Neurules are a kind of hybrid rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Thus, the corresponding neurule base consists of a number of autonomous adaline units (neurules). Due to this fact, a modular and natural knowledge base is constructed, in contrast to existing connectionist knowledge bases. In this paper, we present a method for g...

In the paper, some problems of the methods that are used to analyze the power quality issues are firstly pointed out. A kind of Artificial Neural Networks, Adaline, and its new algorithm for analysis of power quality are presented. The new algorithm has the advantages of being simply calculated and easily implemented through hardware. The simulating results of voltage quality disturbances detec...

It was demonstrated in 1964 by F.W. Smith and B. Widrow that a neural network used as an adaptive controller could be trained to stabilize an inverted pendulum fixed to a non-stationary platform or cart (the "broom-balancer"). The critical state variables (pendulum angle, pendulmn angular velocity, cart position, cart velocity) were measured and fed to the system in digital form. An unrealized ...

This paper concerns an adaptive finite element method for the elliptic obstacle problem.We consider the formulation of the problem as an elliptic variational inequation.The adaptive algorithm (modified Uzawa adaptive method)we construct is based on a combination of the Uzawa method associated with the corresponding multivalued operator and a convergent adaptive mehtod for the linear problem. As...

A rigorous mathematical analysis is presented of an adaline-like network operating in continuous time with spatially continuous inputs and outputs. Weights adapt continually, whether or not a training signal is present. It is shown that consistent input-output pairs can be learned perfectly provided every pattern is repeated at least once in every N successive inputs, and the input patterns are...

Adaptive threshold logic elements called ADALINES can be used in trainable pattern recognition systems. Adaptation by the LMS (least mean squares) algorithm is discussed. Threshold logic elements only realize linearly separable functions. To implement more elaborate classification functions, multilayered ADALINE networks can be used. A pattern recognition concept involving first an “invariance ...

some numerical and experimental investigations are made on the performance of five different hyperelastic constitutive models (second order polynomial, yeoh, arruda-boyce, ogden and marlow) in tension and compressionmodes. first, the results of the tensile and compression tests on a rubber sample were used to determine the parameters of the models by curve fitting methods. next, by using an alg...