A novel neural model to electrical load forecasting in transformers

The paper describes a novel neural model to electrical load forecasting in transformers. The network acts as identifier of structural features to forecast process. So that output parameters can be estimated and generalized from an input parameter set. The model was trained and assessed through load data extracted from a Brazilian Electric Utility taking into account time, current, tension, active power in the three phases of the system. The results obtained in the simulations show that the developed technique can be used as an alternative tool to become more appropriate for planning of electric power systems.

Analysis of forecasting capabilities of ground surfaces valuation using artificial neural networks

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Electrical load forecasting formulation by a fast neural network

The objective of this work is to develop a methodology for electric load forecasting based on a neural network. Here, backpropagation algorithm is used with an adaptive process that based on fuzzy logic and using a decaying exponential function to avoid instability in the convergence process. This methodology results in fast training, when compared to the conventional formulation of backpropagation algorithm. The results are presented using data from a Brazilian Electric Company, and shows a very good performance for the proposal objective.

Electric load forecasting using a fuzzy ART&ARTMAP neural network

This work presents a neural network based on the ART architecture ( adaptive resonance theory), named fuzzy ART& ARTMAP neural network, applied to the electric load-forecasting problem. The neural networks based on the ARTarchitecture have two fundamental characteristics that are extremely important for the network performance ( stability and plasticity), which allow the implementation of continuous training. The fuzzy ART& ARTMAP neural network aims to reduce the imprecision of the forecasting results by a mechanism that separate the analog and binary data, processing them separately. Therefore, this represents a reduction on the processing time and improved quality of the results, when compared to the Back-Propagation neural network, and better to the classical forecasting techniques (ARIMA of Box and Jenkins methods). Finished the training, the fuzzy ART& ARTMAP neural network is capable to forecast electrical loads 24 h in advance. To validate the methodology, data from a Brazilian electric company is used. (C) 2004 Elsevier B.V. All rights reserved.

Multinodal Load Forecasting in Power Electric Systems using a Neural Network with Radial Basis Function

In this paper we present the results of the use of a methodology for multinodal load forecasting through an artificial neural network-type Multilayer Perceptron, making use of radial basis functions as activation function and the Backpropagation algorithm, as an algorithm to train the network. This methodology allows you to make the prediction at various points in power system, considering different types of consumers (residential, commercial, industrial) of the electric grid, is applied to the problem short-term electric load forecasting (24 hours ahead). We use a database (Centralised Dataset - CDS) provided by the Electricity Commission de New Zealand to this work.

Multi-Agent Simulation of Urban Social Dynamics for Spatial Load Forecasting

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

A Cellular Automaton Approach to Spatial Electric Load Forecasting

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Short-Term Multinodal Load Forecasting Using a Modified General Regression Neural Network

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Orientation dependence of stored energy of cold work in semi-processed electrical steels after temper rolling

Microhardness measurements were carried out in a low carbon lamination steel after 6% of temper rolling, in order to evaluate local variations of work hardening as a function of crystallographic orientation. EBSD (electron back scattered diffraction) was used to determine grain orientations with respect to individual rolling planes and rolling directions. Hardness was shown to increase with the local Taylor factor. TEM observations and a well-known dislocation hardening model were used to confirm the equivalence between hardness values and the stored energy of cold work. A definite correlation between stored energy and Taylor factors could therefore be established, being more consistent than previous data reported in the literature. The improvement was thought to be related to the rather small plastic deformation, during which Taylor factors could be considered to remain constant. (c) 2006 Elsevier B.V. All rights reserved.

Evaluation of strip rolling directly from the semi-solid state

defect metal alloy strip when thixorolling directly from the semi-solid state. To facilitate the study lead/tin alloys were chosen for their relatively low operating temperature. The objective is to extrapolate these findings to the higher temperature aluminium, alloys. Three alloys (70%Pb30%Sn, 60%Pb-40%Sn, 50%Pb-50%wtSn) were used particularly to study the influence of the solidification interval. The equipment consists of a two roll mill arranged as an upper and lower roller, where both rollers are driven at a controlled speed. The lower roller is fed with semi solid alloy through a ceramic nozzle attached to the lower end of a cooling slope. Several types of nozzle and their position at the roller were tested. This produced different solidifications and consequently different finished strip. The alloys were first cast and then poured onto the cooling slope through a tundish in order to create a continuous laminar flow of slurry and uniformity of metal strip quality. The pouring was tested at different positions along the slope. The cooling slope was coated with colloidal graphite to promote a smooth slurry flow and avoid the problem of adherence and premature solidification. The metallic slurry not only cools along the slope but is also initially super-cooled to a mush by the lower roller whilst at room temperatures, thus enabling thixorolling. It was also found that the nozzle position could be adjusted to enable the upper roller to also contribute to the solidification of the metallic slurry. However the rollers and the cooling slope naturally heat up. Temperature distribution in these zones was analysed by means of three thermocouples positioned along the cooling slope and a fourth in the base of the semi solid pool within the nozzle. The objective being to design an optimum pouring and cooling system. The formed strip was cooled down to room temperature with a shower of water. Microstructures of the thixorolling process were analysed. The differences in solidification conditions resulted in differing qualities of finished strip and corresponding defect types, all of which are a serious quality issue for the rolled product.

A model to predict R134a refrigerant leakage through the radial clearance of rolling piston compressors

In this paper a non-isothermal two-phase model for oil-R134a refrigerant mixture flow is presented to predict the R134a leakage through the radial clearance of rolling piston compressors. The flow is divided in a liquid single-phase region and in a two-phase region, in which the homogeneous model is used to simulate the flow. The refrigerant leakage is determined using the mixture mass flow rate and the refrigerant mass fraction variation along the flow. The results are obtained for inlet pressures varying from 200 to 700 kPa, inlet temperatures ranging from 40 to 60 degrees C, and minimal clearances between 10 and 60 mu m. The results are firstly compared to existing isothermal model data, showing that there is a significant difference between the leakage flow rates predicted by isothermal and non-isothermal models. Finally, a useful general equation for compressor designers is proposed to calculate the refrigerant leakage for a large range of operation conditions. (C) 2012 Elsevier Ltd and IIR. All rights reserved.

Effect of mangiferin on the development of periodontal disease: Involvement of lipoxin A(4), anti-chemotaxic action in leukocyte rolling

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Performance comparisons of the kicking of stationary and rolling balls in a futsal context

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Rolling technique for treatment of left displacement of the large colon in horses: 11 cases (2004-2009)

Durante o período de 2004 a 2009, 11 animais foram tratados para o deslocamento à esquerda do cólon maior, por meio da técnica de rolamento sob anestesia geral, com uma técnica distinta das demais previamente descritas. A seleção dos casos foi baseada nos achados da palpação retal e confirmada ultrassonograficamente. Nove animais foram tratados com sucesso e dois foram submetidos ao tratamento cirúrgico após três tentativas de rolamento. Não foram observadas complicações decorrentes do procedimento a curto e a longo prazos. Somente um animal apresentou recidiva do quadro clínico 10 meses após o tratamento e foi novamente submetido ao rolamento. Apesar da diferença com relação às outras técnicas, esta também se mostrou eficaz. O rolamento, mesmo quando realizado mais de uma vez, mostrou ser um procedimento seguro, porém enfatiza-se a necessidade de cuidados especiais aos animais após a sua realização, pois medidas emergenciais podem ser necessárias caso complicações decorrentes desta técnica ocorram.

Spatial electric load forecasting using an evolutionary heuristic

A method for spatial electric load forecasting using elements from evolutionary algorithms is presented. The method uses concepts from knowledge extraction algorithms and linguistic rules' representation to characterize the preferences for land use into a spatial database. The future land use preferences in undeveloped zones in the electrical utility service area are determined using an evolutionary heuristic, which considers a stochastic behavior by crossing over similar rules. The method considers development of new zones and also redevelopment of existing ones. The results are presented in future preference maps. The tests in a real system from a midsized city show a high rate of success when results are compared with information gathered from the utility planning department. The most important features of this method are the need for few data and the simplicity of the algorithm, allowing for future scalability.