Evaluating Deep Learning Networks Versus Hybrid Network for Smart Monitoring of Hydropower Plants
One of the main goals of the International Energy Agency (IEA) is to manage and utilize clean energy to achieve net zero emissions by 2050. Hydropower plants can significantly contribute to this goal as they are vital components of the global energy infrastructure, providing a clean, safe, and susta...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/17/22/5670 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850267471716548608 |
|---|---|
| author | Fatemeh Hajimohammadali Emanuele Crisostomi Mauro Tucci Nunzia Fontana |
| author_facet | Fatemeh Hajimohammadali Emanuele Crisostomi Mauro Tucci Nunzia Fontana |
| author_sort | Fatemeh Hajimohammadali |
| collection | DOAJ |
| description | One of the main goals of the International Energy Agency (IEA) is to manage and utilize clean energy to achieve net zero emissions by 2050. Hydropower plants can significantly contribute to this goal as they are vital components of the global energy infrastructure, providing a clean, safe, and sustainable power source. Accordingly, there is great interest in developing methods to prevent errors and anomalies and ensure full operational availability. With modern hydropower plants equipped with sensors that capture extensive data, machine learning algorithms utilizing these data to detect and predict anomalies have gained research attention. This paper demonstrates that deep learning algorithms are particularly powerful in predicting time series. Three well-known deep learning networks are examined and compared to previous approaches, followed by the introduction of a new, innovative hybrid network. Using real-world data from two hydropower plants, the hybrid model outperforms individual deep learning models by achieving more accurate fault detection, reducing false positives, offering early fault prediction, and identifying faults several weeks before occurrence. These results showcase the hybrid network’s potential to enhance maintenance planning, reduce downtime, and improve operational efficiency in energy systems. |
| format | Article |
| id | doaj-art-cf9c6eb629c34a08af19dde78b82ff75 |
| institution | OA Journals |
| issn | 1996-1073 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-cf9c6eb629c34a08af19dde78b82ff752025-08-20T01:53:45ZengMDPI AGEnergies1996-10732024-11-011722567010.3390/en17225670Evaluating Deep Learning Networks Versus Hybrid Network for Smart Monitoring of Hydropower PlantsFatemeh Hajimohammadali0Emanuele Crisostomi1Mauro Tucci2Nunzia Fontana3Department of Energy, Systems, Territory and Constructions Engineering, University of Pisa, 56122 Pisa, ItalyDepartment of Energy, Systems, Territory and Constructions Engineering, University of Pisa, 56122 Pisa, ItalyDepartment of Energy, Systems, Territory and Constructions Engineering, University of Pisa, 56122 Pisa, ItalyDepartment of Energy, Systems, Territory and Constructions Engineering, University of Pisa, 56122 Pisa, ItalyOne of the main goals of the International Energy Agency (IEA) is to manage and utilize clean energy to achieve net zero emissions by 2050. Hydropower plants can significantly contribute to this goal as they are vital components of the global energy infrastructure, providing a clean, safe, and sustainable power source. Accordingly, there is great interest in developing methods to prevent errors and anomalies and ensure full operational availability. With modern hydropower plants equipped with sensors that capture extensive data, machine learning algorithms utilizing these data to detect and predict anomalies have gained research attention. This paper demonstrates that deep learning algorithms are particularly powerful in predicting time series. Three well-known deep learning networks are examined and compared to previous approaches, followed by the introduction of a new, innovative hybrid network. Using real-world data from two hydropower plants, the hybrid model outperforms individual deep learning models by achieving more accurate fault detection, reducing false positives, offering early fault prediction, and identifying faults several weeks before occurrence. These results showcase the hybrid network’s potential to enhance maintenance planning, reduce downtime, and improve operational efficiency in energy systems.https://www.mdpi.com/1996-1073/17/22/5670hydropower plantsprocess controlpredictive maintenancefault detectionhybrid deep learning modelstime series forecasting |
| spellingShingle | Fatemeh Hajimohammadali Emanuele Crisostomi Mauro Tucci Nunzia Fontana Evaluating Deep Learning Networks Versus Hybrid Network for Smart Monitoring of Hydropower Plants Energies hydropower plants process control predictive maintenance fault detection hybrid deep learning models time series forecasting |
| title | Evaluating Deep Learning Networks Versus Hybrid Network for Smart Monitoring of Hydropower Plants |
| title_full | Evaluating Deep Learning Networks Versus Hybrid Network for Smart Monitoring of Hydropower Plants |
| title_fullStr | Evaluating Deep Learning Networks Versus Hybrid Network for Smart Monitoring of Hydropower Plants |
| title_full_unstemmed | Evaluating Deep Learning Networks Versus Hybrid Network for Smart Monitoring of Hydropower Plants |
| title_short | Evaluating Deep Learning Networks Versus Hybrid Network for Smart Monitoring of Hydropower Plants |
| title_sort | evaluating deep learning networks versus hybrid network for smart monitoring of hydropower plants |
| topic | hydropower plants process control predictive maintenance fault detection hybrid deep learning models time series forecasting |
| url | https://www.mdpi.com/1996-1073/17/22/5670 |
| work_keys_str_mv | AT fatemehhajimohammadali evaluatingdeeplearningnetworksversushybridnetworkforsmartmonitoringofhydropowerplants AT emanuelecrisostomi evaluatingdeeplearningnetworksversushybridnetworkforsmartmonitoringofhydropowerplants AT maurotucci evaluatingdeeplearningnetworksversushybridnetworkforsmartmonitoringofhydropowerplants AT nunziafontana evaluatingdeeplearningnetworksversushybridnetworkforsmartmonitoringofhydropowerplants |