1.6 mm were used. FeCrC was used for the energized wire, while FeCrC+Nb and FeCrC+Ti were used for the non-energized wire. The base metal used was SAE 1045. Test specimens were constructed for wear evaluation in the laboratory using a Rubber Wheel Abrasion Tester in accordance with ASTM G65-91 standard. Wear evaluation was performed based on mass loss. Hardness and microstructure analyses of the coatings were also carried out. The best results for resistance to abrasive wear were obtained with the combination of FeCrC and FeCrC+Ti (nonenergized wire). It showed better performance at both interpass temperatures compared to other wire combinations. In all combinations, the presence of M7C3 carbides was observed. The combination of FeCrC and FeCrC+Ti showed the presence of titanium carbides (TiC), while the combination of FeCrC andFeCrC+Nb exhibited niobium carbides (NbC). All combinations with an interpass temperature of 200°C demonstrated higher wear resistance compared to those with an interpass temperature of 50°C.Item Tratamento de superfície em substratos de aço da indústria farmacêutica via laser de CO2(Universidade Federal de Goiás, 2023-08-31) Martins, André Carvalho; Cunha, Daniel Fernandes da; http://lattes.cnpq.br/7364532451621106; Contin, André; http://lattes.cnpq.br/5450987692265022; Contin, André; Bertholdi, Jonas; Ferreira Filho, Demóstenes; Cunha, Daniel Fernandes daAISI 304 stainless steels play a crucial role in the pharmaceutical industry due to their resistance to chemical reactivity. However, their wear resistance is limited in high-temperature and highpressure environments. Laser treatment emerges as a promising approach to enhance their properties. In this study, a low-cost 100 W CO2 laser is used for the surface treatment of AISI 304 steels, with the addition of carbon black powder. The results showed a significant increase in surface hardness after laser treatment compared to the untreated substrate. EDS analyses revealed the presence of carbon on the surface of the substrates. In addition to the increased surface hardness, the coefficient of friction of the laser-treated samples was reduced when compared to the reference substrate. Ultimately, carbon black acted as a photoabsorbing material for radiation, a source of carbon for increasing surface hardness, and as a solid lubricant. These results demonstrate the viability of using a low-cost CO2 laser as an efficient, versatile, and rapid alternative to improve the properties of materials employed in the pharmaceutical industry.Item Avaliação de resistência mecânica e análise de forma geométrica de elementos de fixação por rosca fabricados através de manufatura aditiva(Universidade Federal de Goiás, 2023-08-31) Prado, Thiago Menezes do; Viana, Rhander; http://lattes.cnpq.br/5270141650315822; Cunha, Daniel Fernandes da; http://lattes.cnpq.br/7364532451621106; Cunha, Daniel Fernandes da; Ziberov, Maksyn; Medeiros, Everton Coelho de; Viana, RhanderThe work addresses the mechanical tensile strength of internal fillets in specimens manufactured in PLA and ABS from additive manufacturing by Fused Deposition Modelling (FDM). Test specimens measuring 30 x 30 x 20 mm were manufactured in PLA and ABS with a 3D printer model Ender 3 V2. The through hole of the specimens has measurements M12 x 1.75. Varied parameters used were: infill (p), number of walls (w) and height of the layers (h), to enable the understanding of how the mechanical resistance of the material is affected. Thus, the present study aimed to compare the mechanical resistance of PLA and ABS polymers through tensile tests, defining which material has greater resistance and with low production cost from 3D printing. The tensile tests were carried out using a tensile machine with a maximum capacity of 600 kN, which gradually applied tension to the specimens until the material fractured or ruptured. For the result analysis, relation of resistance from the specimens was verified graphically (force x time) and statistically (ANOVA), judging the influence of variables in individual and collective content in the achieved results. Pieces printed in PLA showed a higher quality of mechanical resistance compared to those made from ABS material when graphic results obtained were verified. As a statistical result, the ANOVA analysis identified the factor with greatest influence on tests were infill (P%), being preponderant both individually and collectively, when analyzing its influence with other two variables.Item Minimização da ondulação de torque em motores a relutância variável por meio de correntes de fase de referência otimizadas por algoritmo genético(Universidade Federal de Goiás, 2023-12-18) Soares, Israel Rodrigues; Paula, Geyverson Teixeira de; http://lattes.cnpq.br/0140145167826333; Paula, Geyverson Teixeira de; Oliveira, Eduardo Sylvestre Lopes de; Almeida, Thales Eugenio Portes deThis work proposes an innovative control strategy for the Switched Reluctance Motor with the aim of minimizing torque ripple. The strategy is based on an algorithm for generating current profiles that prioritize the smooth commutation mode of the asymmetric half-bridge converter. This algorithm employs genetic algorithms to calculate these profiles through simulations in a finite element model developed based on a 6x4 Switched Reluctance Motor from the Laboratório de Ensaios de Pequenos Motores at the Universidade Federal de Goiás. To enhance the adaptability of the proposed control, the addition of a compensation derived from torque error to these profiles has been suggested. Simulations compared the Proposed Control with Direct Instantaneous Torque Control and the Proposed Control without the addition of compensation under various operating conditions. The results highlight significant average reductions in metrics used to evaluate torque ripple. In the Torque Ripple metric, there was an average reduction of 16.02% compared to Direct Instantaneous Torque Control and 13.14% compared to the Proposed Control without compensation. As for the Torque Ripple Factor metric, this reduction was 15.34% and 15.96%, respectively. The study concludes by affirming the good performance of the generated current profiles, demonstrating that the inclusion of compensation derived from torque error in these profiles was crucial for the low levels of torque ripple achieved by the proposed control technique.Item Aplicação da transformada de Hilbert-Huang e da seleção paraconsistente de características no campo da entomologia agrícola: uma abordagem para identificação e estimativa de densidade de cigarras em lavouras cafeeiras(Universidade Federal de Goiás, 2023-12-01) Souza, Uender Barbosa de; Escola, João Paulo Lemos; http://lattes.cnpq.br/5894769490673984; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Vieira, Flávio Henrique Teles; Lemos, Rodrigo Pinto; Escola, João Paulo Lemos; Maccagnan, Douglas Henrique BotturaThe sounds emitted by various insect species carry specific and reliable acoustic characteristics. For this reason, acoustic identification of insects has been widely investigated by the scientific community in the field of pattern recognition. In Brazil, the cicada species Quesada gigas is considered a pest in coffee crops due to its sap-feeding habits, which can cause losses to farmers during intense attacks. Given this scenario, and considering the fact that the most striking characteristic of cicadas is sound emission for reproductive purposes, this work proposes a system designed to assist in the management of pest insects in coffee crops. Specifically, this system aims to detect the presence of cicadas or estimate their density through acoustic signals. The approach innovatively combines the extraction and analysis/selection of sound features through the Hilbert-Huang Transform (HHT) and Paraconsistent Feature Engineering, two emerging methods of growing interest in the scientific community. A detailed study was conducted on the influence of eight stopping criteria for the Empirical Mode Decomposition, the first step of HHT, considering variations of parameters, temporality, signal sampling, and also the encoding of these signals in two formats. The first defines vectors by the energies of the Intrinsic Mode Functions (IMFs) in order of extraction, while the second distributes the energies of the IMFs according to the 25 frequency bands of the Bark Scale. Additionally, the dimensional variation of the vectors was analyzed. The experiments allowed determining low computational cost configurations, showcasing the efficacy of the proposed system, with models based on Support Vector Machines achieving accuracies above 98% in both identification and density estimation of cicadas. Thus, this document details the theoretical foundations, design, development of the system, discussions about possibilities for its practical application, and an initial analysis of a developed application for smartphones. This proposal has the potential to encourage the reuse of old electronic equipment, promoting sustainable and economically viable practices.