Search

In this paper, an integrated quantum inspired GA (QGA) based generalized neural network (QGA–GNN) has been developed. The QGA–GNN is used for estimation of stator resistance of a 5 hp three phase induction motor (3Φ I.M.) under different healthy and unhealthy working conditions. The experimentation is performed in the laboratory for estimating stator winding resistance under healthy and faulty (i.e., 10, 20, 30, or 40% short circuited) conditions. The motor current and motor speed are considered as input and stator resistance as output of the proposed technique. The results obtained from QGA–GNN are compared with the ANN and GNN. QGA–GNN is giving good results under different working conditions. [ABSTRACT FROM AUTHOR]

A self-tuned fuzzy logic power system stabilizer to enhance the damping of power system oscillations is presented. The design of the self-tuned fuzzy logic power system stabilizer is based on a simple fuzzy logic controller that possesses a significantly reduced rule base, a small number of tuning parameters, and is implemented through a simple control algorithm and architecture. The control structure of the self-tuned fuzzy logic power system stabilizer consists of the simple fuzzy logic controller and a fuzzy tuner. The fuzzy tuner is used to non-linearly modify on-line the sensitivity of the simple fuzzy logic controller to its input variable, which indirectly changes the relative sensitivity of areas of associated input membership functions. [ABSTRACT FROM AUTHOR]

A model reference adaptive fuzzy controller (MRAFC) consisting of a reference model and self-learning fuzzy logic controller and its application as a power system stabilizer (PSS) is described in this article. Off-line model identification is used to obtain a dynamic equivalent model for the synchronous machine with respect to the rest of the system. This model is used as the basis for defining a reference model for the generating unit. A fuzzy controller with self-learning capability is then used to adapt the system performance to track the reference model. The self-learning ability of the fuzzy controller is based on the steepest descent algorithm. The effectiveness of the proposed adaptive PSS based on this technique is demonstrated. Results obtained show improvement in the overall system damping characteristics using the proposed adaptive PSS. [ABSTRACT FROM AUTHOR]

This paper proposes a numerical taxonomy-based method for short-term load forecasting. The method is formulated as an optimization problem using MAPE as an objective function. The data matrix andthe cluster size are optimization variables. The accuracy of the method is demonstrated on a practical system data. Two models are developed using the proposed method. Model 1 uses two temperature variables and Model 2 uses two load and two temperature variables. Both models were compared with 35 input supervised back propagation model [8] and 6 input unsupervised/supervised radial basis function [15] reported in literature for the data of the same system. It is observed that both the models gave better prediction than feed forward neural network and radial basis function neural networks. [ABSTRACT FROM AUTHOR]

Detection of the direction of a fault on a transmission line is essential to the proper performance of a power system. W ith the advent of large generating stations and highly interconnected power systems, shorter fault clearing times are becoming necessary. To classify forward and backward faults on a given line rapidly, a neural network's abilities in pattern recognition and classification could be considered as a solution. To demonstrate the applicability of this solution, neural network technique is employed to design two different fault direction discrimination modules. Results of performance studies with the proposed networks are presented in this paper. Results obtained indicate that the direction of fault on a transmission line can be identified rapidly and correctly by the proposed approaches. [ABSTRACT FROM AUTHOR]