Loading...
20 results
Search Results
Now showing 1 - 10 of 20
- Identification of aircraft gas-turbine dynamics using B-splines neural networksPublication . Lopes, J. C.; Ruano, Antonio; Fleming, P. J.This paper describes preliminary results regarding the development of a B-splines neural network model of the fuel feed to shaft-speed dynamics of a twin-shaft gas turbine engine. Data recorded from practical testing of the turbine to a multisine input were employed, and models were identified at different points along the turbine operating curve. B-splines neural networks have been found to be good models of the system, delivering good results especially for long-range predictions.
- Web-based learning: a complementary approach to standard teachnig schemesPublication . Martins, L.; Arsenio, L.; Ruano, AntonioWeb Based Learning is increasingly attracting the interest of several teaching Institutions. It provides mechanisms for improving the conventional learning process, and also allows the opportunity for reaching new students, throughout the world, by just using an Internet connection. This paper describes the objectives of an Europeanfunded project in this area, the features found in current Web-design tools, and our own first experiences within this new teaching scheme.
- A WWW-based learning environment to complement a university course on neural networksPublication . Martins, L.; Silva, C.; Rodrigues, C.; Ruano, AntonioWeb Based Learning is increasingly attracting the interest of several teaching Institutions. It provides mechanisms for improving the conventional learning process, and also allows the opportunity for reaching new students, throughout the world, by just using an Internet connection. This paper describes a tool that is being built in the University of Algarve, to complement an optional course on Neural Networks. This tool incorporates multimedia material to explain visually important concepts, integrates Matlab, and will allow self-assessment and automatic student marking.
- Predicting solar radiation with RBF neural networksPublication . Ferreira, P. M.; Ruano, AntonioIn this paper radial basis function neural networks are applied to the prediction of global solar radiation. The networks are employed as one-step-ahead predictors of the solar radiation time series and iterated over time to obtain longer term predictions. Several models are compared varying the input dimension, the network size and the time series sampling rate. An empiric rule is proposed for network input selection. All networks are trained using one data set and evaluated for prediction performance on unseen data. Predictor performance is assessed taking root mean square measures of the error over the prediction horizon. The aim of this work is to select a model to be used in a climate simulator for an hydroponic greenhouse.
- Speeding up a learning algorithm for multilayer perceptrons using the MAPS EnvironmentPublication . Daniel, H. A.; Ruano, AntonioArtificial neural networks, as non-linear adaptive elements, have been proposed for applications in adaptive control. Their ability to accurately approximate large classes of non-linear functions made them also a valuable tool for non-linear systems identification. However, in some cases, the parameter estimation phase may take considerable amount of time, and this is crucial in real-time applications. One way of speeding up these learning algorithms consists in executing them over a multiprocessor system. In this paper an implementation over MAPS integrated development environment, which automatically generates a parallel application from a sequential description of a learning algorithm for multilayer perceptrons is presented.
- An internet-based course on neural networksPublication . Rodrigues, C.; Ruano, AntonioWeb based instruction is increasingly attracting the interest of Universities. In this paper, an Internet based course on neural networks, developed in the University of Algarve, is discussed. A special attention is given to techniques of student self-assessment. A structure of knowledge, to enable the automatic creation of on-line courses, is proposed.
- Comparison of on-line learning algorithms for RBF models in greenhouse environmental control problemsPublication . Ferreira, P. M.; Faria, E. A.; Ruano, AntonioThe problem with the adequacy of radial basis function neural networks to model the inside air temperature as a function of the outside air temperature and solar radiation, and the inside relative humidity in an hydroponic greenhouse is addressed.
- Automatic tuning of PID controllers using a neuro-genetic systemPublication . Ruano, Antonio; Lima, João; Azevedo, Ana Beatriz da Piedade de; Duarte, N. M.; Fleming, P. J.Neural networks and genetic algorithms have been in the past successfully applied, separately, to controller turning problems. In this paper we propose to combine its joint use, by exploiting the nonlinear mapping capabilites of neural networks to model objective functions, and to use them to supply their values to a genetic algorithm which performs on-line minimization.
- Comparison of off-line and on-line performance of alternative neural network modelsPublication . Lima, João; Ruano, AntonioThe Proportional Integral and Derivative (PID) controller is often used in industrial applications due to its functional simplicity and robust performance. Autotuning methods for these simple controllers are economically important. In order to accomplish this auto tuning in real time, without perturbing the closed-loop operation, models of criteria that are intended to be optimised are needed. In this paper, the ITAE criterion will be employed, as responses obtained with this criterion are well damped. In this paper neural networks are proposed as tools that allow these kinds of mappings. To improve the autotuner performance in a continuous operation, these models should be updated online. This way, the corresponding neural networks, after being trained off-line should be adapted on-line in real time. In the present work, the off-line and on-line performances of Multi-layer Perceptrons (MLPs), Radial Basis Function (RBFs) and Basis-Spline neural networks (B-splines), are analysed and compared.
- Regressive and non-regressive RBFNN estimators in non-invasive temperature estimationPublication . Teixeira, C. A.; Ruano, M. Graça; Ruano, Antonio; Pereira, W. C. A.In this paper two modelling strategies were applied for non-invasive temperature estimation in a gel-based phantom subjected to physiotherapeutic ultrasound. The two strategies differ in the consideration of regressive or nonregressive radial basis functions neural networks (RBFNN) structures. The gel-based phantom was heated using four different ultrasound intensities. Temperature was monitored at five points inside the phantom, where temperature is to be estimated. The best regressive model reaches a mean maximum absolute error of 0.4 ºC, against 0.8 ºC presented by the best non-regressive model. The regressive strategy presented better error performance with a smaller computational complexity. Thus, being the appropriate one for real-time temperature monitoring in hyperthermia/diathermia procedures, where resolutions below 0.5 ºC are required.