Artificial Neural Network Model for Estimating the Pelton Turbine Shaft Power of a Micro-Hydropower Plant under Different Operating Conditions

• Published in: Energies (Basel) Vol. 17; no. 14; p. 3597
• Main Authors: Delgado-Currín, Raúl R., Calderón-Muñoz, Williams R., Elicer-Cortés, J. C.
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2024
• Subjects: Accuracy; Algorithms; Analysis; Artificial intelligence; artificial neural networks; Data entry; Efficiency; Electric generators; Generators; Hydraulics; Hydroelectric plants; Hydroelectric power; Hydroelectric power plants; Machine learning; Mean square errors; micro-hydropower plant; Modernization; Neural networks; Neurons; Pelton turbine; Pelton turbine shaft power; Sensors; Turbine industry; Turbines; Water-power; Chile; Germany
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en17143597

The optimal performance of a hydroelectric power plant depends on accurate monitoring and well-functioning sensors for data acquisition. This study proposes the use of artificial neural networks (ANNs) to estimate the Pelton turbine shaft power of a 10 kW micro-hydropower plant. In the event of a failure of the sensor measuring the torque and/or rotational speed of the Pelton turbine shaft, the synthetic turbine shaft power data generated by the ANN will allow the turbine output power to be determined. The experimental data were obtained by varying the operating conditions of the micro-hydropower plant, including the variation of the input power to the electric generator and the variation of the injector opening. These changes consequently affected the flow rate and the pressure head at the turbine inlet. The use of artificial neural networks (ANNs) was deemed appropriate due to their ability to model complex relationships between input and output variables. The ANN structure comprised five input variables, fifteen neurons in a hidden layer and an output variable estimating the Pelton turbine power. During the training phase, algorithms such as Levenberg–Marquardt (L–M), Scaled Conjugate Gradient (SCG) and Bayesian were employed. The results indicated an error of 0.39% with L–M and 7% with SCG, with the latter under high-flow and -energy consumption conditions. This study demonstrates the effectiveness of artificial neural networks (ANNs) trained with the Levenberg–Marquardt (L–M) algorithm in estimating turbine shaft power. This contributes to improved performance and decision making in the event of a torque sensor failure.