Detection and classification of complex power quality disturbances using S-transform amplitude matrix-based decision tree for different noise levels

Kubendran, Arun Kumar Puliyadi; Loganathan, Ashok Kumar

doi:10.1002/etep.2286

Cited by 26 publications

(10 citation statements)

References 20 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the mathematical models of PQDs, MATLAB software was employed to generate the PQ disturbances of the 31 categories of single and multiple problems in a power network, by changing the specified bounds of the PQD mathematical models. A total of 10 cycles were considered for each PQD, which contains total 5120 points/10 cycle of the synthetic dataset, whereas the fundamental frequencies of each PQDs is 50 Hz.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Classification of multiple power quality events via compressed deep learning

Liu

Hussain

Shen

et al. 2019

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary This paper presents a recently established compressed sensing (CS) and sparse autoencoder (SAE) based on deep learning (DL) method for classification of single and multiple power quality disturbances (PQDs). The CS technique is paying considerable attention in recent years due to below sampling rate comparatively Nyquist sampling. Initially, the CS technique is applied to extract the features of PQD waveforms. The extracted features are applied as inputs to the sparse autoencoder based on DL for classification of nine single and 22 combined classes of PQDs. The DL helps to remove a redundant feature and improves classification performance. Finally, backpropagation is applied to fine‐tune the entire network. The effectiveness of the proposed algorithm has been tested with more than 6580 numbers of real and synthetic single and multiple PQD data, and the results are recorded. High correct classification rate is obtained with noise and without noise level. Noise level was considered from 20 to 50 dB. The performance of the proposed technique has been assessed by comparing the results against recently reported methods. Results show that the proposed CS‐ and SAE‐based DL algorithms can be efficiently used for single and multiple PQDs classifications.

show abstract

Section: Methodsmentioning

confidence: 99%

“…In the real power system network, multiple power quality (MPQ) disturbances have been occurred due to power failure, capacitors switching, power electronic circuits, etc . Many methods have been revealed for the detection and classification of single PQD signal .…”

Section: Introductionmentioning

confidence: 99%

Classification of multiple power quality events via compressed deep learning

Liu

Hussain

Shen

et al. 2019

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

show abstract

“…Flicker, notching and spikes were considered in the equations implemented by Kumar et al [13] and Granados-Lieberman et al [14] to model a total of nine single disturbances. Other authors have considered many more types of combined distortions (Hooshmand & Enshaee [15], Kanirajan & Kumar [16], Kubendran & Loganathan [17]). Igual et al [6] merged several existing proposals into an integral mathematical model that considered most of the equations implemented by other authors.…”

Section: Introductionmentioning

confidence: 99%

Analysis of public datasets of power quality distortions

Dominguez-Gimeno¹,

Igual²,

Medrano³

2020

REPQJ

View full text Add to dashboard Cite

Automatic classification of power quality distortions has gained interest in research due to the proliferation of distributed power systems with renewable sources. To train and test a classification system, data with power quality distortions are required. Most studies generate synthetic data from mathematical equations, since real distortions are difficult to record. A possible alternative is to use public datasets of real disturbances. However, there are strong differences among public datasets. In this paper, existing datasets of power quality distortions were compiled and their main features were analysed and compared. To the best of our knowledge, this is the first work reviewing these datasets. To identify the datasets, the most cited papers on this topic were surveyed. In addition, systematic searches were conducted in four popular scientific repositories. As a result, four available datasets were identified. They included a limited number of samples (20-44) and types of distortions. Sampling frequencies and recording conditions were appropriate and the two main fundamental grid frequencies (50 and 60 Hz) were also considered. Although these datasets are appropriate for partially testing automatic classifiers, a remaining research effort is to provide comprehensive datasets with hundreds of samples and several types of distortions.

show abstract

“…Appropriate features must be selected to ensure classification efficiency. The PQDs include not only stationary signals such as flickers but also nonstationary signals such as oscillatory transients and notches, so signal‐processing tools like the wavelet transform (WT), the Gabor transform, the S‐transform (ST), and empirical mode decomposition (EMD) readily apply to feature extraction. Wavelet transform, unfortunately, is noise‐sensitive and ill‐suited to selecting proper basic wavelet functions; furthermore, it is not capable of directly providing the distinctive features which make each disturbance unique and salient.…”

Section: Introductionmentioning

confidence: 99%

“…The specific disturbance type is determined in the pattern recognition phase. Artificial intelligence methods such as the decision tree, rule‐based system, artificial neural network, fuzzy logic, expert system, support vector machine (SVM), or relevance vector machine are typically used as classifiers for PQ analysis. There are 2 important requirements the classifier must meet.…”

Section: Introductionmentioning

confidence: 99%

Classification of power quality disturbances using dual strong tracking filters and rule-based extreme learning machine

Chen

Xiao

2018

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

SummaryThe classification of single and simultaneous power quality disturbances (PQDs) has become an issue of concern in the power system field. This paper proposes a novel approach based on dual strong tracking filters (STFs) and the rule-based extreme learning machine (ELM) for detecting and classifying single and simultaneous PQDs. Dual STFs are a hybrid structure of a low-order STF and high-order STF. The fading factor of the low-order STF is used to detect sudden changes in PQDs; the fundamental amplitude variation is tracked by the high-order STF. Six distinctive features extracted from the dual STFs serve as the input to the ELM classifier for PQD classification. The rule-based ELM technique, which is equipped with certain decision rules, can improve the ELM classification accuracy when the number of hidden nodes is insufficient. In consideration of special structures of matrices, the real-time computation of the proposed method can be realized. A PQD dataset is generated in MATLAB for simulation experiments; the results show that 20 types of PQDs, including single and simultaneous disturbances, can be accurately classified under the different levels of noise via the proposed method. The method is also tested on a real recorded waveform to verify its effectiveness in PQD classification. | INTRODUCTIONIn recent years, power quality (PQ) has become a critical issue for researchers and developers concerned with power system stability and the propagation of PQ-related effects in the grid. Poor PQ can lead to maloperations or failures of sensitive loads such as embedded systems or electronic devices, ultimately incurring substantial cost for end users. The increased use of unbalanced and nonlinear loads, line faults, switching devices, and power electric converters represents a wide variety of disturbances. Faults among lines to ground, unbalanced, or nonlinear loads can lead to amplitude (AM) variations of the fundamental frequency such as sags, swells, and interruptions. Flickers andThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Detection and classification of complex power quality disturbances using S-transform amplitude matrix-based decision tree for different noise levels

Cited by 26 publications

References 20 publications

Classification of multiple power quality events via compressed deep learning

Classification of multiple power quality events via compressed deep learning

Analysis of public datasets of power quality distortions

Classification of power quality disturbances using dual strong tracking filters and rule-based extreme learning machine

Contact Info

Product

Resources

About