Engenharias

Permanent URI for this community

https://ri.ucsal.br/handle/123456730/304

Browse

Now showing 1 - 20 of 30

Adaptação do WGAN ao processo estocástico
(Universidade Católica do Salvador, 2020-09-30) Aquino, Rafael Rembrandt; Wyzykowski, André Brasil Vieira; http://lattes.cnpq.br/; Pereira, Mário Jorge Pereira; http://lattes.cnpq.br/; Reis, Marcelo Índio dos; http://lattes.cnpq.br/
Within different areas of knowledge, data (different types of information) are valuable and their analysis is even more valuable. Then, associating the area of artificial intelligence, a new trend is observed, the generation of synthetic data to fill the lack of data. Therefore, analyzing current contexts, this work aims to demonstrate the use of techniques based on random events to optimize the result in the execution of algorithms based on GAN (Generative adversarial networks) and through a validation through the calculating the FID (Frechet Inception Distance) it was possible to analyze the results, determining the quality of the data generated by the proposed algorithm compared to WGAN.
Análise experimental entre as técnicas TDD e Test-Last no processo de manutenção corretiva de software
(Universidade Católica do Salvador, 2019-06-18) Barros, Gabryela Santana; Pereira Junior, Lielson Ribeiro; Reis, Marcelo Indio dos; lattes.cnpq.br; Wyzykowski, André Brasil Vieira; lattes.cnpq.br; Wyzykowski, Andre Brasil Vieira; lattes.cnpq.br; Reis, Marcelo Indio dos; lattes.cnpq.br; Neiva, Antonio Claudio Pedreira; lattes.cnpq.br
In the context of software development, It is possible to find any approaches. The test last development technique (TLD) is the most common process in software building practice. The test-driven development (TDD) is a technique in which tests are applied before the implementation of a feature. Due to software process improvement and with the influence of the agile movement, the TDD gained notoriety and nowadays is very widespread in the community. It is well known about benefits of software development, but there are few sources of information about corrective maintenance. This work was done in three steps. The first step had the objective of creating a dataset of codes made using TDD and TLD aprroach. For the second step a total of ten valid codes were selected during this phase, five codebases using TLD approach and five codebases using TDD approach. The third step using code that were create on previous phase, were submitted for maintenance, where possible implmentation errors should be detected. The objective of this research is, through experiments with students of various levels in the area of computing, is to check the efficiency of TDD in software maintenance compared to TLD. During development session, It is possible to notice that code built with TDD has less size and more quality comparing to TLD. In maintenance, it was observed that the codes built with TDD, had a larger number of bugs solved than the codes built with TLD. However, results of the time-saving for fixing bugs were inconclusive.
Avaliação do desempenho econômico na implantação da recompressão mecânica de vapor em uma coluna de destilação para a separação de aldeídos
(Universidade Católica do Salvador, 2021-12-20) Jucene, Maria Eduarda Araújo; Rios, Agostinho Souza; http://lattes.cnpq.br/; Conceição, Wagner Almeida Mônaco; http://lattes.cnpq.br/; Neves, Sérgio Bello; http://lattes.cnpq.br/
The high rate of energy consumption arising from the distillation operations is one of the great motivators of this project, so using methods that introduce cleaner and more conscientious engineering is the main objective. The object of study for this work is a distillation column implanted in the Industrial Pole in the municipality of Camaçari-BA, with the purpose of obtaining a top current rich in isobutyraldehyde and a bottom current in n-butyraldehyde, this column demands a high consumption of steam, as a consequence of a high reflux ratio to perform the required separation. The scheme adopted to make this column technically viable is a mechanical recompression of the top steam, which is a process that aims to return the energy once initially deposited in the column. For this solution, a compressor is installed at the top of the column, which at temperature and pressure levels allow the transfer of condensing heat to the column boiler, avoiding being rejected in the cooling tower. This article presents the computer simulation of two systems, one representing the real operational data of the process and the other including the coupling of mechanical steam recompression, where a comparative analysis was performed, in order to check if there is an economic feasibility in the process.
Bioplástico: alternativa viável e sustentável ao plástico convencional
(Universidade Católica do Salvador, 2019-12-13) Azevedo, Larissa Guimarães; Neves, Sérgio Bello; http://lattes.cnpq.br/; Conceição, Wagner Almeida Mônaco; http://lattes.cnpq.br/; Hayashi, Júlio César; http://lattes.cnpq.br/
Conventional plastics are macromolecular polymers, synthesized from fossil raw material, petroleum. It is part of the third generation of the petrochemical chain and from the outset has many benefits to society, mainly due to its high resistance. This feature becomes unfavorable when there is insufficient solid waste management, making it one of the main pollutants of fauna and flora with proven toxicity, as well as representing economic and potential waste. The need for innovation in the polymer area has been creating space for the conscious development of new materials, such as bioplastics, derived from renewable raw materials, presenting biodegradability and boasting a good marketing perspective although it costs, on average, twice the conventional plastic because it is a new technology of smaller scale. Brazil, which is the fourth largest producer of plastics moreover, recycles less than 5%, would have lower production costs of bioplastics than countries in Europe, the United States and China. The article aims to present the main bioplastics as alternatives to petrochemicals, in order to support the structuring of this new industry and perform the role of environmental awareness agent.
Desenvolvimento de um aplicativo gamificado para o ensino de matemática básica para crianças com síndrome de Down: uma abordagem utilizando elementos de gamificação como estratégia educacional
(UCSal - Universidade Católica do Salvador, 2023-06-27) Conceição, Natália de Lima; Santos, Roberto Nascimento dos; Sena, Sara Oliveira Lima; Gabriel, Tatiane Ximenes de Oliveira; Gomes, Thiago de Melo Santos; Borges, Fernando Cezar Reis (Orient.)
Esse Trabalho tem como objetivo apresentar um aplicativo gamificado para o ensino de matemática básica para crianças com Síndrome de Down com foco na faixa etária de 7 a 15 anos. O protótipo do aplicativo foi validado junto ao público alvo, a fim de perceber a receptividade desse público com a interface projetada. O projeto foi desenvolvido a partir da ideia da gamificação como mecanismo para o aprendizado da matemática com base nas contribuições do artigo "A identificação, análise e priorização de requisitos de aplicações gamificadas para o ensino de crianças com Síndrome de Down", por Souza et al. [36] que afirma que a gamificação é uma possibilidade viável para auxiliar o ensino das crianças com Síndrome de Down. O trabalho aborda ainda a importância da matemática unificada com a gamificação, como uma maneira de tornar o aprendizado mais envolvente e eficiente para o público alvo da pesquisa. Ficou claro, ao final do experimento, que o aplicativo de gamificação ainda tem alguns tópicos para evoluir, mas sua aplicação para apresentar melhorias no desenvolvimento da disciplina de matemática para crianças com Síndrome de Down demonstrou ser possível.
Desenvolvimento de um sistema IOT voltado à acessibilidade na mobilidade urbana
(Universidade Católica do Salvador, 2019-06-18) Cruz, Carlos Daniel Santana; Wyzykowski, André Brasil Vieira; lattes.cnpq.br; Wyzykowski, André Brasil Vieira; lattes.cnpq.br; Reis, Marcelo Indio dos; lattes.cnpq.br; Pereira, Mario Jorge; lattes.cnpq.br
In Brazil, until the 2010 year, there were about 11 million people with some visual impairment. However, even with this significant quantity of people, and despite the existence of some urban mobility policies and laws related to accessibility, some aspects of their daily lives still constitute a problem. Among these problems is the lack of accessibility in public transport. Based on the mentioned problem, this work aimed to propose a system composed of an embedded IOT device, together with a web application and an application for mobile devices, all with the purpose of contributing to the improvement in accessibility and urban mobility, more specifically regarding to the public transport modality, consequently contributing to a more autonomous and independent life to people with some impairment. First, a bibliographic review was carried out based on the themes related to the work; then, a Requirements analysis was made for the initial functionalities that the system would have; finally, are described the steps taken in the development of the parts that compose the system, along with some problems encountered, and how these problems were worked out. The developed system, even being a first experimental version, made it possible for a visually impaired person to access estimated distances between their location and a specific vehicle’s location, and in a controlled experiment, enabling the vehicle to be identified by the person. Due to this, with the conclusion of this work, it was planned for future projects, among other characteristics, the addition of functionalities, in order to offer to the user a greater range of information along a bus trip.
Detecção de catarata por meio de imagens utilizando redes neurais convolucionais
(Universidade Católica do Salvador, 2020-12-11) Carneiro, Hugo Vinícius; Santos, Lucas Pereira; Wyzykowski, André Brasil Vieira; http://lattes.cnpq.br/; Jesus, Arnaldo Bispo de; http://lattes.cnpq.br/; Assis, Semiramis Ribeiro de; http://lattes.cnpq.br/
Cataract is one of the diseases of the eyeball that generates the most blindness in the world. The rapid detection of this disease, close to the appropriate treatment, contributes to the improvement of the patients’ quality of life. This work uses convolutional neural networks to train three sets of data containing images of different patients, in order to classify cataract patients and non-carriers. For this, a convolutional neural network vgg19 had its architecture modified and improved. The most successful results used by the network, was an accuracy of 100 %.
Detecção de Covid-19 em imagens radiológicas torácicas através da rede neural convolucional (RNC)
(Universidade Católica do Salvador, 2020-12-11) Santana, Saulo de Andrade; Wyzykowski, André Brasil Vieira; http://lattes.cnpq.br/; Jesus, Arnaldo Bispo de; http://lattes.cnpq.br/; Borges, Fernando Cezar Reis; http://lattes.cnpq.br/
The new Covid-19 pandemic, the new coronavirus (SARS-CoV-2), has caused many problems in several areas of society. Among these problems, the high number of tests carried out, and the lack of tests, especially in small cities, stands out efficiently. Consid- ering this insufficient resource in the identification of Covid-19, the objective of this work was to propose a solution, in an experimental study, to enable the detection of the new virus using the images of chest radiological medical examinations, which have facilitators in their realization, such as cost and availability, with the help of an Artificial Intelligence, more specifically the Convolutional Neural Network (RNC), which they are usually used to analyze images. The work consisted of its own architecture and a set of 16,500 im- ages separated into 3 classes (Normal, Covid-19 and Pneumonia), and the results of the RNC were analyzed and took place on the accuracy of the network algorithms in image recognition disorders, which is higher than 80 %. The technique proved to be promising in meeting this demand, in an experimental context. Therefore, it can be indicated as a complementary instrument in medical diagnosis in the health system for its efficacy and effectiveness, in addition to the benefits and ease for its implementation, however more tests are carried out, with a set of wide variables.
e-Coach: um sistema de recomendação de equipes e personagens de league of legends utilizando redes neurais multicamadas
(Universidade Católica do Salvador, 2019-06-18) Gonçalves, Danilo Silva; Wyzykowski, André Brasil Vieira; lattes.cnpq.br; Wyzykowski, André Brasil Vieira; lattes.cnpq.br; Reis, Marcelo Indio dos; lattes.cnpq.br; Aquino, Pamela Arielle Brito de; lattes.cnpq.br
The mode of electronic sports has been increasingly present in society, crowding stadiums in different parts of the world and conquering more and more supporters by where their events take place. Between investment and millionaire awards, a career as a cyber athlete has become a goal of young people in the gamer community, as well as encouraging other companies in the area. In this sense, this study demonstrates the implementation of an algorithm applying Multi Layer Perceptron networks, using as a database the results of ranked matches of League of Legends. In addition, it explains the execution of experiments with players in real matches using the algorithm and comparing them to matches without using the algorithm. Thus, making possible the realization of the prediction of which team and characters that best fit for the match in obtaining victory.
Estudo da viabilidade técnico- econômica para instalação de uma usina eólica na Bahia
(Universidade Católica do Salvador, 2020-12-17) Miranda, Vitória Rafaela Matos; Mustafá, George de Souza; http://lattes.cnpq.br/; Conceição, Wagner Almeida Monaco; http://lattes.cnpq.br/; Neves, Sérgio Bello; http://lattes.cnpq.br/
This Course Completion work aims to show the entire analysis made of a preliminary study of the technical and economic feasibility for installing a wind farm in Bahia. The main points related to the studies carried out will be demonstrated: Market, to identify which are the perspectives of consumption / market with the installation of the industry; Location, based on analysis of some criteria, will define the best location in terms of cost / benefit; Technical study that will select the main equipment necessary for the operation of the plant and its technical specifications and the Economic study that will be responsible for analyzing the economic viability of the business.
Estudo de caso sobre o uso da notação BPMN no mapeamento do processo de baixa de atividades complementares na UCSAL
(Universidade Católica do Salvador, 2020-06-29) Oliveira, Jeferson Sunderlande de; Borges, Fernando Cezar Reis; http://lattes.cnpq.br/; Wyzykowski, André Brasil Vieira; http://lattes.cnpq.br/; Melo, Osvaldo Requião; http://lattes.cnpq.br/
To demonstrate the benefits that the use of BPM can provide for a higher education institution, a case study was carried out to assess whether the BPMN notation is applicableand whether it has benefits in mapping the process of writing off complementary activities in Catholic University of Salvador (UCSAL) and, with this, point out the positive impact of the Business Process Management (BPM) approach. Therefore, it was necessary to map the initial state of the process of writing off complementary activities - AS IS at the Catholic University of Salvador, to identify improvements to be implemented, to model the new TO BE procedure, and to create manuals to assist and standardize the modeled actions. Thus, a research was carried out with a qualitative approach to the problem, explanatory as to the purposes and with the procedure of the case study. Therefore, it was found that the reduction in the number of activities in the process of writing off complementary activities, attenuation from five to two actors in the process, and the standardization of procedures in the process. It then confirms that the BPMN notation assists in strategic decisions and collaborates in identifying the reality that presents itself with the business process and, through the analysis of the mapped process, it is possible to define the improvements to be applied.
Estudo sobre a dinâmica de fluidos computacional
(Universidade Católica do Salvador, 2021-06-17) Cunha Júnior, Antonio Alves da; Conceição, Wagner Almeida Mônaco; http://lattes.cnpq.br/; Lima, Paula Gois de; http://lattes.cnpq.br/; Neves, Sérgio Bello; http://lattes.cnpq.br/
Computational fluid dynamics, or CFD, is a field that deals with the numerical simulation of fluid flows, heat transfer and related phenomena, being able to calculate how operating conditions - temperature, pressure and transport properties - in three-dimensional or two-dimensional space. In this way, there is a possibility of verifying problems that a traditional simulation cannot map because it works with average parameters. This study aims to explore the CFD and the equations involved, with a demonstration and a comparison between the k-epsilon model and the SST (shear stress transport turbulence) using the ANSYS-CFD (FLUENT) tool - student license end to a mixing Tee where enter a hot fluid (water) at a temperature of 363.15 K and a velocity of 3 m / s and a cold fluid (water) at a temperature of 283.15 K and a velocity of 5 m / s thus doing a study on the behavior of the mixture. To evaluate the proposed solution, a comparison of temperature and velocity parameters was performed for each model and for each change made to the geometry. It was found that the k-e and SST model converged with a criterion of 10e-6, the two models well represent the water flow along the mixing Tee, although the SST model better represents the velocity vectors along the pipeline, despite from this the two models demonstrated confidence in the temperature variation and the fluid displacement through the mixer. The worlds made on the geometry have a satisfactory answer, thus making sure that the software is an interesting tool to perform simulations involving fluid flow.
Uma ferramenta multicritérios de priorização de requisitos baseada na técnica Analytic Hierarchy Process
(Universidade Católica do Salvador, 2020-06-26) Pergentino, Jessica das Neves; Reis, Marcelo Indio dos; http://lattes.cnpq.br/; Reis, Marcelo Indio dos; http://lattes.cnpq.br/; Wyzykowski, André Brasil Vieira; http://lattes.cnpq.br/; Borges, Fernando Cezar Reis; http://lattes.cnpq.br/
Over time, companies and businesses have constantly evolved, which makes systems and the way to develop software evolve together, becoming increasingly interactive the way to create products. Thus, it is important to have a consistent requirements prioritization phase, which takes into account the stakeholders requirements and development conditions. Doing good prioritization can define whether product development will be successful or not. The requirements prioritization system presented in this paper aims to assist decision makers in the management and prioritization of functional requirements of their projects., taking into account the prioritization considerations. This system will make it possible to use the requirements prioritization technique Analytic Hierarchy Process based on multicriteria in an automated way, facilitating the use of the technique. For this, it was necessary to make a selection of the criteria, through a study in the literature and interviews with three specialists in the area of requirements engineering. For the construction of the tool, an analysis of the domain was made, followed by the survey of the functional requirements and the elaboration of the documentation. To validate the proposed solution, a case study was carried out in a project of the software factory of the Catholic University of Salvador, the case study had four phases, where the first was the identification of the participants’ profile, the second was the prioritization of requirements using an auxiliary spreadsheet, in the sequence, the participants carried out the prioritization using the tool described in this paper, finally, a questionnaire was applied to collect information about the priorities and impressions of the participants. The results obtained in the case study demonstrate that the tool was able to automate the technique of the Analytical Hierarchy Process and facilitate the process of prioritizing requirements. The criteria presented in this paper are also suitable for the context of the project in which they were used. Participants reported that the prototype of the tool is intuitive and practical, showing that it has the potential to be improved for commercial use.
Iridescent: Um serious game que visa identificar a possibilidade de adaptação de um teste psicológico tendo como base o DASS-21
(Universidade Católica do Salvador, 2019-06-18) Almeida, Felipe Deveza de; Costa, Hudson Luís da Silva; Wyzykowski, André Brasil Vieira; lattes.cnpq.br; Wyzykowski, Andre Brasil Vieira; lattes.cnpq.br; Reis, Marcelo Indio dos; lattes.cnpq.br; Melo, Osvaldo Requião; lattes.cnpq.br; Araujo, Jeane Franco de; lattes.cnpq.br
Software engineering and the IT arena in general offer solutions to problems in many other areas, ranging from simpler software to management to the most complex systems imaginable. Given that anxiety and depression are problems affecting millions of people around the world and the already mentioned high number of solutions that software engineering can offer, a textit serious game has been developed. textit Serious games are games that are meant to align the audio visual experience with a specific goal that is not tied to textit gameplay. The game described in this work has the objective of verifying if there is a possibility of adapting the psychological test DASS-21 to another platform, opening the doors to new adaptations and studies in the area. To validate our adaptation, two experiments were carried out with a total of 25 participants, allowing data collection and comparison with the form responses. The tests were carried out voluntarily by the participants, being totally in agreement with the norms established by the DASS-21. The experiment consisted of two steps: to play textit Serious games and to respond to the DASS-21 form, after these two steps, the participant would send his answers to the evaluators. The results obtained in this work show that from the point of view of IT, the DASS-21 test has the possibility of being adapted, reaching up to 94
Levantamento experimental de dados de equilíbrio líquido-líquido através de uma metodologia gravimétrica
(Universidade Católica de Salvador, 2018-12-18) Santos, Ivaniele Vieira; Neves, Sérgio Bello; http://lattes.cnpq.br; Conceição, Wagner Almeida Mônaco; http://lattes.cnpq.br; Neves, Sérgio Bello; http://lattes.cnpq.br; Conceição, Wagner Almeida Mônaco; http://lattes.cnpq.br; Marques, Celso Argolo Xavier; http://lattes.cnpq.br
The study of liquid-liquid equilibrium is extremely important for planning and development of projects, as well as providing support for analysis and selection of unit operations and industry processes. The present work aims to develop a methodology for the data collection of liquid-liquid equilibrium from the density of mixtures of the ternary system, water-acetone-chloroform. The mass fractions of the three components were obtained by the liquid-liquid extraction experimental method, as well as the density, which was determined by the gravimetric method of pycnometry. Through the modeling developed, it was possible to calculate the molar volume of excess of each binary, from the component composition data, to predict the density of the ternary mixture. In the same way, the substances present in the solution could be quantified by the experimental density. Through the analysis of the results obtained throughout the work, the modeling developed proved to be quite effective
Metodologia para projeto de unidade de tratamento de efluente com estudo de caso
(Universidade Católica do Salvador, 2019-12-13) Santos, Jéssica Sousa dos; Conceição, Wagner Almeida Mônaco; http://lattes.cnpq.br/; Neves, Sérgio Bello; http://lattes.cnpq.br/; Hayashi, Júlio César; http://lattes.cnpq.br/
Water is among the natural resources most used by the population and industries. Studies and comparative analyses of consumption, availability and environmental impact have shown that in many parts of the world, it is impossible to consume water without it being subjected to appropriate treatments and that various emissions are polluted due to the negligent disposal of water after its use. More and more financial and technological investments are being safeguarded in order to achieve an adequate sanitary security and preservation of the environment. The industry in general, is characterized as one of the largest consumers of water and consequently, end up being the ones that generate more liquid effluents in their production process. Based on this premise, it is necessary to elaborate and study efficient projects and technologies that can guarantee the quality of this generated effluent, to ensure the quality of the receiving water body when this effluent is discarded and so that it complies with the standards required by Environmental Legislation. The objective of this work was to analyze an effluent generated by a given company, to characterize this effluent in order to verify its parameter in accordance with the environmental requirements available in the state of Bahia and, based on this analysis, to study the type of technology that should be used for this effluent in order to reduce the parameter present in this effluent so that it complies with the demanding standards to release it to the receiving body without causing environmental damage and public health.
Os impactos da indústria 4.0 e da 5a era da qualidade na indústria e no mercado consumidor brasileiro
(UCSal - Universidade Católica do Salvador, 2024-06-19) Mello, Andreza Maria Andrade de; Trierweiler, Larissa Fonseca; Lima, Yasmin Lopes de; Bastos, Luciane Conceição Silva (Orient.)
A evolução da indústria e da qualidade tem caminhado lado a lado desde o início da Era industrial. Com esse contexto em mente, foi realizada uma revisão bibliográfica e um estudo de caso para analisar e investigar os impactos da Indústria 4.0 e da Quinta Era da Qualidade na indústria e no mercado consumidor brasileiro. O objetivo foi compreender como essas transformações tecnológicas e de gestão influenciam a eficiência, a qualidade, a competitividade e a satisfação dos clientes, visando fornecer orientações para práticas empresariais mais eficazes e o desenvolvimento de carreiras. Os resultados da análise temática e de conteúdo mostraram-se alinhados com a literatura, destacando a importância da Indústria 4.0 e da Quinta Era da Qualidade no contexto brasileiro e ressaltando a necessidade de adaptação e integração das tecnologias nos processos industriais e na gestão da qualidade. Os desafios identificados, como altos custos, resistência às mudanças e escassez de mão de obra qualificada, são obstáculos que precisam ser superados com estratégias eficazes. Além disso, foi evidenciado o impacto positivo dessas transformações no mercado consumidor, sublinhando a importância das certificações de qualidade. Entre as sugestões desenvolvidas, destaca-se a implementação de soluções tecnológicas como a Internet das Coisas, sistemas ciber-físicos e inteligência artificial para otimizar a produção e fortalecer a gestão da qualidade, consolidando um ambiente industrial mais competitivo e alinhado com as demandas do mercado global, desta forma, as empresas brasileiras podem não apenas melhorar suas operações internas, mas também aumentar sua competitividade no cenário internacional, contribuindo para o desenvolvimento econômico e tecnológico do país.
Previsão de demanda de sobressalentes na indústria
(Universidade Catolica de Salvador, 2019-08-01) Silva, Lucas Jordi Nascimento da; Dias, Vinicius do Rego; lattes.cnpq.br
Revisão bibliográfica das principais tecnologias de captura do CO2
(Universidade Católica do Salvador, 2021-06-17) Souza, Juliana Sousa e; Neves, Sérgio Bello; http://lattes.cnpq.br/; Conceição, Wagner Almeida Mônaco; http://lattes.cnpq.br/; Mustafá, George de Souza; http://lattes.cnpq.br/
The annual global emissions of greenhouse gases have been growing substantially since 2016, a period in which there was a fall in these emissions. Of the total emissions of greenhouse gases, carbon dioxide (CO2) occupies the first place 74%, followed by methane (CH4) responsible for 17% and nitrous oxide (N2O), 6.2%, and fluorinated gases ( composed of HFCs, PFCs, SF6 and NF3) which represents 2% of global emissions and come from industrial processes. Currently, the world already lives with the consequences of climate change, resulting from the greenhouse effect, in view of this, more actions that may control these emissions, especially that of carbon dioxide, which is the gas that contributes the most to the greenhouse effect, be put into practice. CO2 capture is considered an important route for climate mitigation, there are four types of basic systems for CO2 capture, these can be subdivided into post-combustion, pre-combustion, combustion with oxygen and industrial process. There are several technologies for capturing CO2 from the combustion of fossil fuels in power generation plants. These mainly include chemical and physical absorption, adsorption, membranes, ionic liquids and cryogenic process. In the development of this work, the main CO2 capture technologies were discussed, as well as the advantages and disadvantages of each one. The present work had as main objective to map and carry out a comparison between the main technologies for the capture of carbon dioxide (CO2) in industrial activity and in the generation of energy.
Robô Cobra: sistema para identificação de organismos vivos em estruturas colapsadas
(Universidade Católica do Salvador, 2020-06-29) Araújo, Adriano Ricardo Andrade; Rios, Luiz Henrique Brito; Wyzykowski, André Brasil Vieira; http://lattes.cnpq.br/; Reis, Marcelo Indio dos; http://lattes.cnpq.br/; Melo, Osvaldo Requião; http://lattes.cnpq.br/
When a structure collapse occurs, caused by collapse or even for another reason, to obtain an optimized response time in the search and rescue of survivors, technology becomes an important ally in maintaining life. In this context, we see robotics as a process optimizer. This work deals with the construction of a Snake Robot, a system for the identification of living organisms in collapsed structures, which aims to identify living beings in these structures using machine learning, contemplating the implementation of an autonomous locomotion system, in addition to a classification of thermal images. For this, a thermal image dataset was generated, where we use data augmentation to add it in volume and variety, and from it generate a predictive model. This predictive model, in conjunction with object detection, allows the snake robot to function autonomously during the detection / classification of objects in living or non-living beings. In building the solution, sensors, an Arduino microcontroller were used, in addition to the Tensorflow library with Keras. With the simulated practice experiments carried out, the robot had its operation tested and validated, accurately detecting in a 180o field of view at distances between 10 to 150 cm, obtaining an average accuracy of 97.5 % for classification.

Browse

Browsing Engenharias by Title

Results Per Page

Sort Options