Navegando por Assunto "Power systems"

Agora exibindo 1 - 4 de 4

Acesso aberto (Open Access)
Estratégia de otimização para a melhoria da interpretabilidade de redes bayesianas: aplicações em sistemas elétricos de potência
(Universidade Federal do Pará, 2009-12-10) ROCHA, Cláudio Alex Jorge da; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
The study of methods, techniques and tools that can aid the decision processes in power systems, in its many sections, is a subject of great interest. This decision support can be accomplished through many different techniques, particularly those based on computational intelligence, given their applicability on domains with uncertainty. In this proposal, Bayesian networks are used for the extraction of knowledge models from the available data on power systems. Moreover, given the demands of these systems and some limitations imposed to the inferences in Bayesian networks, a method is proposed, using genetic algorithms, capable of extending the power of comprehensibility of the patterns discovered; it aims at finding the optimal scenario in order to attain a given target, considering the incorporation of a priori knowledge from domain specialists, identifying the most influent variables in the domain for the maximization of the target variable.
Acesso aberto (Open Access)
Influências de famílias wavelets e suas ordens no desempenho de um localizador de faltas em linhas aéreas de transmissão de energia elétrica
(Universidade Federal do Pará, 2011-11-04) ARAUJO, Maryson da Silva; BARRA JUNIOR, Walter; http://lattes.cnpq.br/0492699174212608; BARREIROS, José Augusto Lima; http://lattes.cnpq.br/1246564618922453
This dissertation objective to analyze the influence of wavelets families and their orders in the performance of a fault location algorithm through the traveling waves from two ends of an overhead transmission line. Then, a secondary objective is the modelling of an electric power system (EPS) to obtaining of a fault’s universe to validate the algorithm. For that, part of an EPS of the Eletrobrás-Eletronorte on 500/230 kV was modeled in Alternative Transient Program (ATP) using real parameters. The Wavelet Transform, through multiresolution analysis (MRA), it’s used because its time domain localization characteristic to allow characterizations of electromagnetic transitory moments caused by contingencies. The waves generated by faults traveling towards the line’s terminals containing the wave propagation times from defect point at the terminals and these times can be conveniently extracted for such transformed. By means of the methodology adopted in the algorithm, the difference between those times determines the fault occurrence place on the line with good accuracy. However, one of the error variant agents in the estimation it’s the selection of the wavelet used in MRA of the signals, therefore the evaluation of that choice upon those errors, the main objective of this work, it’s justified for the still inexistent scientific bases that assure the choice of a great wavelet to a certain application. Among a diversity of discrete wavelets, appropriated results were obtained for 16 of them with maximum errors smaller than 250 meters, stipulated precision adopted. Two wavelets, Db15 and Sym17, were more exact than the others, respectively, 3.5 and 1.1 times. The methodology to get those results consists of the: export of the fault data files from ATP for MATLAB®; application of the Clarke’s modal transformation of voltages; decomposition of alpha modes and synthesis of the levels 1 of details through AMR; calculation of their maximum magnitudes and time indexes determination; finally, the traveling waves theory is used to formulate the estimate equation of the contingency place on the line. All methodology was programmed in MATLAB and the errors’ statistical analysis was made in Microsoft Excell®. At the end, a GUI (Guide User Interface) for (Human Machine Interface) HMI of locator was elaborated, which is also a graphical analysis interface, no matter which the contingency applied to the EPS. The attained results demonstrate an improved performance in reason of the most appropriate wavelet selection to the algorithm and they suggest a practical application of the locator.
Acesso aberto (Open Access)
Localização de falhas em linhas de transmissão utilizando decomposição harmônica e redes neurais artificiais
(Universidade Federal do Pará, 2006-07-05) GOMES, Cristiane Ruiz; VIEIRA JÚNIOR, Petrônio; http://lattes.cnpq.br/1958791286192330
This work proposes a new methodology for fails location in transmission lines. This methodology consists in using harmonic decomposition of the leakage current and in the application of an Artificial Neural Network (ANN), this is able to recognize patterns of normal and fails conditions of a transmission line. It was developed a Pi model capable to use real data of voltage and current of the three phases. In this model values of capacitance, inductance and resistance can be modified in agreement of weather conditions. Fails were generated in all the towers with different values of capacitance. The input/output data were used to train the neural network. The real voltage and current data acquisition were done by instruments installed in the two terminals of the Guamá-Utinga transmission line belonging to Centrais Elétricas do Norte - ELETRONORTE. The computation of the parameters was made by the well known matricial method and was improved by Finite Element Method. An ANN was developed with Matlab software. For training the ANN it was used the backpropagation resilient algorithm, which presented good performance, been fast and accurate. The ANN was trained by two different sets to analyze differences between outputs. In the two cases results were satisfactory.
Acesso aberto (Open Access)
Metodologia de controle preventivo baseado em árvore de decisão para a melhoria da segurança estática e dinâmica de sistemas elétricos de potência
(Universidade Federal do Pará, 2015-12-05) GAIA, Dieigo Sá; BEZERRA, Ubiratan Holanda; http://lattes.cnpq.br/6542769654042813; VIEIRA, João Paulo Abreu; http://lattes.cnpq.br/8188999223769913
This work aims to present a set of computational tools to support the real time operation and preventive control to enhance the static and dynamic security of power systems. The data mining technique known as decision tree was utilized to determine power system operating state as well as to provide operating guidelines for the preventing control actions necessary to avoid continuous decline of bus voltages and transient instability problems. Preliminary tests were carried out using operation historical data collected by SCADA/SAGE host located at Eletrobrás Eletronorte's regional control center. The obtained results validated the set of computational tools and also demonstrated the prospective application in real time operating environment.