Application of machine learning for hydropower plant silt data analysis
Kumar, Krishna LU
and Saini, R. P.
(2020)
2020 International Conference on Innovations in Clean Energy Technologies, ICET 2020
p.5575-5579
- Abstract
Among all renewable energy resources, hydropower is the most predictable and reliable source of energy. In the Himalayan region, most of the hydropower plants suffer from the problem of silt erosion. During the monsoon period, the quantum of silt particles is remained quite high, which damages the hydro-mechanical components of the plant. In order to reduce the risk that occurred by the silt erosion, a popular machine learning-based technique can be used. The Self-Organizing Map (SOM) algorithm based on artificial neural networks offers a broad range of techniques for the visualization of data. Under the present paper, a novel technique is used on MB-II (304 MW) hydropower plant of UJVN Ltd., which will classify the density of silt data... (More)
Among all renewable energy resources, hydropower is the most predictable and reliable source of energy. In the Himalayan region, most of the hydropower plants suffer from the problem of silt erosion. During the monsoon period, the quantum of silt particles is remained quite high, which damages the hydro-mechanical components of the plant. In order to reduce the risk that occurred by the silt erosion, a popular machine learning-based technique can be used. The Self-Organizing Map (SOM) algorithm based on artificial neural networks offers a broad range of techniques for the visualization of data. Under the present paper, a novel technique is used on MB-II (304 MW) hydropower plant of UJVN Ltd., which will classify the density of silt data resulting from neighbor and radius based distances. Based on the analysis of the silt data, maintenance scheduling of hydropower plants can be planned. The SOM technique provides a better insight into silt data. It identifies outliers data as well as useful data that can be used for accurate prediction of daily silt pattern.
(Less)
- author
- Kumar, Krishna
LU
and Saini, R. P.
- publishing date
- 2020
- type
- Contribution to conference
- publication status
- published
- subject
- keywords
- ANN, Clustering, Hydropower, Machine learning, Renewable Energy, SOM
- pages
- 5 pages
- conference name
- 2020 International Conference on Innovations in Clean Energy Technologies, ICET 2020
- conference location
- Bhopal, India
- conference dates
- 2020-08-26 - 2020-08-27
- external identifiers
-
- scopus:85112698786
- DOI
- 10.1016/j.matpr.2020.09.375
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © 2020 Elsevier Ltd. All rights reserved.
- id
- 5856eaa0-d6be-4457-9aa6-eaab692fc378
- date added to LUP
- 2024-04-15 13:05:59
- date last changed
- 2024-05-16 14:46:48
@misc{5856eaa0-d6be-4457-9aa6-eaab692fc378,
abstract = {{<p>Among all renewable energy resources, hydropower is the most predictable and reliable source of energy. In the Himalayan region, most of the hydropower plants suffer from the problem of silt erosion. During the monsoon period, the quantum of silt particles is remained quite high, which damages the hydro-mechanical components of the plant. In order to reduce the risk that occurred by the silt erosion, a popular machine learning-based technique can be used. The Self-Organizing Map (SOM) algorithm based on artificial neural networks offers a broad range of techniques for the visualization of data. Under the present paper, a novel technique is used on MB-II (304 MW) hydropower plant of UJVN Ltd., which will classify the density of silt data resulting from neighbor and radius based distances. Based on the analysis of the silt data, maintenance scheduling of hydropower plants can be planned. The SOM technique provides a better insight into silt data. It identifies outliers data as well as useful data that can be used for accurate prediction of daily silt pattern.</p>}},
author = {{Kumar, Krishna and Saini, R. P.}},
keywords = {{ANN; Clustering; Hydropower; Machine learning; Renewable Energy; SOM}},
language = {{eng}},
pages = {{5575--5579}},
title = {{Application of machine learning for hydropower plant silt data analysis}},
url = {{http://dx.doi.org/10.1016/j.matpr.2020.09.375}},
doi = {{10.1016/j.matpr.2020.09.375}},
year = {{2020}},
}