Identification of the Conduit Water Starting Time Constant in Hydropower Plants Using LSTM and MLP Machine Learning Algorithms
Journal
Precision Mechanics & Digital Fabrication
Date Issued
2025-03-31
Author(s)
DOI
10.56578/pmdf020105
Abstract
The accurate determination of the conduit water starting time constant (
) is critical for optimizing hydro turbine performance and dynamic control in hydropower plants. Instead of relying on conventional calculation methods, machine learning (ML) techniques, specifically long short-term memory (LSTM) networks and multilayer perceptron (MLP) models, have been employed to identify
. The dataset used for model training and validation comprises real operational data collected from two hydropower plants. The effectiveness of both algorithms in
identification has been evaluated through simulation, with Python serving as the primary programming environment. The findings indicate that, despite its more complex architecture, LSTM does not necessarily yield superior results. In contrast, MLP, as a relatively simpler model, demonstrates greater accuracy in estimating
, suggesting that intricate network structures are not always required for precise identification. Additionally, an optimization function (
) has been utilized to assess the reliability of the identified
values by comparing them with actual hydro turbine responses. The results underscore the practicality of MLP in hydropower system modeling, providing a computationally efficient alternative for conduit water starting time constant identification. These insights contribute to improving real-time turbine control and enhancing the efficiency of hydropower generation.
) is critical for optimizing hydro turbine performance and dynamic control in hydropower plants. Instead of relying on conventional calculation methods, machine learning (ML) techniques, specifically long short-term memory (LSTM) networks and multilayer perceptron (MLP) models, have been employed to identify
. The dataset used for model training and validation comprises real operational data collected from two hydropower plants. The effectiveness of both algorithms in
identification has been evaluated through simulation, with Python serving as the primary programming environment. The findings indicate that, despite its more complex architecture, LSTM does not necessarily yield superior results. In contrast, MLP, as a relatively simpler model, demonstrates greater accuracy in estimating
, suggesting that intricate network structures are not always required for precise identification. Additionally, an optimization function (
) has been utilized to assess the reliability of the identified
values by comparing them with actual hydro turbine responses. The results underscore the practicality of MLP in hydropower system modeling, providing a computationally efficient alternative for conduit water starting time constant identification. These insights contribute to improving real-time turbine control and enhancing the efficiency of hydropower generation.
File(s)![Thumbnail Image]()
Loading...
Name
PMDF_02.01_05.pdf
Size
1.38 MB
Format
Adobe PDF
Checksum
(MD5):c6d65618fe8dd7b6b0799f84dbab72b1