Ganapati Panda

Identification of nonlinear dynamic systems using functional link artificial neural networks

We have presented an alternate ANN structure called functional link ANN (FLANN) for nonlinear dynamic system identification using the popular backpropagation algorithm. In contrast to a feedforward ANN structure, i.e., a multilayer perceptron (MLP), the FLANN is basically a single layer structure in which nonlinearity is introduced by enhancing the input pattern with nonlinear functional expansion. With proper choice of functional expansion in a FLANN, this network performs as good as and in some cases even better than the MLP structure for the problem of nonlinear system identification.

Frequency estimation of distorted power system signals using extended complex Kalman filter

The paper proposes an extended complex Kalman filter and employs it for the estimation of power system frequency in the presence of random noise and distortions. From the discrete values of the 3-phase voltage signals of a power system, a complex voltage vector is formed using the well known /spl alpha//spl beta/-transform. A nonlinear state space formulation is then obtained for this complex signal and an extended Kalman filtering approach is used to compute the true state of the model iteratively with significant noise and harmonic distortions. As the frequency is modeled as a state, the estimation of the state vector yields the unknown power system frequency. Several computer simulations test results are presented in the paper to highlight the usefulness of this approach in estimating near nominal and off-nominal power system frequencies.

Fault Classification and Section Identification of an Advanced Series-Compensated Transmission Line Using Support Vector Machine

Distance protection of flexible ac transmission lines, including the thyristor-controlled series compensator (TCSC), static synchronous compensator, and static var compensator has been a very challenging task. This paper presents a new approach for the protection of TCSC line using a support vector machine (SVM). The proposed method uses postfault current samples for half cycle (ten samples) from the inception of the fault and firing angle as inputs to the SVM. Three SVMs are trained to provide fault classification, ground detection, and section identification, respectively, for the line using TCSC. The SVMs are trained with polynomial kernel and Gaussian kernel with different parameter values to get the most optimized classifier. The proposed method converges very fast with fewer numbers of training samples compared to neural-network and neuro-fuzzy systems which indicates fastness and accuracy of the proposed method for protection of the transmission line with TCSC

Active mitigation of nonlinear noise Processes using a novel filtered-s LMS algorithm

In many practical applications the acoustic noise generated from dynamical systems is nonlinear and deterministic or stochastic, colored, and non-Gaussian. It has been reported that the linear techniques used to control such noise exhibit degradation in performance. In addition, the actuators of an active noise control (ANC) system very often have nonminimum-phase response. A linear controller under such situations can not model the inverse of the actuator, and hence yields poor performance. A novel filtered-s least mean square (FSLMS) algorithm based ANC structure, which functions as a nonlinear controller, is proposed in this paper. A fast implementation scheme of the FSLMS algorithm is also presented. Computer simulations have been carried out to demonstrate that the proposed algorithm outperforms the standard filtered-x least mean square (FXLMS) algorithm and even performs better than the recently proposed Volterra filtered-x least mean square (VFXLMS) algorithm, in terms of mean square error (MSE), for active control of nonlinear noise processes. An evaluation of the computational requirements shows that the FSLMS algorithm offers a computational advantage over VFXLMS when the secondary path estimate is of length less than 6. However, the fast implementation of the FSLMS algorithm substantially reduces the number of operations compared to that of FSLMS as well as VFXLMS algorithm.

Brief Communication: A novel feature representation method based on Chou's pseudo amino acid composition for protein structural class prediction

During last few decades accurate determination of protein structural class using a fast and suitable computational method has been a challenging problem in protein science. In this context a meaningful representation of a protein sample plays a key role in achieving higher prediction accuracy. In this paper based on the concept of Chous pseudo amino acid composition (Chou, K.C., 2001. Proteins 43, 246-255), a new feature representation method is introduced which is composed of the amino acid composition information, the amphiphilic correlation factors and the spectral characteristics of the protein. Thus the sample of a protein is represented by a set of discrete components which incorporate both the sequence order and the length effect. On the basis of such a statistical framework a simple radial basis function network based classifier is introduced to predict protein structural class. A set of exhaustive simulation studies demonstrates high success rate of classification using the self-consistency and jackknife test on the benchmark datasets.

Nonlinear channel equalization for QAM signal constellation using artificial neural networks

Application of artificial neural networks (ANNs) to adaptive channel equalization in a digital communication system with 4-QAM signal constellation is reported in this paper. A novel computationally efficient single layer functional link ANN (FLANN) is proposed for this purpose. This network has a simple structure in which the nonlinearity is introduced by functional expansion of the input pattern by trigonometric polynomials. Because of input pattern enhancement, the FLANN is capable of forming arbitrarily nonlinear decision boundaries and can perform complex pattern classification tasks. Considering channel equalization as a nonlinear classification problem, the FLANN has been utilized for nonlinear channel equalization. The performance of the FLANN is compared with two other ANN structures [a multilayer perceptron (MLP) and a polynomial perceptron network (PPN)] along with a conventional linear LMS-based equalizer for different linear and nonlinear channel models. The effect of eigenvalue ratio (EVR) of input correlation matrix on the equalizer performance has been studied. The comparison of computational complexity involved for the three ANN structures is also provided.

A survey on nature inspired metaheuristic algorithms for partitional clustering

Abstract The partitional clustering concept started with K-means algorithm which was published in 1957. Since then many classical partitional clustering algorithms have been reported based on gradient descent approach. The 1990 kick started a new era in cluster analysis with the application of nature inspired metaheuristics. After initial formulation nearly two decades have passed and researchers have developed numerous new algorithms in this field. This paper embodies an up-to-date review of all major nature inspired metaheuristic algorithms employed till date for partitional clustering. Further, key issues involved during formulation of various metaheuristics as a clustering problem and major application areas are discussed.

IIR system identification using cat swarm optimization

Conventional derivative based learning rule poses stability problem when used in adaptive identification of infinite impulse response (IIR) systems. In addition the performance of these methods substantially deteriorates when reduced order adaptive models are used for such identification. In this paper the IIR system identification task is formulated as an optimization problem and a recently introduced cat swarm optimization (CSO) is used to develop a new population based learning rule for the model. Both actual and reduced order identification of few benchmarked IIR plants is carried out through simulation study. The results demonstrate superior identification performance of the new method compared to that achieved by genetic algorithm (GA) and particle swarm optimization (PSO) based identification.

A radial basis function neural network controller for UPFC

This paper presents the design of radial basis function neural network controllers (RBFNN) for UPFC to improve the transient stability performance of a power system. The RBFNN uses either a single neuron or multi-neuron architecture and the parameters are dynamically adjusted using an error surface derived from active or reactive power/voltage deviations at the UPFC injection bus. The performance of the new single neuron controller is evaluated using both single-machine infinite-bus and three-machine power systems subjected to various transient disturbances. In the case of three-machine 8-bus power system, the performance of the single neuron RBF controller is compared with a BP (backpropagation) algorithm based multi-layered ANN controller. Further it is seen that by using a multi-input multi-neuron RBF controller, instead of a single neuron one, the critical clearing time and damping performance are improved. The new RBFNN controller for UPFC exhibits a superior damping performance in comparison to the existing PI controllers. Its simple architecture reduces the computational burden thereby making it attractive for real-time implementation.

Artificial neural network-based nonlinearity estimation of pressure sensors

A new approach to pressure sensor modeling based on a simple functional link artificial neural network (FLANN) is proposed. The response of the sensor is expressed in terms of its input by a power series. In the direct modeling, using a FLANN trained by a simple neural algorithm, the unknown coefficients of the power series are estimated accurately. The FLANN-based inverse model of the sensor can estimate the applied pressure accurately. The maximum error between the measured and estimated values is found to be only /spl plusmn/2%. The existing techniques utilize ROM or nonlinear schemes for linearization of the sensor response. However, the proposed inverse model approach automatically compensates the effect of the associated nonlinearity to estimate the applied pressure. Frequent modification of the ROM or nonlinear coding data is required for correct readout during changing environmental conditions. Under such conditions, in the proposed technique, for correct readout, the FLANN is to be retrained and a new set of coefficients is entered into the plug-in module. Thus this modeling technique provides greater flexibility and accuracy in a changing environment. >