Classification of Single and Combined Power Quality Disturbances Using Stockwell Transform, ReliefF Feature Selection Method and Multilayer Perceptron Algorithm

The power quality (PQ) disturbance signals have the characteristics of short duration and strong randomness, and often form complex disturbances, which make the disturbance signals difficult to detect and identify. In this paper, EMD algorithm is introduced to decompose the PQ disturbance signals and calculate the intrinsic mode function (IMF) of the disturbance signals. Then, Hibert transform are performed for each IMF to obtain the characteristic information of the disturbance signal. EMD transform is used to detect the type, duration, frequency and amplitude of PQ disturbances. To verify the effectiveness of the algorithm, several kinds of PQ disturbance signals are simulated with transient harmonic, voltage interruption, voltage drop and voltage surge and complex disturbances. Experimental results show that the algorithm can accurately detect power quality interferences. This paper provides a new method for the detection of PQ disturbances and a new idea for the power management.

Power quality disturbances (PQDs) can significantly affect the reliability of electrical power systems, leading to potential equipment damage and operational inefficiencies. Accurate classification of these disturbances is essential for ensuring continuous and reliable service. The study proposes a deep transfer learning (TL) approach for PQD classification. In the proposed work, various single and multiple PQD signals pertaining to 15 different classes have been generated using mathematical models of PQDs adhering to the guidelines of the IEEE 1159 and IEC 61000-4-30 standards. Time-domain PQD signals are first converted into 2D color images using continuous wavelet transform (CWT). These images are then used to re-train modified pre-trained models such as GoogleNet, SqueezeNet, ResNet-18, and ShuffleNet on synthetic PQD data. Various single and combined PQDs are then classified using trained models. Moreover, the performance of the trained models is evaluated with the PQD signals containing noise of various signal-to-noise ratios (SNR), as well as PQD signals collected from the experimental setup in the laboratory. The results signify that the GoogleNet model exhibits consistent performance for classifying PQDs under various conditions, achieving classification accuracy of 99.8% for synthetic noiseless signals, 98.87% for signals with 20 dB SNR, and 98.89% for signals acquired through experimental setup. Furthermore, the trained models were tested using real-world PQD signals, comprising 26 sag and 42 impulse signals. The GoogleNet model achieved the highest classification accuracy, correctly identifying 23 sag and 34 impulse events, thereby demonstrating real-world applicability and robustness of the proposed approach.

A novel ensemble neural network structure is presented for automatic classification of power quality disturbances. Power quality (PQ) disturbances analysis is the focus of power quality control. The characteristics of PQ disturbances include short duration, variety of types and so on. Power quality disturbances classification is the foundation of power quality control automation. Different types of Neural network, such as BP neural networks, RBF neural networks and probabilistic neural network etc, is already applied in the area of PQ disturbances classification and recognition. The researches about the neural network for PQ disturbances recognition are mainly focused on the optimizing for the signal type of neural network. But the accuracy rate of the classification is still needed to be improved. Ensemble and hybrid algorithms research is currently flourishing in pattern classification machine learning and decision sciences. Compare to traditional NN, the ensemble and hybrid NN classifier achieves higher classification rate. In this paper, a novel PQ classification system using S-transform and ensemble and hybrid NN is designed. There are 2 stages in the novel system. Firstly, the PQ disturbances signals are transformed by S-transform and the subset of features extracted from the result of S-transform is used as the input vector of the ensemble and hybrid NN. Secondly in the pattern classification process, BP network and RBF neural network are utilized as two classification agents. Through choosing different parameters and different samples, every agent includes a group of neural networks. The classification results, generated by different agents, are fuzzified into fuzzy numbers. The centroid of all fuzzy numbers is compared with the threshold. Finally we obtain the classification results. In the simulation, 6 types of disturbances signals which are simulated by Matlab 7.0 use for test the new classification system. Simulation result shows that when the new system has better classification rate especially at the high noising environment.

An effective wavelet-based feature extraction method for classification of power quality disturbance signals

This study introduces a novel unified framework for simultaneous denoising and compression of electric power system disturbance signals using sparse signal decomposition and reconstruction on overcomplete hybrid dictionary (OHD) matrix. In the proposed method, the power quality signal is first decomposed into deterministic sinusoidal components and non‐deterministic components using the OHD matrix, including discrete impulse dictionary (I), cosine dictionary (C), sine dictionary (S) and the ℓ1‐norm optimisation algorithm. Then, the hard‐thresholding, uniform threshold dead‐zone quantisation, modified index coding and Huffman coding techniques are used for compression of significant detail signal samples and approximation coefficients. To justify the selection of OHD matrix, four compression methods are implemented using the decomposition techniques based on the dictionaries Ψ = [I C S] and Ψ = [I C], the wavelet transform (WT) and the discrete cosine transform (DCT). The performance of each method is tested and validated using a wide variety of typical power quality disturbance (PQD) signals taken from the IEEE‐1159‐PQE and GIM–PQE databases and generated using the Microgrid model. The results show that the method with dictionary Ψ = [I C S] is capable of effectively compressing the PQD signals as well as suppressing the noise components in the signals.

Detection of power quality disturbance is most essential to ensure the good Power Quality (PQ). The power disturbance signal will reduce the reliability of power system and create some disadvantage on operation process. Aging of electrical device, incorrect measurement, devices malfunction are the consequence of this condition. The characteristic of power disturbance signals are non-stationary and the way to detect this disturbance needed a sample method. The term of non-stationary in signal processing is regularly used to define a process in which the spectrum is changing with time. One kind of methods for analyzed this problem is S-transform (ST). However, Due to this method have relatively fixed Gaussian window the S-transform cannot provide satisfactory time-frequency resolution for all types of disturbance signals. Modified S-transform (MST) provides more suitable means for achieving desired time-frequency for several PQ disturbances signals. This paper proposes power quality analysis (PQA) using modified S-transform (MST) method. Both the time and the frequency domain information of each PQ component are extracted by MST. Comparison between MST simulation result and ST is applied to validate the accuracy and efficiency of modified S-transform (MST) method algorithm. The result of simulation show that this method can accurately detect and show the power signal disturbance such as voltage sag, voltage swell, interruption, flicker, oscillatory transient, notch, spike, and harmonic.

This paper presents a novel hybrid approach combining Gramian Angular Summation Field (GASF) method with a convolutional neural network (CNN) to classify power quality disturbances. Firstly, a 1-D Power quality disturbance signal is transformed into a 2-D image file using GASF. Subsequently, CNN is implemented for features extraction and image classification. In this work, the synthetic power quality (PQ) disturbances are considered including nine single disturbances and five mixed disturbances. Further, to capture multi-scale aspects of power quality disturbances problem and reduce overfitting, a unit is designed using 2-D convolutional, pooling, and batch-normalization layers. The classification study is further supported by experimental signals obtained on a prototype setup of PV system. The obtained results demonstrate the efficiency and reliability of the proposed method. The proposed method is compared with the other advanced CNNs and other conventional methods to illustrate its effectiveness.

The performance analysis of spectrogram and S-transform for power quality disturbances such as swell, sag, interruption, harmonic, inter-harmonic, and transient based on IEEE Std 1159-2009 are presented. These analyses are performed to identify the best performance for detection of power quality disturbances. This is important to provide the improvement of power quality which capable to accurately measured, detect the power quality phenomena. Therefore the accurate detection of power quality disturbances can be developed based on the best techniques. By using both techniques, the temporal and spectral information are obtained. From the time frequency representation (TFR) the signal parameters are estimated such as instantaneous root means square voltage (RMS), total waveform distortion (TWD), total harmonic distortion (THD) and total non harmonic distortion (TnHD).The signal characteristics are calculated from signal parameters to verify the performances of both techniques, the APE results are used to identify the accuracy of these techniques. By perform the analysis; the result show the S-transform is a better tool to analyze the transient disturbances whereas for voltage variation and harmonic disturbances the spectrogram gives higher accuracy result. As a conclusion both techniques are capable to analyzed power quality disturbances, and it clearly shows that, the S-transform has an advantages in term of time-frequency resolution which capable to detect and localized various kind of power quality disturbances and it essential for the development of advanced real-time monitoring.

The electric utilities and end users of power system network have become more concerned about power quality issues due to technical and financial consequences that have resulted from electric power quality disturbances. The power quality monitoring technology has an effective on analyzing power quality related problems. This paper presents a novel study combining wavelet transform with pattern recognition technique to investigate voltage stability using for power quality events. The wavelet transformation possesses capabilities of time and frequency domain localizations, achieving a great impetus in signal singularity detection. The statistics-based denoising method is designed to filter the random noise and impulse noise in power quality disturbance signals, incorporating the advantages of wavelet transform to extract signal feature meanwhile restraining various noises. The wavelet decomposition coefficients as feature vector of neural network are presented for extracting disturbance signal. The neural network provides a means of determining a degree of belief for each identified disturbance waveform. The performance of the proposed approach is studied and a proper combination of wavelet transformation and neural network is identified.

Power quality becomes a severe problem due to the increasing use of nonlinear electrical loads, complex electric power systems on smart grids, inverters in renewable power plants, and electronic control equipment. Power quality problems include variations in voltage or current such as sag, swell, flicker, spike, overvoltage, undervoltage, interruption, transient, harmonics, and frequency fluctuations. Research on power quality disturbances mostly applies signal processing and transformation methods such as Fast Fourier transform, S-transform, and Wavelet. In this paper, we use empirical mode decomposition methods and statistical parameters to analyze power quality disturbance signals. It gives more detailed characteristics of power quality disturbances. We conducted a six-step analysis to get a percentage of each power quality disturbance signal. The developed method provides a preliminary description of the power quality characteristics from the percentage values of RMS, range, and energy levels at the first IMF. The positive percentage indicates the existence of power quality disturbances contains flicker and swell, while negative indicates contain harmonics, sag, and transient.

The continuous monitoring of power quality (PQ) disturbances in electrical power distribution system has become an important issue for utilities and customers. The power system operation can be improved and maintained by analyzing the PQ disturbances systematically. In this paper, an attempt has been made to review the modeling and simulation of the PQ disturbances due to the exploitation of various types of loads. The PQ disturbances are created by using parametric equations as well as electrical power distribution system models in MATLAB/SIMULINK environment. The PQ disturbances of voltage magnitude variation such as sag, swell and interruption are created by applying different types of faults and heavy load in the power distribution model. The frequency variation types of PQ disturbances like harmonics are generated by applying power electronic converter. The non-stationary or transient PQ disturbances are produced by applying a capacitor switching bank in distribution model. The results of PQ disturbance waveforms obtained by both techniques are very similar to real- time PQ signals. The PQ waveforms obtained are suitable for checking the performance of the new automatic classification algorithms.

This paper presents a S-transform effective feature extraction method for power quality (PQ) disturbance classification problem. Firstly, S-transform technique is used to extract the significant features of distorted signal. Then, an optimum combination of the most useful features is identified for increasing the accuracy of classification. Features extracted by using the S-transform are applied as input to support vector machines (SVM) for automatic classification of the power quality (PQ) disturbances that solves a relatively complex problem. Seven single disturbances and six complex disturbances selected as reference are considered for the classification. Sensitivity of proposed classifier under different noise conditions is investigated. The analysis and results show that the classifier can effectively classify different PQ disturbances.

This manuscript describes an algorithm based on Stockwell Transform and rule based decision tree for detection and classification of complex power quality disturbances. The multiple (complex) power quality (PQ) events are generated by various combinations of single stage PQ disturbances. These complex PQ disturbances are generated in conformity with IEEE Standard-1159 using the mathematical relations in MATLAB as per various combinations of voltage swell, voltage sag, momentary interruption (MI), oscillatory transient (OT), harmonics and impulsive transient (IT). These complex power quality signals are decomposed with the help of Stockwell transform to obtain S-matrix. Various plots are obtained from the S-matrix. Various features are extracted from these plots and given as input to the rule-based decision tree for classification of complex PQ disturbances. The effectiveness of proposed algorithm is established by testing 30 data sets of each complex PQ disturbance obtained by varying the parameters.

The automatic pattern recognition of single and multiple power quality (PQ) disturbances is a very important task for the detection and monitoring of multiple faults and events in electrical power system. This paper presents an automatic classification algorithm for PQ disturbances based on wavelet norm entropy features and probabilistic neural network (PNN) as an effective pattern classifier. The proposed method employs the discrete wavelet transform based on multi-resolution analysis technique to extract the most important and constructive features of PQ disturbances at various resolution levels. The distinctive norm entropy features of the PQ disturbances have been extracted and were employed as inputs to the PNN. Various other architectures of artificial neural network such as multilayer perceptron and radial basis function neural network have also been employed for comparison. The PNN is found the most suitable pattern recognition tool for the classification of the PQ disturbances. Various PQ disturbances used for analysis were generated by simulating a typical 11-kV distribution system. The simulation results obtained show that the proposed approach can detect and classify the PQ disturbances effectively and can be implemented successfully in real-time electrical power distribution networks.

The widespread integration of renewable energy sources (RESs) into power systems using power electronics-based interface devices has led to a substantial rise in power quality (PQ) issues. There is an immediate requirement for effective monitoring, detection, and classification of power quality disturbances (PQDs) that is needed to take remedial measures and design planning of the system architecture. This study presents a hybrid approach with an objective for the feature extraction and classification of PQDs. The proposed hybrid approach is comprised of an optimized tunable-Q wavelet transform (OTQWT) for the feature extraction and incremental support vector machine (ISVM). A four-stage approach is suggested for the PQ detection and classification in this study. In the first stage, the various data are retrieved both in the form of synthetic data by mathematical formulations and real-time data with prototype design setup. In the second stage, regardless of the specified wavelet function, the PQD signals are decomposed into low-pass and high-pass sub-bands using the tunable-Q wavelet transform (TQWT). However, the utilization of default decomposition parameters to address nonstationary PQ signals may lead to information loss and reduced performance of the system. To avoid this limitation, an OTQWT as an enhanced technique to TQWT based on an Adaptive Particle Swarm Optimization (APSO) is suggested. A modified objective function based on the mean square error (MSE) is used to improve the decomposition process. In the third stage, an efficient classifier is suggested based on the ISVM. Lastly, to test and evaluate the performance of the proposed approach, twelve types of PQDs including noise and multiple occurrences are considered. The comparative analysis with other popular methods reflects the better performance of the proposed approach and justifies its use for PQ detection and classification purposes in real-time​ conditions.