What is it about?
Unmonitored Electrical fault detection for unlabeled data is a method of detecting electric faults on both labeled and unlabeled data. Electrical defect detection is done according to the dataset in this project, and machine learning methods are employed on the dataset, with simulation for improved prediction. Machine learning is increasingly being utilised to automate the identification of electrical faults.
Featured Image
Photo by israel palacio on Unsplash
Why is it important?
When a wires structure is interrupted due to a break in one of the wires (phase or neutral) or a fried fuse, an open circuit problem arises. A fault in a three-phase system can involve one or more phases and a ground failure, or it can happen just between the phases. Current flows into to the ground in a "ground fault" or "earth fault.". In most of the time, for a foreseeable fault, short current can be calculated.
Perspectives
Writing this article was a great pleasure as it has co-authors with whom I have had long standing collaborations. This article also lead to rare disease groups contacting me and ultimately to a greater involvement in rare disease research.
Viji D
SRM University
Read the Original
This page is a summary of: Electrical fault detection using machine learning algorithm, January 2023, American Institute of Physics,
DOI: 10.1063/5.0154682.
You can read the full text:
Contributors
The following have contributed to this page
