Supervised Learning for Fault Classification Using Hybrid Training Datasets

Archana Ranganathan, Simon H. Tindemans, Frans Provoost

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

9 Downloads (Pure)


Electrical faults in the distribution system can lead to interruptions in customer power supply resulting in penalties that are borne by the distribution system operator. Accurate fault classification is an important step in locating the fault to achieve faster network restoration times. This paper presents a classification model in two parts: one determines the degree of stability in the fault waveforms and the second uses a machine learning model to classify real-world faults based on the number of fault phases. A set of business rules are developed to characterise instability by performing a windowed Fourier analysis and studying the strength of the fundamental frequency component of fault waveforms. Results show that the developed SVM model can differentiate between real-world instances of single-phase, two-phase and threephase stable faults with a classification accuracy of 95%. Additionally, we show that adding a small subset of synthetically developed faults to the training data improves classification accuracy.
Original languageEnglish
Title of host publicationProceedings of the 27th International Conference on Electricity Distribution (CIRED 2023)
Number of pages5
ISBN (Electronic)978-1-83953-855-1
Publication statusPublished - 2023
Event27th International Conference on Electricity Distribution (CIRED 2023) - Rome, Italy
Duration: 12 Jun 202315 Jun 2023
Conference number: 27th


Conference27th International Conference on Electricity Distribution (CIRED 2023)

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.


Dive into the research topics of 'Supervised Learning for Fault Classification Using Hybrid Training Datasets'. Together they form a unique fingerprint.

Cite this