Improving RF-based partial discharge localization via machine learning ensemble method

Iorkyase, Ephraim Tersoo and Tachtatzis, Christos and Glover, Ian A. and Lazaridis, Pavlos and Upton, David and Saeed, Bakhtiar and Atkinson, Robert C. (2019) Improving RF-based partial discharge localization via machine learning ensemble method. IEEE Transactions on Power Delivery, 34 (4). pp. 1478-1489. ISSN 0885-8977

[thumbnail of E_Iorkyase_et_al_Improving_RF_based_PD_localisation_via_machine_learning_ensemble_method_Accepted_paper.pdf]
Preview
Text (E_Iorkyase_et_al_Improving_RF_based_PD_localisation_via_machine_learning_ensemble_method_Accepted_paper.pdf)
E_Iorkyase_et_al_Improving_RF_based_PD_localisation_via_machine_learning_ensemble_method_Accepted_paper.pdf
Accepted Author Manuscript

Download (4MB)| Preview
    [thumbnail of Iorkyase-etal-TOPD-2019-Improving-RF-based-partial-discharge-localization-via-machine-learning-ensemble-method]
    Preview
    Text (Iorkyase-etal-TOPD-2019-Improving-RF-based-partial-discharge-localization-via-machine-learning-ensemble-method)
    Iorkyase_etal_TOPD_2019_Improving_RF_based_partial_discharge_localization_via_machine_learning_ensemble_method.pdf
    Final Published Version
    License: Creative Commons Attribution 4.0 logo

    Download (4MB)| Preview

      Abstract

      Partial discharge (PD) is regarded as a precursor to plant failure and therefore, an effective indication of plant condition. Locating the source of PD before failure is key to efficient maintenance and improving reliability of power systems. This paper presents a low cost, autonomous partial discharge radiolocation mechanism to improve PD localization precision. The proposed radio frequency-based technique uses the wavelet packet transform (WPT) and machine learning ensemble methods to locate PDs. More specifically, the received signals are decomposed by the WPT and analyzed in order to identify localized PD signal patterns in the presence of noise. The regression tree algorithm, bootstrap aggregating method, and regression random forest are used to develop PD localization models based on the WPT-based PD features. The proposed PD localization scheme has been found to successfully locate PD with negligible error. Additionally, the principle of the PD location scheme has been validated using a separate test dataset. Numerical results demonstrate that the WPT-random forest PD localization scheme produced superior performance as a result of its robustness against noise.

      ORCID iDs

      Iorkyase, Ephraim Tersoo ORCID logoORCID: https://orcid.org/0000-0002-1995-4387, Tachtatzis, Christos ORCID logoORCID: https://orcid.org/0000-0001-9150-6805, Glover, Ian A., Lazaridis, Pavlos, Upton, David, Saeed, Bakhtiar and Atkinson, Robert C. ORCID logoORCID: https://orcid.org/0000-0002-6206-2229;