Absrraa -Electric energy demand forecasting represents a fundamental information to plan the activities of the companies that generate and distribute it. So a good prediction of its demand will provide an invaluable tool to plan the production and purchase policies of both generation and distribution or reseller companies. This demand may be seen as a temporal series when its data are conveniently arranged. In this way the prediction of a future value may be performed stud,ying the past ones. Neural networks have proved to be a very powerful tool to do this. They are mathematical structures thalt mimic that of the nervous system of living beings and are used extensively for system identification and prediction of their future evolution. In this work a neural network is presented1 to predict the evolution of the monthly demand of electric consumption. A Feedforward Multilayer Perceptron (MLP) has been used as neural model with Backpropagation as learning strategy. The network has three hidden layers with a 8-4-8 distribution. It takes twelve past values to predict the following one. Errors smaller than 5% have been obtained in most of the predictions.

No abstract

No abstract

The liquid bridge can be used either as an accelerometer for steady accelerations or as a tensiometer. This can be done by fitting the theoretical predictions to the observed contours. The procedure involves two calculations. First, the contour has to be recognized in a liquid bridge image. The result is either a curve or a set of points which represent the contour. Second, the values of the parameters characterizing the contour have to be inferred by fitting the theoretical predictions. In this contribution, a method to perform this double calculation is presented. The method is used to measure both the volume of the liquid bridge and the Bond number in several experiments. The results are compared with those obtained from a procedure established previously. Finally, the relative advantages of the two methods are discussed.

No abstract