DECAT - Departamento de Controle e Automação
URI permanente desta comunidadehttp://www.hml.repositorio.ufop.br/handle/123456789/490
Navegar
4 resultados
Resultados da Pesquisa
Item Automatic system for visual detection of dirt buildup on conveyor belts using convolutional neural networks.(2020) Santos, André Almeida; Rocha, Filipe Augusto Santos; Reis, Agnaldo José da Rocha; Guimarães, Frederico GadelhaConveyor belts are the most widespread means of transportation for large quantities of materials in the mining sector. Therefore, autonomous methods that can help human beings to perform the inspection of the belt conveyor system is a major concern for companies. In this context, we present in this work a novel and automatic visual detector that recognizes dirt buildup on the structures of conveyor belts, which is one of the tasks of the maintenance inspectors. This visual detector can be embedded as sensors in autonomous robots for the inspection activity. The proposed system involves training a convolutional neural network from RGB images. The use of the transfer learning technique, i.e., retraining consolidated networks for image classification with our collected images has shown very effective. Two different approaches for transfer learning have been analyzed. The best one presented an average accuracy of 0.8975 with an F-1 Score of 0.8773 for the dirt recognition. A field validation experiment served to evaluate the performance of the proposed system in a real time classification task.Item A self-adaptive evolutionary fuzzy model for load forecasting problems on smart grid environment.(2016) Coelho, Vitor Nazário; Coelho, Igor Machado; Coelho, Bruno Nazário; Reis, Agnaldo José da Rocha; Enayatifar, Rasul; Souza, Marcone Jamilson Freitas; Guimarães, Frederico GadelhaThe importance of load forecasting has been increasing lately and improving the use of energy resources remains a great challenge. The amount of data collected from Microgrid (MG) systems is growing while systems are becoming more sensitive, depending on small changes in the daily routine. The need for flexible and adaptive models has been increased for dealing with these problems. In this paper, a novel hybrid evolutionary fuzzy model with parameter optimization is proposed. Since finding optimal values for the fuzzy rules and weights is a highly combinatorial task, the parameter optimization of the model is tackled by a bio-inspired optimizer, so-called GES, which stems from a combination between two heuristic approaches, namely the Evolution Strategies and the GRASP procedure. Real data from electric utilities extracted from the literature are used to validate the proposed methodology. Computational results show that the proposed framework is suitable for short-term forecasting over microgrids and large-grids, being able to accurately predict data in short computational time. Compared to other hybrid model from the literature, our hybrid metaheuristic model obtained better forecasts for load forecasting in aMG scenario, reporting solutions with low variability of its forecasting errors.Item Multi-objective energy storage power dispatching using plug-in vehicles in a smart-microgrid.(2016) Coelho, Vitor Nazário; Coelho, Igor Machado; Coelho, Bruno Nazário; Cohen, Miri Weiss; Reis, Agnaldo José da Rocha; Silva, Sidelmo Magalhães; Souza, Marcone Jamilson Freitas; Fleming, Peter J.; Guimarães, Frederico GadelhaThis paper describes a multi-objective power dispatching problem that uses Plug-in Electric Vehicle (PEV) as storage units.We formulate the energy storage planning as a Mixed-Integer Linear Programming (MILP) problem, respecting PEV requirements, minimizing three different objectives and analyzing three different criteria. Two novel cost-to-variability indicators, based on Sharpe Ratio, are introduced for analyzing the volatility of the energy storage schedules. By adding these additional criteria, energy storage planning is optimized seeking to minimize the following: total Microgrid (MG) costs; PEVs batteries usage; maximum peak load; difference between extreme scenarios and two Sharpe Ratio indices. Different scenarios are considered, which are generated with the use of probabilistic forecasting, since prediction involves inherent uncertainty. Energy storage planning scenarios are scheduled according to information provided by lower and upper bounds extracted from probabilistic forecasts. A MicroGrid (MG) scenario composed of two renewable energy resources, a wind energy turbine and photovoltaic cells, a residential MG user and different PEVs is analyzed. Candidate non-dominated solutions are searched from the pool of feasible solutions obtained during different Branch and Bound optimizations. Pareto fronts are discussed and analyzed for different energy storage scenarios. Perhaps the most important conclusion from this study is that schedules that minimize the total system cost may increase maximum peak load and its volatility over different possible scenarios, therefore may be less robust.Item A cognitive system for fault prognosis in power transformers.(2015) Sica, Fernando Cortez; Guimarães, Frederico Gadelha; Duarte, Ricardo de Oliveira; Reis, Agnaldo José da RochaThe power transformer is one of the most critical and expensive equipments in an electric power system.If it is out of service in an unexpected way, the damage for both society and electric utilities is verysignificant. Over the last decades, many computational tools have been developed to monitor the ‘health’of such an important equipment. The classification of incipient faults in power transformers via DissolvedGas Analysis (DGA) is, for instance, a very well known technique for this purpose. In this paper we presentan intelligent system based on cognitive systems for fault prognosis in power transformers. The proposedsystem combines both evolutionary and connectionist mechanisms into a hybrid model that can bean essential tool in the development of a predictive maintenance technology, to anticipate when anyequipment fault might occur and to prevent or reduce unplanned reactive maintenance. The proposedprocedure has been applied to real databases derived from chromatographic tests of power transformersfound in the literature. The obtained results are fully described showing the feasibility and validity ofthe new methodology. The proposed system can help Transformer Predictive Maintenance programmesoffering a low cost and highly flexible solution for fault prognosis.