Time‐frequency analysis and classification of power signals using adaptive cuckoo search algorithm

Abstract

A new approach to Hilbert energy spectrum and pattern recognition of nonstationary power signals is presented in this paper. In the proposed work, visual localization, detection, and classification of nonstationary power signals are achieved using Hilbert transform (HT)-based adaptive local iterative filter (ALIF). The HT is applied on all the intrinsic mode functions that are obtained from both empirical mode decomposition (EMD) and ALIF to extract instantaneous amplitude and frequency components. The instantaneous Hilbert energy spectrum results in clear visual detection, localization, and classification of the different power signal disturbances. The visual energy spectrum by Hilbert-Huang Transform (HHT) on ALIF showing a better result than HHT applied on EMD. The feature vectors are extracted from the Hilbert energy spectrum for automatic pattern recognition of various nonstationary signals using a traditional fuzzy C-means algorithm (FCMA). Finally, the center of the cluster is further optimized using fuzzy C-means-based adaptive cuckoo search algorithm. The average classification accuracy of the disturbances is 91.25% and 99.25% using fuzzy C-means and adaptive cuckoo search-based FCMA, respectively. KEYWORDS adaptive cuckoo search algorithm (ACSA), adaptive local iterative filter (ALIF), empirical mode decomposition (EMD), fuzzy C-means algorithm (FCMA), Hilbert transform (HT), intrinsic mode functions (IMFs) | INTRODUCTIONNonstationary power signal disturbances 1,2 and power quality (PQ) has been a cause for concern for both the utilities and users due to the use of many types of electronic equipment. Harmonics, voltage swell, voltage sag, transients, and momentary interruptions can adversely affect this equipment. These disturbances cause several problems, such as overheating, failure of motors, disoperation of sensitive and protective equipment, and inaccurate metering. Voltage swell and sag can occur due to lightning, capacitor switching, motor starting, nearby circuit faults, or accidents and can also lead to power interruptions. Nonstationary power signal waveform analysis plays a major role in addressing these concerns and thereby improving the stability of power systems. The distorted characteristic can be recognized from the nonstationary signal through PQ analysis. Many methods and algorithms have already been proposed by earlier researchers for PQ event characterization. Fourier transform (FT)-based PQ analysis gives information regarding the frequency components present but does not contain information on when they exist and for how long. Although FT

Improvement and Application of Adaptive Hybrid Cuckoo Search Algorithm

“…In 2018, Hosseinalizadeh et al [33] proposed a hybrid CS and applied it to the improvement of steam turbine speed regulation and excitation system identification procedures. In 2018, Biswal et al [34] proposed an adaptive CS algorithm and applied the improved algorithm to time-frequency analysis and classification of power signals.…”

Recognition of voltage sag causes using fractionally delayed biorthogonal wavelet

“…feature extraction, feature selection, classification) have been listed and compared amongst each other. There are two types of approaches found in the literature; one is time-domain based techniques like sliding window, dV/dt, root mean square value (Axelberg et al, 2007; Styvaktakis et al, 2002), higher order statistics (Perez et al, 2011), envelope analysis, Kalman filter (Khoa and Tung, 2018; Xi et al, 2018) and so forth; another type is frequency domain based techniques like fast Fourier transform, wavelet transform (WT) (Jeevitha et al, 2018), Hilbert transform (Biswal et al, 2018; Sahani and Dash, 2018), Goertzel algorithm (Najafi et al, 2018) and so forth.…”