Time-frequency based pattern recognition technique for detection and classification of power quality disturbances

Chilukuri, M.V.; Dash, P.K.; Basu, Kinjal

doi:10.1109/tencon.2004.1414756

Cited by 17 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally noise comes from voltage and current sensing devices. The noise is generally a white Gaussian noise and value of signal-to-noise (SNR) ratio lies between 20 to 40 dB (Chilukuri et al 2004;Mishra et al 2008;Zhang et al 2003;Zhao and Yang 2007). Therefore, the proposed methods are tested with noisy data and classification results for different SNR are mentioned in Tables 3, 4, 5, and 6.…”

Section: Testing With Simulated Pq Disturbance Signalsmentioning

confidence: 99%

Hybrid Methods for Fast Detection and Characterization of Power Quality Disturbances

Upadhyaya

Mohanty

Bhende

2015

J Control Autom Electr Syst

View full text Add to dashboard Cite

In this paper, recently developed variants of wavelet transform, namely the maximum overlapping discrete wavelet transform and the second-generation wavelet transform, are used for detection of ten types of the power quality (PQ) disturbance signals. Further, the features of PQ signal disturbances are extracted using these wavelet transforms. Those extracted features are then used to classify various PQ disturbances. Random forest (RF) classifier is presented in this paper. The RF is constructed with multiple trees for classification of large number of classes simultaneously. In order to represent realistic situation, the proposed technique is tested with noisy data.Keywords Power quality disturbances (PQD ) · Maximal overlap discrete wavelet transform (MODWT ) · Secondgeneration wavelet transform (SGWT ) · Random forest (RF ) · Power quality (PQ ) · Classification accuracy (CA )

show abstract

Section: Testing With Simulated Pq Disturbance Signalsmentioning

confidence: 99%

Hybrid Methods for Fast Detection and Characterization of Power Quality Disturbances

Upadhyaya

Mohanty

Bhende

2015

J Control Autom Electr Syst

View full text Add to dashboard Cite

show abstract

“…The critical flicker waveform (equation 29) is added with SNR of 30 dB to 10 dB. SNR of 30 dB is able to simulate the noise level for practical measurement [30]. Figure 8 shows the aforementioned critical flicker waveform with SNR of 30 dB and 10 dB.…”

Section: Part 3: Voltage Flicker Generation (With Signal Noise Ratio mentioning

confidence: 99%

A Simple Predictive Method of Critical Flicker Detection for Human Healthy Precaution

Peng

Radzi

Hizam

et al. 2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Interharmonics and flickers have an interrelationship between each other. Based on International Electrotechnical Commission (IEC) flicker standard, the critical flicker frequency for a human eye is located at 8.8 Hz. Additionally, eye strains, headaches, and in the worst case seizures may happen due to the critical flicker. Therefore, this paper introduces a worthwhile research gap on the investigation of interrelationship between the amplitudes of the interharmonics and the critical flicker for 50 Hz power system. Consequently, the significant findings obtained in this paper are the amplitudes of two particular interharmonics are able to detect the critical flicker. In this paper, the aforementioned amplitudes are detected by adaptive linear neuron (ADALINE). After that, the critical flicker is detected by substituting the aforesaid amplitudes to the formulas that have been generated in this paper accordingly. Simulation and experimental works are conducted and the accuracy of the proposed algorithm which utilizes ADALINE is similar, as compared to typical Fluke power analyzer. In a nutshell, this simple predictive method for critical flicker detection has strong potential to be applied in any human crowded places (such as offices, shopping complexes, and stadiums) for human healthy precaution purpose due to its simplicity.

show abstract

“…Besides, random white noises with SNR (signal to ratio) rating from 50 to 20 and zero mean is added to these PQ events [6]. For instance, two results are displayed in Figures 7 and 8.…”

Section: Features Extractionmentioning

confidence: 99%

Power Supply Quality Analysis Using S-Transform and SVM Classifier

Li¹,

Chilukuri²

2014

JPEE

View full text Add to dashboard Cite

In this paper, a SVM classifier based on S-Transform is presented for power quality disturbances classification. Firstly, seven types of PQ events are created using Matlab simulation. These signals are analyzed to detect and localize PQ events via S-Transform by visual inspection. Then five significant features of the PQ disturbances are extracted from the S-Transform output. Afterwards, PQ disturbance samples with the five features are fed to SVM for training and automatic classification. Besides, particle swarm optimization is implemented to improve the performance of SVM. The results of the classification indicate that SVM classifier is an effective mechanism to detect and classify power quality disturbances.

show abstract

Time-frequency based pattern recognition technique for detection and classification of power quality disturbances

Cited by 17 publications

References 10 publications

Hybrid Methods for Fast Detection and Characterization of Power Quality Disturbances

Hybrid Methods for Fast Detection and Characterization of Power Quality Disturbances

A Simple Predictive Method of Critical Flicker Detection for Human Healthy Precaution

Power Supply Quality Analysis Using S-Transform and SVM Classifier

Contact Info

Product

Resources

About