Research Area:  Machine Learning
The rising development of power systems and smart grids calls for advanced fault diagnosis techniques to prevent undesired interruptions and expenses. One of the most important part of such systems is transmission lines. This paper presents a survey on recent machine learning-based techniques for fault detection, classification, and location estimation in transmission lines. In order to provide reliable and resilient electrical power energy, faster and more accurate fault identification tools are required. Costly consequences of probable faults motivate the need for immediate actions to detect them using intelligent methods, especially emerging machine learning approaches that are powerful in solving diagnosis problems. This paper presents a comprehensive review of various machine learning methodologies including naive Bayesian classifier, decision tree, random forest, k-nearest neighbor, and support vector machine as well as artificial neural networks such as feedforward neural network, convolutional neural network, and adaptive neuro-fuzzy inference system that have been used to detect, classify, and locate faults in transmission lines.
Keywords:  
Transmission line
Machine learning
Deep learning
Fault detection
Fault type classification
Fault location estimation
Artificial neural network
Convolutional neural network
Adaptive neuro-fuzzy inference system
Author(s) Name:  Fatemeh Mohammadi Shakiba, S. Mohsen Azizi, Mengchu Zhou & Abdullah Abusorrah
Journal name:  Artificial Intelligence Review
Conferrence name:  
Publisher name:  Springer
DOI:  10.1007/s10462-022-10296-0
Volume Information:  
Paper Link:   https://link.springer.com/article/10.1007/s10462-022-10296-0