Exploring the Potential of Artificial Intelligence Tools in Enhancing the Performance of an Inline Pipe Turbine

Abstract

In this study, investigations were conducted using computational fluid dynamics (CFD) to assess the applicability of a Francis-type water turbine within a pipe. The objective of the study is to determine the feasibility of implementing a turbine within a pipe and enhance its performance values within the operating range. The turbine within the pipe occupies significantly less space in hydroelectric power plants since a spiral casing is not used to distribute the flow to stationary vanes. Consequently, production and assembly costs can be reduced. Hence, there is a broad scope for application, particularly in small and medium-scale hydroelectric power plants. According to the results, the efficiency value increases on average by approximately 1.5% compared to conventional design, and it operates with higher efficiencies over a wider flow rate range. In the second part of the study, machine learning was employed for the efficiency prediction of an inline-type turbine. An appropriate Artificial Neural Network (ANN) architecture was initially obtained, with the Bayesian Regularization training algorithm proving to be the best approach for this type of problem. When the suitable ANN architecture was utilized, the prediction was found to be in good agreement with CFD, with an root mean squared error value of 0.194. An R2 value of 0.99631 was achieved with the appropriate ANN architecture.