|
Dissertations |
|
1
|
-
VINÍCIUS LUIS DE CARVALHO SILVA
-
“Low cost container tracking and tracing system”
-
Advisor : HERMAN AUGUSTO LEPIKSON
-
COMMITTEE MEMBERS :
-
ALIRIO SANTOS DE SA
-
HERMAN AUGUSTO LEPIKSON
-
ROBERTO LUIZ SOUZA MONTEIRO
-
Data: Mar 7, 2019
-
-
Show Abstract
-
The service provided by the Brazilian ports is among the most expensive in the world, a fact attributed mainly to their technological gap, with emphasis on infrastructure, logistics and automation, which are interdependent factors and have a strong impact on operating costs and system efficiency. Among the most relevant issues is the tracking of containers along their entire route, from ship to recipient and back to ship. Therefore, it is a current and widely researched theme in view of the new technologies that have been made viable, and which have peculiarities inherent to each country. In the case of Brazil, the characteristics of the most widely used modal systems, regionalities, tax and fiscal aspects and systemic deficiencies should be considered. This work emphasizes the challenge of obtaining a low cost system capable of locating containers inside and outside the port. As a result of the implementation of this solution it is mainly expected to reduce operating costs arising from the presence of checkers in the yards, eliminate the loss of cargo and search time caused by human error, allow the location and / or online tracking of all containers. from the Web. The solution has innovative features backed by patent applications and with great potential to become a marketable product. The embedded system developed has a microcontroller, an internal mapping identification and location system, as well as a georeferenced tracking system. Basically, the identification system handles the location of containers within the port yard.
Through algorithms developed based on the technology adopted and supported by a database, the system is able to determine the position of all containers in the yard, whether they are on the floor or stacked over other containers. The georeferenced system is responsible for tracking containers when they are outside the port environment, being able to provide the route and location of each asset at programmable intervals.
Validation and testing of system dynamics and behavior in typical yard movements was performed on a container model built using structural material similar to the actual one. These tests allowed simulating and proving the efficiency of the system against the established objectives. To validate the concepts of mobility and the ability to communicate in a real environment, the prototypes were tested in a container carrier container yard and proved functional and adaptable to meet specificities.
|
|
2
|
-
JOSE EMILIO QUESADO DE SOUZA
-
Self-Powered Wireless Vibration Analyzer
-
Advisor : ANTONIO CEZAR DE CASTRO LIMA
-
COMMITTEE MEMBERS :
-
ANTONIO CEZAR DE CASTRO LIMA
-
FABIANO FRAGOSO COSTA
-
IURI MUNIZ PEPE
-
Data: Apr 5, 2019
-
-
Show Abstract
-
This work presents the study and design of vibration analyzer self-powered by energy harvesting, using piezoelectric and magnetic components to convert mechanical energy into electric energy. A prototype vibration analysis instrument was developed to monitor the operating state of machines and motors. This system is powered by a Lithium battery which by its own is recharged by the generator, providing the configuration of self-sufficient to the system. The hybrid structure proposed in this work analyzes and demonstrates the gains and obtained from the miscegenation of two generator models. The results obtained from simulations and tests in the experimental platform show an effective solution for power generation for low energy consumption devices and instruments.
|
|
3
|
-
MATHEUS OLIVEIRA DE BRITO
-
Thermosolar didactic plant for modeling, identification, simulation and control tests
-
Advisor : MARCUS VINICIUS AMERICANO DA COSTA FILHO
-
COMMITTEE MEMBERS :
-
ACBAL RUCAS ANDRADE ACHY
-
BERNARDO ORDONEZ
-
IURI MUNIZ PEPE
-
MARCUS VINICIUS AMERICANO DA COSTA FILHO
-
Data: May 10, 2019
-
-
Show Abstract
-
This work proposes a didactic thermosolar plant for model studies, simulations and process control. The thermosolar plant uses solar energy to perform the heating of a fluid generating heat, an input that is widely used in industry. In addition to the physical structure of the plant, some instruments were developed for the sensing of important physical quantities, such as solar irradiance and the state of the control valve. One of the objectives of this work is to offer a study environment that approximates the theoretical foundations of teaching to the industrial reality, a primordial philosophy for the area of education in engineering. The equipment allows analyzes and applications in modeling, simulation and control through Matlab / Simulink and Labview softwares. A case study is presented in order to demonstrate the functionalities of the proposed system, being possible the study and application of advanced control.
|
|
4
|
-
SAULO MASCARENHAS FRÓES
-
TECHNIQUE FOR OBTAINING ANTENNA RADIATION DIAGRAMS IN ECOLOGICAL ENVIRONMENTS
-
Advisor : ANTONIO CEZAR DE CASTRO LIMA
-
COMMITTEE MEMBERS :
-
ANTONIO CEZAR DE CASTRO LIMA
-
EDUARDO FURTADO DE SIMAS FILHO
-
MARCELA SILVA NOVO
-
Data: Jun 7, 2019
-
-
Show Abstract
-
Anechoic chambers are indicated for the determination of antenna radiation diagrams, among other quantities. This is because cameras of this type are produced with materials that absorb electromagnetic waves, reducing the occurrence of reflections. However, anechoic chambers are often too costly for small businesses or university centers to acquire. In the state of Bahia, for example, there is only one semi-anechoic chamber and none completely anechoic. In order to overcome this difficulty, several techniques are currently being developed with the purpose of suppressing the effect of echoes in measurements performed in echo environments. This has proven to be possible through the use of digital signal processing techniques based on classical concepts such as deconvolution, impulse response and filtering. In this work, a technique for obtaining the radiation diagram in non-anechoic environments was studied. Briefly, the method consists of making measurements taken at different initial positions of the transmitting and receiving antennas and, through a similarity identification algorithm, reconstructing the real radiation diagram. The reconstructed diagram was then evaluated from the comparison with the radiation diagram obtained in an anechoic chamber. The obtained results indicated that the proposed technique is promising for the reconstruction of antenna radiation measured in echo environments. A better functioning of the technique was observed especially when peaks / attenuations due to reflections occurred in only one specific position.
|
|
5
|
-
ÉRICO AUGUSTO NUNES PINTO
-
Fuzzy Logic Based Financial Operations Recommendation System.
-
Advisor : LEIZER SCHNITMAN
-
COMMITTEE MEMBERS :
-
LEIZER SCHNITMAN
-
CARLOS ARTHUR MATTOS TEIXEIRA CAVALCANTE
-
MARCIO FONTANA
-
Data: Jun 17, 2019
-
-
Show Abstract
-
Making predictions and providing buy and sell recommendations in the stock market are usually considered difficult tasks, given the complex behavior of financial asset price movement, which is regarded as dynamic, nonlinear, and stochastic. Just as in the fields of knowledge where artificial intelligence (AI) techniques are applied to obtain accurate and faster information, companies that constantly provide trading recommendations seek to gain advantages using AI systems and mathematical modeling, reducing analysis time. and increasing the accuracy of recommendations. This paper presents the application of systems based on fuzzy logic to predict the price behavior of a set of shares of companies listed on the Bovespa and to recommend a strategy of buying and selling shares on a daily basis, based on indicators and price estimates. . A first recommendation system relies on classical rules of technical analysis to predict stock price movement, relying solely on the combination of some indicators, such as: Relative Strength Index (RSI), Stochastic and Williams. This strategy, although commonly exploited by the market, is unable to escape the stochastic influence of price series, ie it does not provide, for example, long sequences of hits. To this end, a second recommendation system was proposed, which differs from the previous one by also considering price forecasting information based on the stochastic model of stock behavior known as the Brownian Geometric Motion (MBG) in addition to the OBV indicator. On Balance Volume). The results presented by the systems had their performances compared from the number of recommendations and hits. With the first system it was shown that not all assets can be operated from a similar set of indicators, affecting the financial results. The second, which was aided by the price forecast proposal, achieved better performance and consistency in the recommendations.
|
|
6
|
-
JOSÉ MARCELO DE ASSIS SANTOS
-
PHOTOVOLTAIC DATA ACQUISITION SYSTEM FOR CHARACTERIZATION OF LOCAL INSOLATION FOR SUPPORT SERVICE FOR MICRO AND SMALL GENERATORS
-
Advisor : IURI MUNIZ PEPE
-
COMMITTEE MEMBERS :
-
EDSON PEREIRA MARQUES FILHO
-
ITA TEODORO DA SILVA
-
IURI MUNIZ PEPE
-
Data: Jun 28, 2019
-
-
Show Abstract
-
The generation of electric energy from solar energy is an alternative to the traditional energy matrix and, increasingly, its participation in the energy generation market is increasing. Solar irradiation depends on several factors, such as: locality, season, atmospheric composition, cloud cover and surface shape. As the intensity of the solar radiation is variable, a survey of its values is necessary to guarantee a better use of the generation system throughout the year. In this work, a photovoltaic data acquisition and sensing system was implemented to characterize the local insolation, based on three solar cell technologies, namely: monocrystalline silicon, polycrystalline silicon and thin film. During the calibration and validation tests, the saturation of the silicon cell signals was observed when the external resistive load was greater than 30 ohm. This saturation can be avoided by the use of an acrylic bulkhead, with two hole matrices, which served as a collimator and attenuator (attenuation ratio of -12.0 ± 0.5 dB). The developed system was able to determine the normalized efficiency of the solar cells during the day, in different seasons of the year. Thus in the winter the cell that has the highest normalized efficiency was CIGS, whereas in the spring this domain falls, remaining at the beginning and at the end of the day. In the summer the silicon cells show higher normalized efficiency when compared to the CIGS cell.
|
|
7
|
-
GUSTAVO DE ALMEIDA NEVES
-
ROTATED MULTI-OBJECT DETECTION FROM FORWARD-LOOKING SONAR IMAGES
-
Advisor : LUCIANO REBOUCAS DE OLIVEIRA
-
COMMITTEE MEMBERS :
-
EDUARDO FURTADO DE SIMAS FILHO
-
LUCIANO REBOUCAS DE OLIVEIRA
-
PAULO CESAR MACHADO DE ABREU FARIAS
-
Data: Nov 13, 2019
-
-
Show Abstract
-
The underwater world is a hazardous place to people, being even unreachable in some places. It is common to employ manned or unmanned underwater vehicles, when human activities have to be performed underwater. Particularly, oil and gas companies have used remotely operated vehicles (ROVs) to inspect and maintain submerged structures of subsea facilities. Because of the complexity and the high cost of ROV operations, some researches have addressed autonomous underwater vehicles (AUVs) to perform inspection tasks under water. AUVs are typically equipped with perception sensors, such as optical cameras and sonars that ultimately provide visual and acoustic information of underwater scenarios. With the goal of comprehending the surrounding environment, object detection over perception sensor data is a crucial task. Indeed, detected objects can be used for many applications of the AUV system, such as to locate obstacles, to provide landmarks for the navigation, to move the vehicle with respect to a detected target object and to plan AUV trajectories. Although optical cameras are still important sensors for AUVs, their sensing capability is limited underwater, being only able to work at very short ranges, and in low-turbidity water conditions. In contrast, sonars can cover larger operative ranges through the water and work in turbid water conditions. However sonars provide noisy data with lower resolution and more dicult interpretation, thus making object recognition in sonar images an arduous task. Having all this in mind, our work propose a novel multi-object detection framework that outputs object position and rotation from sonar images. Two convolutional neural network based architectures are proposed to detect and estimate rotated bounding boxes: An end-to-end system, called RBoxNet, and a pipeline comprised of two networks, called YOLOv2+RBoxDNet. Both proposed approaches are structured from one of three representations of rotated bounding boxes regressed deep inside. To the best of our knowledge, there is no other work in the literature that estimates rotated bounding boxes in sonar images. Experimental analyses were performed by comparing several congurations of our proposed methods (by varying backbone, regression representation and architecture) with other state-of-the-art methods over real sonar images. Results showed that RBoxNet presented the best tradeo between accuracy and speed, reaching an averaged mAP@[.5,.95] of 90:3% at 8:58 frames per seconds (FPS), while YOLOv2+RBoxDNet was the fastest solution running at 16:19 FPS, but with a lower averaged mAP@[.5,.95] of 77:5%. Both proposed methods were robust to variations of additive Gaussian noise, detecting objects even when the noise level is up to 0:10.
|
|
8
|
-
IGOR MENDES LIMA PATARO
-
ADVANCED SIMULATION OF D-RTO ASSOCIATED WITH PREDICTIVE CONTROL STRATEGIES FOR ETHANOL DISTILLATION COLUMNS
-
Advisor : MARCUS VINICIUS AMERICANO DA COSTA FILHO
-
COMMITTEE MEMBERS :
-
HERMAN AUGUSTO LEPIKSON
-
JULIO ELIAS NORMEY RICO
-
MARCUS VINICIUS AMERICANO DA COSTA FILHO
-
RODOLFO CÉSAR COSTA FLESCH
-
Data: Nov 19, 2019
-
-
Show Abstract
-
Alcoholic distillation, one of the main productive stages of the sugar and alcohol industry, still shows timid results in terms of automatic control and optimization. However, advanced control approaches give us good prospects for improving safety, efficiency and productivity in this type of process. In particular, predictive control techniques, widely known as MPC (Model Predictive Control) allow the operation of the distillation columns considering the complexity of the system, such as multiple inputs and outputs and numerous disturbances that can compromise the quality of the products. In addition, strategies based on time compensators, such as the filtered Smith Predictor (FSP), can incorporate formulations that allow to increase the robustness of the closed loop control system. From this perspective, this work presents the application of an advanced control structure in two layers. The first layer consists of implementing a predictive control system. In particular, the infinite horizon (IHMPC), MIMO FSP and DTCGPC were designed, capable of maintaining the alcoholic distillation process under the conditions defined as a reference. For the second layer, a dynamic optimizer in real time was developed, capable of calculating the best operation points of the process using a reliable model, considering economic and productivity conditions. For that, a computational platform was also developed that allows the advanced simulation of the system as well as its dynamic behavior in a Software-in-the-Loop environment as a way to guarantee the fidelity of the results and propose the application of these strategies in a real scenario. OLE (Object Linking and Embedding) Automation integrates Matlab and Aspen Hysys software to simulate practical OPC (Open Platform Communications) scenarios commonly found in the industry. Controllers are evaluated, in simulation scenarios, from control performance indexes (ITAE, ITSE, SSC) and the computational performance of each strategy, as a quantitative metric for comparing the proposed structures. Furthermore, the economic performance of the optimization layer is compared with the classic PID control strategy still applied in the sugar and alcohol industry. This study showed that the dynamic optimization associated with predictive controllers increased the production of the distillation column, showing itself to be more robust and stable compared to the approaches commonly used in the current scenario of ethanol distilleries. In view of the particular benefits of each strategy, this work aims to propose different control solutions for different scenarios of the sugar and alcohol industry, in order to maintain a more efficient, economical and clean production. In addition, it is intended to evolve the practical application of advanced control strategies that take into account the stability of the system, the efficiency of production and the robustness in closed loop.
|
|
9
|
-
RAFAEL SILVA DE LIMA
-
Development of Combined Beta-CUSUM Binomial control charts for monitoring nonconforming products
-
Advisor : CARLOS ARTHUR MATTOS TEIXEIRA CAVALCANTE
-
COMMITTEE MEMBERS :
-
CARLOS ARTHUR MATTOS TEIXEIRA CAVALCANTE
-
ANGELO MARCIO OLIVEIRA SANT ANNA
-
DANILO MARCONDES FILHO
-
MAURICIO SANTANA LORDELO
-
Data: Nov 29, 2019
-
-
Show Abstract
-
Statistical process control charts are tools widely used to monitor the quality of products, processes and services. Proposals for Shewhart in 1924 are traditionally applied because of their ease of implementation and analysis. Over the years, various control codes are allowed in the Shewhart type, with increased performance or performance due to process automation and high quality product use. However, these letters have a disadvantage of not detecting small changes within productive processes, where the use of cumulative sum letters (CUSUM) proposed by Page in 1954 is more appropriate. When a magnitude of change within a process is not known, one of the solutions is an application of combined cards as characteristics of Shewhart cards with CUSUM cards. The objective of this work is the development of a combined control chart as a control chart features, with beta distribution and accumulated total attributes chart, based on binomial distribution. Binomial Beta-CUSUM combined chart development procedures and their application to discrete and continuous data are demonstrated. The results show that a combined chart performs similarly to the Shewhart-CUSUM Binomial chart when applied to discrete data and performs better when applied to continuous data. Thus, a proposed Beta-CUSUM Binomial letter is valid and is a new combined letter alternative for monitoring nonconforming items.
|
|
10
|
-
IGOR CORDEIRO DOS SANTOS
-
DIAGNOSIS OF KNOWLEDGE MANAGEMENT IN CIVIL CONSTRUCTION COMPANIES USING THE FUZZY-AHP METHOD
-
Advisor : CARLOS ARTHUR MATTOS TEIXEIRA CAVALCANTE
-
COMMITTEE MEMBERS :
-
ANGELO MARCIO OLIVEIRA SANT ANNA
-
AVA SANTANA BARBOSA
-
CARLOS ARTHUR MATTOS TEIXEIRA CAVALCANTE
-
DAVI NOBURO NAKANO
-
Data: Dec 13, 2019
-
-
Show Abstract
-
Diagnosis of Knowledge Management based on the measurement of performance indicators in Brazilian civil construction companies in the building sector, whose main activities are: execution of residential works and industrial and commercial buildings. Use of knowledge management using performance indicators in the field of civil construction, aiming to study its application effectiveness and convergence of the identified results. The available literature is focused on the conceptual field, without effective proof of application and validation in practice. A self-administered questionnaire for data collection was elaborated, with subsequent application of the Diffuse Analytical Hierarchical Method (Fuzzy-AHP) to choose and make decisions about the best Knowledge Management model for the Brazilian civil construction sector. The use of Fuzzy-AHP to diagnose the importance and performance of Knowledge Management for Brazilian Civil Construction Organizations in the Buildings sector ratified the need for a structured approach so that organizations can remain in constant learning, productive and competitive. Performance gaps and opportunities for improvement in the field of knowledge were identified as knowledge management is centered on controls that do not necessarily provide opportunities for improvement for organizations, being used only as a source of data and information to support research. reaction to the failures that occurred, without visualization by all hierarchies, mainly the tactical and operational levels. It is important to emphasize the implications of this research related mainly to the nature of qualitative work. As it involves subjective elements of analysis and considerations, the present situation and feeling of the participants reflectedand considerations, the situation and present feeling of the participants reflected considerably in the contributory actions of this research. Similarly, there are the limitations of Knowledge Management itself, as it includes intangible assets, which are difficult to measure, especially if related to tacit knowledge. Despite a vast body of literature on Knowledge Management, the article demonstrates these factors within a Brazilian context. An essential point is that the study is based on feedback from construction professionals and managers, who carry out their analyzes and conclusions from practical points of view, without relevant theoretical knowledge of the relationship between the process variables. The Diffuse Analytical Hierarchical Method applied to the theme of Knowledge Management through Performance Indicators in Civil Construction addresses the degrees of imprecision arising from difficulties and ambiguities of human perception.
|
|
11
|
-
KLEBER DE LIMA SANTANA FILHO
-
Classification of Hand and Fist Gestures Through Muscle Synergies.
-
Advisor : LEIZER SCHNITMAN
-
COMMITTEE MEMBERS :
-
ANGELO AMANCIO DUARTE
-
LEIZER SCHNITMAN
-
TEODIANO FREIRE BASTOS FILHO
-
Data: Dec 19, 2019
-
-
Show Abstract
-
This paper proposes a new approach for the activation of pattern recognition myoelectric devices, using a convolutional neural network model, which receives input extracted characteristics based on the concept of muscle synergies. This concept is based on the assumption that the central nervous system controls movements by combining muscle groups, rather than directly controlling each degree of freedom, thereby reducing the number of parameters that need to be controlled. Non-Negative Matrix Factorization (NMF) algorithms are used to extract synergies in the form of matrix factorization activation signals, allowing these signals to be used in the control of myoelectric devices. The new approach utilizes the estimation of neural control activations, notably force functions, in conjunction with a deep learning pattern recognition model to enable improved accuracy rates in the task of recognizing sets of hand and wrist gestures. The proposed technique was evaluated by 3 different tests, for which signals extracted from two public databases (NINAPRO Project and CAPGMYO) were used.
|
|
|
Thesis |
|
1
|
-
GILDEBERTO DE SOUZA CARDOSO
-
Transverse Feedback Linearization Applied to RRT*
-
Advisor : LEIZER SCHNITMAN
-
COMMITTEE MEMBERS :
-
CRISTIANO HORA DE OLIVEIRA FONTES
-
LEIZER SCHNITMAN
-
MARCIO ANDRE FERNANDES MARTINS
-
THIAGO PEREIRA DAS CHAGAS
-
TIAGO TRINDADE RIBEIRO
-
Data: Jun 10, 2019
-
-
Show Abstract
-
The thesis deals with the analysis of the feedback transverse linearization as a control for a unicycle robot's navigation. The path to be followed by a robot will be given through a set of curves whose distance is Euclidean. Feedback transverse linearization makes this path attractive and time-invariant, it means that, if the robot is initialized on the path with an appropriate orientation, it will remain on the path for all the time. The limitation of the technique is analyzed when the angle between the segments of lines that compose the path is obtuse, in this case, the robot follows an opposite path to the desired. There was no evidence in the literature of limitation of transverse feedback linearization when the angles are obtuse. It is mathematically demonstrated the existence of a set of controller gain values that guarantee that the robot will follow the desired path, if the angle formed between the straight segments of the path is acute. Dynamic Transverse Feedback Linearization is proposed as a solution to this limitation. For the purpose of exemplifying the proposed control, the transverse feedback linearization with the rapidly exploring random trees star is integrated, modifying the path planner in order to meet the limitation of the transverse feedback linearization. Here, such linearization is compared with dynamic transverse feedback linearization. Transverse feedback linearization is applied to the Kobuki robotic platform in order to experimentally show the robot convergence in a direction opposite to the desired one.
|
|
2
|
-
DION BARBOSA DOS SANTOS RIBEIRO
-
Project Neutrinos Angra: the final detector ,redesigne , assembly and commissioning.
-
Advisor : IURI MUNIZ PEPE
-
COMMITTEE MEMBERS :
-
IURI MUNIZ PEPE
-
TIAGO FRANCA PAES
-
MARCUS VINICIUS AMERICANO DA COSTA FILHO
-
ANTONIO FERREIRA DA SILVA
-
JOÃO CARLOS COSTA DOS ANJOS
-
DENIS GILBERT FRANCIS DAVID
-
Data: Jul 5, 2019
-
-
Show Abstract
-
The Neutrinos Angra project aims to monitor the thermal power and evolution of fissile fuel of the Angra II nuclear power plant, located at Almirante Álvaro Alberto Nuclear Power Station, in Angra dos Reis, to corroborate the development of nuclear safeguards and the detection physics of nuclear fuels. neutrinos at surface level. For this purpose, a neutrino detector based on Cherenkov radiation detection in 0.2% by mass gadolinium doped ultra pure water was installed adjacent to the reactor building of this plant. The project is a collaboration started in 2006 that soon became a 100% Brazilian project. This condition promoted unparalleled development of local content and personnel, but also imposed serious restrictions and delays on project implementation. The detector developed is a concentric tank monolith with a 32 photomultiplier polypropylene target tank and 1.3 cubic meters of gadolinium-doped water. Surrounding it is a two-volume polypropylene shielding with 1.65 m3 and 3 m3, respectively, and 4 photomultipliers for barring muons and neutrons. Above this set is an additional veto tank with 1.45 m3 of water and 4 sensors. This detector is connected to a data acquisition system composed of signal conditioning, discrimination, discretization, selection and storage modules. This paper describes the neutrino detector assembly at the Brazilian Center for Physical Research, where it was tested; the subsequent disassembly of the same, its transportation and final assembly in the laboratory container of the project at CNAAA; and finally, the commissioning of this detector.
|
|
3
|
-
AYDIN JADIDI
-
SHORT-TERM FORECASTING OF THE GLOBAL HORIZONTAL IRRADIANCE AND ELECTRICAL POWER DEMAND USING MACHINE LEARNING TECHNIQUES
-
Advisor : ANTONIO CEZAR DE CASTRO LIMA
-
COMMITTEE MEMBERS :
-
ANTONIO CEZAR DE CASTRO LIMA
-
MARCIO ANDRE FERNANDES MARTINS
-
FABIANO FRAGOSO COSTA
-
ANGELO AMANCIO DUARTE
-
GERMANO CRISPIM VASCONCELOS
-
Data: Sep 6, 2019
-
-
Show Abstract
-
The use of photovoltaics is still considered to be challenging because of certain reliability issues and high dependence on the global horizontal irradiance (GHI). GHI forecasting has a wide application from grid safety to supply-demand balance and economic load dispatching. On the other hand, load forecasting is important for smart grids and the electricity market in terms of the meeting the demand and distribution of electrical energy. The current research develops a methodology for more precise forecasting results. Two different approaches are developed and applied for GHI forecasting and electric load forecasting. Given a data set, a multi-layer perceptron neural network (MLPNN) is a strong tool for solving the forecasting problems. Furthermore, noise detection and feature selection in a data set with numerous variables are of crucial importance to obtain the desired results. This work employs density-based spatial clustering of applications with noise (DBSCAN) and non-dominated sorting genetic algorithm II (NSGA II) algorithms for noise detection and feature selection, respectively. Tuning the neural network is another important issue that includes choosing the hidden layer size and activation functions between the layers of the network. Previous studies have utilized a combination of different parameters based on trial and error, which seems to be inefficient in terms of accurate selection of the desired features and also tuning of the neural network. In this research, two different methods namely, particle swarm optimization (PSO) algorithm and genetic algorithm (GA) are utilized in order to tune the MLPNN, and the results of one-hour ahead forecasting of the GHI are subsequently compared. The methodology is validated using the hourly data for Elizabeth City located in North Carolina, USA, and the results demonstrated a better performance of GA in comparison with PSO. For electric power demand forecasting, this research proposes a hybrid algorithm for improving the forecasting accuracy where a non-dominated sorting genetic algorithm II (NSGA II) is employed for selecting the input vector, where its fitness function is a multi-layer perceptron neural network (MLPNN). Thus, the output of the NSGA II is the output of the best-trained MLPNN which has the best combination of inputs. The result of NSGA II is fed to the Adaptive Neuro-Fuzzy Inference System (ANFIS) as its input and the results demonstrate an improved forecasting accuracy of the MLPNN-ANFIS compared to the MLPNN and ANFIS models. In addition, genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization (ACO), differential evolution (DE), and imperialistic competitive algorithm (ICA) are used for optimized design of the ANFIS. Electricity demand data for Bonneville, Oregon are used to test the model and among the different tested models, NSGA II-ANFIS-GA provides better accuracy.
The GA-tuned MLPNN reported a normalized root mean square error (nRMSE) of 0.0458 and a normalized mean absolute error (nMAE) of 0.0238 for hourly GHI forecasting and obtained values of error indicators for one-hour-ahead demand forecasting are 107.2644, 1.5063, 65.4250, 1.0570, and 0.9940 for RMSE, RMSE%, MAE, MAPE, and R, respectively.
|
|
4
|
-
ANDRE PIMENTEL MOREIRA
-
Double-Acting Submerged Hydraulic Linear Pump: Process and Device
-
Advisor : HERMAN AUGUSTO LEPIKSON
-
COMMITTEE MEMBERS :
-
ARMANDO SA RIBEIRO JUNIOR
-
HERMAN AUGUSTO LEPIKSON
-
LEIZER SCHNITMAN
-
MANUEL DE ALMEIDA BARRETO FILHO
-
VALTER ESTEVÃO BEAL
-
Data: Sep 9, 2019
-
-
Show Abstract
-
The present work describes the process and artificial lifting apparatus for a doubleacting mechanical pump using a hydraulic system designed to operate partially or completely submerged, and it is suitable for oil production at small, medium and large depths, denominated Double-Acting Submerged Hydraulic Linear Pump (BLS). The proposed device can be used in wells with different configurations (vertical or directional), for lifting fluids with API densities below 22◦ (heavy oil) to densities higher than 31◦ (light oil). Furthermore, it is a viable alternative for extracting water from the underground aquifers in the Northeast regions of Brazil. Given its unprecedented conception, this new concept and pumping system was the object of a recent patent deposited at the National Institute of Intellectual Property (BR 10 2015 019070 0). A prototype of the pumping device was developed to prove its operation. The speed variation tests of the hydraulic cylinders of the prototype compared to the computational simulation, showed only small distortions with an error of between 7.79% and 10.5% for rotations of the submersible electric motor running at between 1800 and 3600 rpm. The pumping test results of the cycle time of the cylinders and the production per cycle were compatible with those calculated and simulated in the Automation StudioTM software. The maximum error obtained was 8.67% between the system running on an experimental test bench and the simulated results. Considering the drive power/geometric lifting height ratio (kW/m), the nominal drive power of the BLS device presented an advantage in relation to the other lifting methods analyzed in this work. However, compared to the centrifugal pump used in the Guarani aquifer presented in this work, the BLS presented higher energy consumption for the drive power in relation to the volumetric flow (kW/m3/d). The comparison, although simplified, demonstrates that the BLS can be characterized as a low flow pump, but that it may soon be an option for production in deep reservoirs. Although the prototype has not yet been tested in a real operating environment, the results of the laboratory tests have been promising. Moreover, since this new pumping apparatus is inserted directly into the production zone, the problems such as those related to the sucker rod column are eliminated. As the greater part of the equipment of this proposed pumping system is in the well, the installation and maintenance tend to present low complexity. Although the work has been evaluated through laboratory tests and computational simulations, there is still potential to evolve its technological side further, giving rise to future work.
|
|
5
|
-
RÔMULO GUEDES CERQUEIRA
-
A multi-device sonar simulator for real-time underwater applications.
-
Advisor : LUCIANO REBOUCAS DE OLIVEIRA
-
COMMITTEE MEMBERS :
-
ANTONIO LOPES APOLINARIO JUNIOR
-
KARL PHILIPS APAZA AGUERO
-
LUCIANO REBOUCAS DE OLIVEIRA
-
Paulo Lilles Jorge Drews Junior
-
Silvia Silva da Costa Botelho
-
Data: Nov 25, 2019
-
-
Show Abstract
-
Mainly when applied in the underwater environment, sonar simulation requires modelling complex acoustic physics and simultaneously rendering time-efficient data. Simulation of sonar operation allows evaluating algorithms and control systems without going to the real underwater environment; that reduces the costs and risks of in-field experiments. Existing methods focus on a basic implementation of one sonar device type with high computational cost, where most of the sound properties are disregarded. Towards a high fidelity virtualization with real time constraints, our proposed system is able to reproduce the operation of two main types of imaging sonars: mechanical scanning imaging sonar and forward-looking sonar. The underwater simulated scene is performed based on three frameworks: (i) Gazebo handles with hydrostatic and hydrodynamic forces, (ii) OpenSceneGraph renders the ocean visual effects, and (iii) ROCK framework manages the sonar in the virtual underwater scenario and exports simulation resources. The underwater simulated scene is then processed by a hybrid rendering pipeline on GPU: Rasterization computes the primary reflections between the sonar and observable surfaces based on deferred shading, while only the reflective areas are ray-traced. Also, the parallel ray-box routines on GPU also accelerated the intersection tests on ray-tracing algorithm. This approach launches few rays when compared to a full ray-tracing, achieving a significant performance gain without quality loss in the final image. Resulting reflections are then characterized as two sonar parameters: Echo intensity and pulse distance, being all calculated over insonified objects in the 3D rendered scene. Sonar-intrinsic parameters, such as speckle noise, transmission loss, reverberation and material properties of observable objects are also considered as part of the final acoustic image. Our evaluation demonstrated that the proposed system is able to operate close to real-world devices in terms of computation time. Also, our method demonstrated the effectiveness to render complex scenes with high quality when compared with real-world sonar images of similar scenes.
|
|
6
|
-
MARIANE DOURADO CORREIA
-
OPEN PLATFORM FOR INTEGRATION OF SERVICES IN DISTRIBUTED MANUFACTURING PROCESSES
-
Advisor : HERMAN AUGUSTO LEPIKSON
-
COMMITTEE MEMBERS :
-
EDUARDO MANUEL DE FREITAS JORGE
-
HERMAN AUGUSTO LEPIKSON
-
LEIZER SCHNITMAN
-
MANOEL GOMES DE MENDONCA NETO
-
SERGIO GORENDER
-
Data: Dec 9, 2019
-
-
Show Abstract
-
With the growing digital transformation that is a relevant part of the new industrial revolution that has already begun, companies need to restructure to adapt to new technologies and the possible changes that signal a moment of transition from a classic and centralized hierarchical model of management and control of companies. information for a new structure that enables the required agility, flexibility and interoperability characteristics of your systems. To the extent that data enable remote and intelligent decision-making, decentralization of decision making, configurability in the production line and service-oriented applications are also important, particularities imposed by Industry 4.0 (I4). Given this scenario, it is crucial to create conditions for this inevitable transition from the classic industrial model of the automation pyramid to a model that projects itself in the near future. These new models should allow legacy and increasingly distributed devices to coexist in an environment compatible with new I4 technologies and molds. A relevant issue to address is the interoperability between heterogeneous shop floor systems, especially when it comes to distributed systems. This research aims to develop an open platform for integration - PAI, which is based on the service-oriented architectural model (SOA), with the objective of enabling interoperability between legacy devices along the lines of Industry 4.0. From an analysis of the best solutions to address the interoperability issue of legacy shop floor systems, along with I4 technology trends, an effective solution based on tools already available has been developed. To validate the proposed platform, three experiments were performed simulating real plants with a focus on process control, where a system capable of allowing service oriented operations, in a modular and scalable manner, aiming at interconnectivity, interoperability and transparency was observed.
|
|