Power Quality Disturbance Recognition Using VMD-Based Feature Extraction and Heuristic Feature Selection

Abstract

Power quality disturbances (PQDs) have a large negative impact on electric power systems with the increasing use of sensitive electrical loads. This paper presents a novel hybrid algorithm for PQD detection and classification. The proposed method is constructed while using the following main steps: computer simulation of PQD signals, signal decomposition, feature extraction, heuristic selection of feature selection, and classification. First, different types of PQD signals are generated by computer simulation. Second, variational mode decomposition (VMD) is used to decompose the signals into several instinct mode functions (IMFs). Third, the statistical features are calculated in the time series for each IMF. Next, a two-stage feature selection method is imported to eliminate the redundant features by utilizing permutation entropy and the Fisher score algorithm. Finally, the selected feature vectors are fed into a multiclass support vector machine (SVM) model to classify the PQDs. Several experimental investigations are performed to verify the performance and effectiveness of the proposed method in a noisy environment. Moreover, the results demonstrate that the start and end points of the PQD can be efficiently detected.

A Hybrid Deep Learning System for Real-World Mobile User Authentication Using Motion Sensors

“…VMD is not as susceptible to singular points in the signal as EMD; VMD is an adaptive and nonrecursive method that can analyze both nonstationary and nonlinear signals [ 54 , 55 ]. The essence of the VMD algorithm is the process of solving the variational problem.…”

“…In order to carry out subsequent effective feature extraction (including statistical feature extraction during the label refactoring stage and CNN feature extraction during hybrid deep learning training), we need to de-noise and enhance the data first. VMD is utilized to decompose the signal obtained into several IMFs for potential feature extraction, as described in previous work [ 54 ]. The submode decomposed by VMD contains a specific spectrum, which can accurately trace the signal changes.…”

“…Figure 4 a–d represent a representative acceleration sample of different decomposition results of VMD when K = 3, 4, 5, and 6, respectively. According to the experience of the existing work [ 54 ], we use the permutation entropy of each IMF to judge the quality of the decomposition results. We set the threshold as 0.6 as [ 54 ] did.…”

“…According to the experience of the existing work [ 54 ], we use the permutation entropy of each IMF to judge the quality of the decomposition results. We set the threshold as 0.6 as [ 54 ] did. It can be observed that the sensor signals in Figure 4 a–c are under-decomposed.…”

A Novel Deep Learning-Based Diagnosis Method Applied to Power Quality Disturbances

“…Viewed in this way, deep learning techniques are to be considered in multiple industrial fields of applications that deal with high-dimensional sets of data and multiple patterns [20]. Application of deep learning has been presenting good performance in areas like image classification, speech recognition, natural language processing, video processing, and, recently, in areas related to energy management [21]. Autoencoder, convolutional neural networks, or recurrent neural networks are the most common techniques to be used for dealing with complex data involved.…”