Prediction of Incipient Faults in Underground Power Cables Utilizing S-Transform and Support Vector Regression

Faisal, Mohamed Fuad; Mohamed, Azah; Shareef, Hussain

doi:10.15676/ijeei.2012.4.2.1

Cited by 13 publications

(7 citation statements)

References 17 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second method is based on artificial neural network [16]. The third method is based on S‐transform and support vector regression [17]. The detection accuracies of the methods are tabulated in Table 1.…”

Section: Resultsmentioning

confidence: 99%

“…Some of well‐known fault detection and location approaches are the methods based on travelling wave [6], impedance [7, 8], and intelligent system [9, 16]. In the frequency domain based approaches by using some tools such as wavelet and S‐transform, the harmonic components of the arc current and/or voltage are utilised [10, 17]. The time varying characteristics of arc voltage and/or current of the incipient faults such as positive and negative sequences as well as current peaks are analysed in the time domain based techniques [7, 8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Kalman filter based incipient fault detection method for underground cables

Ghanbari

2015

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Kalman filter based incipient fault detection method for underground cables

Ghanbari

2015

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

“…Current and voltage measurements have all the information to detect the faults, but different feature extraction methods and techniques are still used for better results. Fault detection using the feature extraction method uses the Fourier, wavelet, and S-transform [5]- [7]. These transforms use real-time-frequency parameters in different domains, and the wavelet domain can categorize as discrete and continuous.…”

Section: Introductionmentioning

confidence: 99%

A new algorithm for fault location in multi-end underground cables using traveling waves

Tariq

Alhamrouni

Rehman³

et al. 2023

IJPEDS

View full text Add to dashboard Cite

<p>A quick, reliable, and accurate fault location approach is essential in underground power systems protection. Being the most optimistic research topic of electrical power systems, this article presents an optimized algorithm for fault location in multi-end underground cables using travelling waves. Existing algorithms based on wavelet theory have fewer reliability and accuracy issues that raise an error to the power systems in fault location. The proposed layout presents a multiterminal underground cables system where the entire system is segregated into several fault identification sections where this model identifies the faulty section and the faulty half. Voltage and current wave transient at the mid-point of each fault locator are taken into account to eliminate the time-synchronous error. Traveling waves models are modelled using Bewley diagrams. Detecting the first and second traveling wave transient at both ends of each cable keeps the system reliable. Extensive simulations are simulated using the alternative transient program (ATP) to discriminate, identify, and locate several faults, while the system can also validate the faults near the busbar. The model is developed in MATLAB, and the obtained results depict the proposed algorithm's higher accuracy in fault location.</p>

show abstract

“…An intelligent system-based approach is proposed in the literature [25]. In the frequency domain-based approach introduced in the literature [26], the S-transform takes into account the harmonic components of the arc current and/or voltage. In the literature [27], a rule-based and SVMbased pattern classifier is used to classify the transient patterns of underground cables.…”

Section: Introductionmentioning

confidence: 99%

Transform Waveforms Into Signature Vectors for General-Purpose Incipient Fault Detection

Weng

Cui

Guo

2022

IEEE Trans. Power Delivery

View full text Add to dashboard Cite

Power system equipment presents special signatures at the incipient stage of faults. As more renewables are integrated into the systems, these signatures are harder to detect. If faults are detected at an early stage, economical losses and power outages can be avoided in modern power grids. Many researchers and power engineers have proposed a series of signature-specific methods for one type of equipment's waveform abnormality. However, conventional methods are not designed to identify multiple types of incipient faults (IFs) signatures at the same time. Therefore, we develop a general-purpose IF detection method that detects waveform abnormality stemming from multiple types of devices. To avoid the computational burden of the general-purpose IF detection method, we embed the abnormality signatures into a vector and develop a pretraining model (PTM) for machine understanding. In the PTM, signal "words," "sentences," and "dictionaries" are designed and proposed. Through the comparison with a machine learning classifier and a simple probabilistic language model, the results show a superior detection performance and reveal that the training radius is highly related to the size of abnormal waveforms.

show abstract

Prediction of Incipient Faults in Underground Power Cables Utilizing S-Transform and Support Vector Regression

Cited by 13 publications

References 17 publications

Kalman filter based incipient fault detection method for underground cables

Kalman filter based incipient fault detection method for underground cables

A new algorithm for fault location in multi-end underground cables using traveling waves

Transform Waveforms Into Signature Vectors for General-Purpose Incipient Fault Detection

Contact Info

Product

Resources

About