Comparison between IA prediction and calculation of relay operation time with overcurrent protection 51 inverse ANSI curve (#802)
Read ArticleDate of Conference
July 17-19, 2024
Published In
"Sustainable Engineering for a Diverse, Equitable, and Inclusive Future at the Service of Education, Research, and Industry for a Society 5.0."
Location of Conference
Costa Rica
Authors
Castillo Caceres, Cesar
Ticona Huillca, Lucy
Gomez Esteba, Dario
Chani Ollachica, Deidamia
Abstract
This work focuses on making a comparison between the prediction of an artificial intelligence and a mathematical formula that calculates the operation time of an overcurrent protection relay with a very inverse ANSI curve. To make this comparison, first, a neural network was built to learn to predict the operation time of an overcurrent protection relay with a very inverse ANSI curve. Then, a web interface was developed where the results of the neural network's prediction and the results of the mathematical calculation using the aforementioned formula can be visualized. To build the neural network, the Google Colab interface was used with the Python programming language, and to create the web interface, HTML, CSS, and JavaScript were employed. With the neural network and web interface developed, a comparison is carried out between the neural network's prediction and a mathematical formula that calculates the operation time of an overcurrent protection relay with a very inverse ANSI curve using three examples, along with discussions, observations, and conclusions.