Study on hydroturbine power trend prediction based on machine learning

The application of computational fluid dynamics combined with 3D modeling of the hydraulic model was discussed in this paper. Through the complex calculation of the internal low field, dynamic simulation was used to predict the characteristics of water energy index. Based on the collection of a larg...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy reports 2023-11, Vol.10, p.1996-2005
Hauptverfasser: Huang, Xiaoping, Lu, Qiu, Zhou, Huamao, Huang, Wenzhe, Wang, Shoufen
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The application of computational fluid dynamics combined with 3D modeling of the hydraulic model was discussed in this paper. Through the complex calculation of the internal low field, dynamic simulation was used to predict the characteristics of water energy index. Based on the collection of a large number of different types of turbine operation data in different working conditions, the improved multi-layer neural network power prediction model based on the adaptive inverse normalization strategy and the improved grey wolf algorithm were used to optimize the least squares support vector machine power prediction model. Rlue activation function was used in the improved multi-layer neural network model uses to improve the computation speed and prevent gradient disappearance. Combined with L2 regularization to prevent data overfitting, Adam gradient optimizer was applied to achieve fast convergence of network output. The simulation results shown that the method can realize the high precision prediction of turbine output power.
ISSN:2352-4847
2352-4847
DOI:10.1016/j.egyr.2023.08.084