Identificação não linear usando uma rede fuzzy wavelet neural network modificada

In last decades, neural networks have been established as a major tool for the identification of nonlinear systems. Among the various types of networks used in identification, one that can be highlighted is the wavelet neural network (WNN). This network combines the characteristics of wavelet multiresolution theory with learning ability and generalization of neural networks usually, providing more accurate models than those ones obtained by traditional networks. An extension of WNN networks is to combine the neuro-fuzzy ANFIS (Adaptive Network Based Fuzzy Inference System) structure with wavelets, leading to generate the Fuzzy Wavelet Neural Network - FWNN structure. This network is very similar to ANFIS networks, with the difference that traditional polynomials present in consequent of this network are replaced by WNN networks. This paper proposes the identification of nonlinear dynamical systems from a network FWNN modified. In the proposed structure, functions only wavelets are used in the consequent. Thus, it is possible to obtain a simplification of the structure, reducing the number of adjustable parameters of the network. To evaluate the performance of network FWNN with this modification, an analysis of network performance is made, verifying advantages, disadvantages and cost effectiveness when compared to other existing FWNN structures in literature. The evaluations are carried out via the identification of two simulated systems traditionally found in the literature and a real nonlinear system, consisting of a nonlinear multi section tank. Finally, the network is used to infer values of temperature and humidity inside of a neonatal incubator. The execution of such analyzes is based on various criteria, like: mean squared error, number of training epochs, number of adjustable parameters, the variation of the mean square error, among others. The results found show the generalization ability of the modified structure, despite the simplification performed

Análise de antenas de microfita em rampa com múltiplas camadas dielétricas

The present work deals with the ana1ysis of microstrip patch antennas printed on tapered dielectric substrates. We investigate the influence ofthe substrate height variations on the properties of configurations such as microstrip patch antennas, microstrip patch antennas with overlay and suspendeô microstrip patch antennas. The dielectric substrates can be isotropic or anisotropic ones. This accurate analysis is based on the full-wave formulation. It is carried out initially for the determination of the impedance matrix, through the use of the spectral¬domain immitance approach. We use a model based on a segmentation of the considered line into uniform microstrip line subsections. Normalized phase constants and characteristic impedances are obtained by means of the Galerkin numerical technique. Then, the cascaded combination of the uniform microstrip subsections are analyzed through an interactive procedure. Numerical results are presented for the input reflection coefficient, voltage standing wave ratio, resonant frequency, and radiation pattems ofthe E_plane and H-plane diagrams. It is found that the variations in the substrate height profile produce a great influence on the bandwidth of microstrip antennas. This procedure gives bandwidth improvements without altering considerably the resonant frequency. Furthermore, the tapered microstrip antenna can be used as a lightweight altemative for bandwidth control and to eXtend the use of microstiip antenna technology to a wider variety of applications. Finally, suggestions for the continuity of this work are presented