Development of correlation to predict the efficiency of a hydro machine under different operating conditions
(2022) In Sustainable Energy Technologies and Assessments 50.- Abstract
The global energy demand is increasing due to an increase in economic growth and urbanization which is set to rise by 4.6% in 2021. A major part of this increasing energy demand is accomplished by fossil fuels which create environmental pollution. Hydropower is the most mature, reliable, and cost-effective source of energy. However, the operation and maintenance (O&M) of hydro turbines is the main concern. The flowing water carries the sediment which passes through the underwater parts and creates silt erosion problems. A number of correlations are available in the literature to predict the silt erosion in hydro turbines considering very few parameters. However, no study has been reported on the complete scenario on O&M of... (More)
The global energy demand is increasing due to an increase in economic growth and urbanization which is set to rise by 4.6% in 2021. A major part of this increasing energy demand is accomplished by fossil fuels which create environmental pollution. Hydropower is the most mature, reliable, and cost-effective source of energy. However, the operation and maintenance (O&M) of hydro turbines is the main concern. The flowing water carries the sediment which passes through the underwater parts and creates silt erosion problems. A number of correlations are available in the literature to predict the silt erosion in hydro turbines considering very few parameters. However, no study has been reported on the complete scenario on O&M of hydropower plants. Under the present study, an attempt has been made to develop correlations for the efficiency factor using Curve fitting, ANN, and Support Vector Machine (SVM) methods. It is found that the developed correlation for efficiency using the ANN method is more reliable than other techniques. It is found to predict the efficiency with R2-value as 0.999986 having an average absolute percentage error of 0.0124% at RMSE of 0.0874%. The developed correlation may be used for developing efficient O&M strategies for hydropower plants.
(Less)
- author
- Kumar, Krishna LU and Saini, R. P.
- publishing date
- 2022-03
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Artificial Intelligence, Correlation, Hydropower, Operation & maintenance, Silt
- in
- Sustainable Energy Technologies and Assessments
- volume
- 50
- article number
- 101859
- publisher
- Elsevier
- external identifiers
-
- scopus:85121291077
- ISSN
- 2213-1388
- DOI
- 10.1016/j.seta.2021.101859
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © 2021 Elsevier Ltd
- id
- 2899c976-f7ac-41f9-bc6d-29ed9fe133a1
- date added to LUP
- 2024-04-15 12:55:39
- date last changed
- 2024-05-16 14:46:46
@article{2899c976-f7ac-41f9-bc6d-29ed9fe133a1, abstract = {{<p>The global energy demand is increasing due to an increase in economic growth and urbanization which is set to rise by 4.6% in 2021. A major part of this increasing energy demand is accomplished by fossil fuels which create environmental pollution. Hydropower is the most mature, reliable, and cost-effective source of energy. However, the operation and maintenance (O&M) of hydro turbines is the main concern. The flowing water carries the sediment which passes through the underwater parts and creates silt erosion problems. A number of correlations are available in the literature to predict the silt erosion in hydro turbines considering very few parameters. However, no study has been reported on the complete scenario on O&M of hydropower plants. Under the present study, an attempt has been made to develop correlations for the efficiency factor using Curve fitting, ANN, and Support Vector Machine (SVM) methods. It is found that the developed correlation for efficiency using the ANN method is more reliable than other techniques. It is found to predict the efficiency with R<sup>2</sup>-value as 0.999986 having an average absolute percentage error of 0.0124% at RMSE of 0.0874%. The developed correlation may be used for developing efficient O&M strategies for hydropower plants.</p>}}, author = {{Kumar, Krishna and Saini, R. P.}}, issn = {{2213-1388}}, keywords = {{Artificial Intelligence; Correlation; Hydropower; Operation & maintenance; Silt}}, language = {{eng}}, publisher = {{Elsevier}}, series = {{Sustainable Energy Technologies and Assessments}}, title = {{Development of correlation to predict the efficiency of a hydro machine under different operating conditions}}, url = {{http://dx.doi.org/10.1016/j.seta.2021.101859}}, doi = {{10.1016/j.seta.2021.101859}}, volume = {{50}}, year = {{2022}}, }