Analysis and classification of power quality disturbances using variational mode decomposition and hybrid particle swarm optimization (original) (raw)
2024, International Journal of Electrical and Computer Engineering (IJECE)
Power quality disturbances (PQD) threaten electrical power systems, especially in distributed generation with renewable energy sources and in smart grids where PQD takes a complex form. Providing accurate information on the status and characteristics of the electrical signal facilitates the identification of practical solutions to this threat. In this paper, a variational mode decomposition (VMD) signal processing tool is proposed to analyze complex PQD. In VMD, the input signal is decomposed into different band-limited intrinsic mode functions (IMF) or non-recursively reconstructed modes. The input signal analysis by VMD, which considers the frequency values and spectral decomposition for each mode, describes the changes in the input waveform, and the IMFs help extract the behavioral patterns of these disturbances. A new hybrid particle swarm optimizationtechnique for order of preference by similarity to ideal solution (PSOTOPSIS) algorithm is also proposed to classify the disturbances based on the features extracted from the signals decomposed using VMD. The performance of this method is then extensively validated by using different PQDs (including complex, stationary, and non-stationary (PQDs) and through a comparison with deep learning methods, such as convolutional and recurrent neural networks. Results show that VMD has several advantages over Fourier, wavelet, and Stockwell transforms, such as its lack of any modal aliasing effect, its capability to diagnose disturbances across four noise levels, and its ability to separate harmonics from other events. The proposed VMD in combination with PSO-TOPSIS performs more accurately than the other methods across all noise levels.
Related papers
This work considers the classification of power quality disturbances based on VMD (Variational Mode Decomposition) and EWT (Empirical Wavelet Transform) using SVM (Support Vector Machine). Performance comparison of VMD over EWT is done for producing feature vectors that can extract salient and unique nature of these disturbances. In this paper, these two adaptive signal processing methods are used to produce three Intrinsic Mode Function (IMF) components of power quality signals. Feature vectors produced by finding sines and cosines of statistical parameter vector of three different IMF candidates are used for training SVM. Validation for six different classes of power qualities including normal sinusoidal signal, sag, swell, harmonics, sag with harmonics, swell with harmonics is performed using synthetic data in MATLAB. Classification results using SVM shows that VMD outperforms over EWT for feature extraction process and the classification accuracy is tabled.
2016 51st International Universities Power Engineering Conference (UPEC), 2016
This paper presents a hybrid detection method and classification Technique based on Hilbert-Huang Transform (HHT) and Feed Forward Neural Networks (FFNNs) to improve the efficient delivery and ensure accurate detection of quality disturbances in the electrical power grids. First, quantities characteristics of power quality disturbances (PQDs) are introduced according its parametrical conditions. Thereafter, a detection and recognition algorithm is used for single and multiple disturbances. Then, a decomposition process and features extraction using Empirical Mode Decomposition (EMD) is conducted for each of these distorted waveforms into Intrinsic Mode Functions (IMFs). Finally, these features are constructed using signal amplitude and frequency and then after fed to one of the powerful Artificial Intelligence Techniques in this field for training, evaluating and testing using (FFNNs) classifier to verify and confirm the effectiveness of the detection methodology.
In this paper, a new approach for the detection and classification of single and combined power quality (PQ) disturbances is proposed using fuzzy logic and a particle swarm optimization (PSO) algorithm. In the proposed method, suitable features of the waveform of the PQ disturbance are first extracted. These features are extracted from parameters derived from the Fourier and wavelet transforms of the signal. Then, the proposed fuzzy system classifies the type of PQ disturbances based on these features. The PSO algorithm is used to accurately determine the membership function parameters for the fuzzy systems. To test the proposed approach, the waveforms of the PQ disturbances were assumed to be in the sampled form. The impulse, interruption, swell, sag, notch, transient, harmonic, and flicker are considered as single disturbances for the voltage signal. In addition, eight possible combinations of single disturbances are considered as the PQ combined types. The capability of the proposed approach to identify these PQ disturbances is also investigated, when white Gaussian noise, with various signal to noise ratio (SNR) values, is added to the waveforms. The simulation results show that the average rate of correct identification is about 96% for different single and combined PQ disturbances under noisy conditions.
2011 7th International Conference on Electrical and Electronics Engineering (ELECO), 2011
This paper presents performance comparisons of Support Vector Machine (SVM) and different classification method for power quality disturbance classification. The first goal of this study is to investigate EEMD (ensemble empirical mode decomposition) performance and to compare it with classical EMD for feature vector extraction and selection of power quality disturbances. Features are extracted from the power electrical signals by using Hilbert Huang Transform (HHT). This technique is a combination of ensemble empirical mode decomposition (EEMD) and Hilbert transform (HT). The outputs of HT are instantaneous frequency (IF) and instantaneous amplitude (IA). Characteristic features are obtained from first IMFs', IF and IA. The ten features, i.e. mean, standard deviation, singular values, maxima and minima of IF and IA, are then calculated. These features are normalized and the inputs of SVM and other classifiers.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.