Hybrid demodulation concept and harmonic analysis for single/multiple power quality events detection and classification

A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances

“…The sparse signal decomposition is a new signal processing tool for the analysis of PQ disturbance signals. In literature, numerous other signal processing techniques recently used for the feature extraction of the PQ disturbances are Chirp-Transform (CT) [110], SpacePhasors (SP) applied to 3-phase voltage signals [111], Morphology Method (MM) [112], Slant-Transform (SLT) [113], Time-Time Transform (TTT) [114],Teager Energy Operator (TEO) [115], Principle Curves (PC) [116], Spectral Kurtosis (SK) [117], Amplitude and Frequency Demodulation (AFD) with FPARR classifier [118].…”

“…In [148] authors proposed DWT feature extraction based FPARR for the recognition of PQ disturbances and classified event classes with minimum error. An efficient PQ event analysis and classification system have been proposed in [118] using amplitude demodulation, frequency demodulation and Multiple Signal Classification (MUSIC) harmonic analysis for making knowledge base for FPARR classifier. The FPARR classifier has the high classification rate due to its learning and generalization capabilities.…”

A novel wavelet transform based voltage sag/swell detection algorithm

“…The well-known application of the DWT is to detect, characterize and locate power system transients [10]. Much research efforts have focused on wavelet-based techniques applied on analyzing power system transients [9], detecting and classifying PQ disturbances [11][12][13][14][15][16][17] and faults [18][19][20]. The start and end times of voltage sags and faults were also detected by means of the wavelet transform analysis [21][22][23].…”

A novel method for power quality multiple disturbance decomposition based on Independent Component Analysis

“…In [11], a classifier is proposed consisting of several processing components arranged in a cascade form, including amplitude estimator (to recognize sags, swells or interruptions), Wavelet Transform, transient detector and neural networks to recognize other multiple disturbances (harmonics and flickers, in this case). In [12], a novel analysis of PQ events is presented using amplitude and frequency demodulation concepts to separate various single/multiple event patterns to be classified using Fuzzy classifiers. All methods cited above have a preprocessing step in common which extracts some representative parameters that can distinguish information from multiple disturbances in some way, and a classification step that uses an intelligent method to make this distinction.…”