Automatic classification of power quality events and disturbances using wavelet transform and support vector machines

Eri̇şti̇, Hüseyin; Demir, Yakup

doi:10.1049/iet-gtd.2011.0733

Cited by 80 publications

(62 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, considering that ϕ(x) is a nonlinear transform, kernels are used for transferring data to a high-dimensional space. For this purpose, the earlier optimization problem is transformed to the following form, which is modeled by the Lagrange method of multipliers [16].…”

Section: Inmentioning

confidence: 99%

Classifications of disturbances using wavelet transform and support vector machine

Hajibandeh¹,

Faghihi²,

Ranjbar³

et al. 2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper proposes a new method to detect and classify all kinds of faults, capacitor switching, and load switching in a power system network based on wavelet transform and support vector machines (SVMs). In this regard, a sample of a power system is simulated via MATLAB/Simulink, and by reading the voltage of the point of common coupling and using the wavelet transform, the differences of the outputs of the wavelet transform are investigated. The SVM approach is employed to distinguish the type of the transient (capacitor switching, fault, and/or load switching) in use for the high level outputs of the wavelet transform. Similar to neural networks, this method, which is based on learning, is considered as a proper tool for data classification. The results of simulations demonstrate that the combination of wavelet transform and SVM recognizes the type of the transient correctly and effectively as well as distinguishes capacitor switching and load switching events from all kinds of faults such as three-phase-to-earth fault, phase-to-phase fault, two-phase-to-earth fault, and single-phase-to-earth fault. In the end, the accuracy of the presented approach is evaluated and the simulation results are proposed for different attributes of transients in the power system network.

show abstract

Section: Inmentioning

confidence: 99%

Classifications of disturbances using wavelet transform and support vector machine

Hajibandeh¹,

Faghihi²,

Ranjbar³

et al. 2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…For the sake of verifying the validity of the feature selection results of the new method, four kinds of classifier, including RF, SVM [14], PNN [13] and DT, are used to classify 15 kinds of PQ signals under the condition of different noise environments and different feature subsets. The DT classifier is constructed by rpart software package in R project.…”

Section: Comparison Experiments and Analysismentioning

confidence: 99%

“…In past studies, feature selection was either in accordance with the filter method based on the features' statistical characteristics, which made it difficult to analyze the classification ability of the feature combination [13,14], or used the wrapper method combined with the particle swarm optimization [15], genetic algorithm [16], rough set theory [17] or other intelligent algorithms, then according to the classification results chose the optimal or sub-optimal feature subset, but the efficiency of the search algorithm is unsatisfactory. Meanwhile, existing feature selection methods have to select different feature subsets under different noise conditions, and this limits the application possibilities of feature selection methods in practical engineering.…”

Section: Introductionmentioning

confidence: 99%

Feature Selection of Power Quality Disturbance Signals with an Entropy-Importance-Based Random Forest

Huang

Cai

et al. 2016

Entropy

View full text Add to dashboard Cite

Power quality signal feature selection is an effective method to improve the accuracy and efficiency of power quality (PQ) disturbance classification. In this paper, an entropy-importance (EnI)-based random forest (RF) model for PQ feature selection and disturbance classification is proposed. Firstly, 35 kinds of signal features extracted from S-transform (ST) with random noise are used as the original input feature vector of RF classifier to recognize 15 kinds of PQ signals with six kinds of complex disturbance. During the RF training process, the classification ability of different features is quantified by EnI. Secondly, without considering the features with zero EnI, the optimal perturbation feature subset is obtained by applying the sequential forward search (SFS) method which considers the classification accuracy and feature dimension. Then, the reconstructed RF classifier is applied to identify disturbances. According to the simulation results, the classification accuracy is higher than that of other classifiers, and the feature selection effect of the new approach is better than SFS and sequential backward search (SBS) without EnI. With the same feature subset, the new method can maintain a classification accuracy above 99.7% under the condition of 30 dB or above, and the accuracy under 20 dB is 96.8%.

show abstract

“…For instance, a continuous signal x(t) can be analyzed if x(t) is correlated with a wavelet function ψ(t), giving as a result wavelet coefficients defined by [21] …”

Section: Wavelet Transformmentioning

confidence: 99%

A New Adaptive Mother Wavelet for Electromagnetic Transient Analysis

Guillén

Idárraga-Ospina

Cortes

2016

Journal of Electrical Engineering

View full text Add to dashboard Cite

Wavelet Transform (WT) is a powerful technique of signal processing, its applications in power systems have been increasing to evaluate power system conditions, such as faults, switching transients, power quality issues, among others. Electromagnetic transients in power systems are due to changes in the network configuration, producing non-periodic signals, which have to be identified to avoid power outages in normal operation or transient conditions. In this paper a methodology to develop a new adaptive mother wavelet for electromagnetic transient analysis is proposed. Classification is carried out with an innovative technique based on adaptive wavelets, where filter bank coefficients will be adapted until a discriminant criterion is optimized. Then, its corresponding filter coefficients will be used to get the new mother wavelet, named wavelet ET, which allowed to identify and to distinguish the high frequency information produced by different electromagnetic transients.

show abstract

Automatic classification of power quality events and disturbances using wavelet transform and support vector machines

Cited by 80 publications

References 26 publications

Classifications of disturbances using wavelet transform and support vector machine

Classifications of disturbances using wavelet transform and support vector machine

Feature Selection of Power Quality Disturbance Signals with an Entropy-Importance-Based Random Forest

A New Adaptive Mother Wavelet for Electromagnetic Transient Analysis

Contact Info

Product

Resources

About