Non-stationary Power Signal Research Articles

Non-stationary power signal processing for pattern recognition using HS-transform

A new approach to time-frequency transform and pattern recognition of non-stationary power signals is presented in this paper. In the proposed work visual localization, detection and classification of non-stationary power signals are achieved using hyperbolic S-transform known as HS-transform and automatic pattern recognition is carried out using GA based Fuzzy C-means algorithm. Time-frequency analysis and feature extraction from the non-stationary power signals are done by HS-transform. Various non-stationary power signal waveforms are processed through HS-transform with hyperbolic window to generate time-frequency contours for extracting relevant features for pattern classification. The extracted features are clustered using Fuzzy C-means algorithm and finally the algorithm is optimized using genetic algorithm to refine the cluster centers. The average classification accuracy of the disturbances is 93.25% and 95.75% using Fuzzy C-means and genetic based Fuzzy C-means algorithm, respectively.

Time Frequency Analysis and Non-Stationary Signal Classification using PSO Based Fuzzy C-Means Algorithm

This paper proposes a new approach for Time frequency analysis and non-stationary power signal classification using PSO based fuzzy C-means algorithm. Various non-stationary power signals like transient of different length (oscillatory transient), Voltage sag, Voltage swell, notches and impulsive transient are processed through S-transform to extract various features. The excellent time frequency resolution characteristic of the Generalized S-transform makes it an attractive candidate for analysis and detection of non-stationary signal. After feature extraction, the PSO (Particle Swarm Optimization) based Fuzzy C-means algorithm is used to cluster the extracted features to get the desired classification. The fuzzy C-means algorithm is then extended using particle swarm optimization algorithm to refine the cluster centers formed by fuzzy C-means algorithm. In the proposed work, the non-stationary power signals like oscillatory transient, impulsive transient, Voltage sag, Voltage swell, and notches have been considered for power signal classification.