Using Neural Networks to Develop a Database of Failures and Emergencies at Hydroelectric Power Stations

The article provides an example of employing a neural network and a natural language model to develop the database of failures and emergencies at hydroelectric power stations around the world that is available at JSC Vedeneev VNIIG. Using particular examples in conjunction with the t-SNE machine lea...

Full description

Saved in:
Bibliographic Details
Published in:Power technology and engineering 2024, Vol.58 (3), p.406-411
Main Authors: Shipilov, A. V., Tikhonova, T. S., Pechantikova, O. A.
Format: Article
Language:English
Subjects:
Algorithms
Clustering
Electrical Machines and Networks
Emergencies
Energy
Energy Systems
Foundations
Geoengineering
Hydraulics
Hydroelectric power stations
Machine learning
Neural networks
Power Electronics
Power plants
Renewable and Green Energy
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The article provides an example of employing a neural network and a natural language model to develop the database of failures and emergencies at hydroelectric power stations around the world that is available at JSC Vedeneev VNIIG. Using particular examples in conjunction with the t-SNE machine learning algorithm for visualization and the DBSCAN data clustering algorithm, the study shows an approach for enhancing the database. This technique enables a remarkable improvement in the selection of analog objects when justifying accident scenarios.
ISSN:1570-145X
1570-1468
DOI:10.1007/s10749-024-01826-7