Browsing by Author "Çelebioğlu, Kutay"

Now showing 1 - 2 of 2

Citation Count: Kaak, Abdul Rahman Sabra...et al. (2024). "A novel CFD-ANN approach for plunger valve optimization: Cost-effective performance enhancement", Flow Measurement and Instrumentation, Vol. 97.
A novel CFD-ANN approach for plunger valve optimization: Cost-effective performance enhancement
(2024) Kaak, Abdul Rahman Sabra; Çelebioğlu, Kutay; Bozkuş, Zafer; Ulucak, Oğuzhan; Aylı, Ece; 265836
This paper introduces a novel computational fluid dynamics-artificial neural network (CFD-ANN) approach that has been devised to enhance the efficiency of plunger valves. The primary emphasis of this research is to achieve an optimal equilibrium between hydraulic flow and geometric configuration. This study is a novel contribution to the field as it explores the flow dynamics of plunger valves using Computational Fluid Dynamics (CFD) and proposes a unique methodology by incorporating Machine Learning (ML) for performance forecasting. An artificial neural network (ANN) architecture was developed using a thorough comprehension of flow physics and the impact of geometric parameters acquired through computational fluid dynamics (CFD). Using optimization, the primary aspects of the Artificial Neural Network (ANN), including the learning algorithm and the number of hidden layers, have been modified. This refinement has resulted in the development of an architecture exhibiting a remarkably high R2 value of 0.987. This architectural design was employed to optimize the plunger valve. By utilizing Artificial Neural Networks (ANN), a comprehensive analysis comprising 1000 distinct configurations was effectively performed, resulting in a significant reduction in time expenditure compared to relying on Computational Fluid Dynamics (CFD). The result was a refined arrangement that achieved maximum head loss, subsequently verified using computational fluid dynamics (CFD) simulations, resulting in a minimal discrepancy of 2.66%. The efficacy of artificial neural networks (ANN) becomes apparent due to their notable cost-efficiency, along with their capacity to produce outcomes that are arduous and expensive to get through conventional optimization research utilizing computational fluid dynamics (CFD).
Citation Count: Çelebioğlu, Kutay...et al. "Exploring the potential of artificial intelligence tools in enhancing the performance of an inline pipe turbine", Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering.
Exploring the potential of artificial intelligence tools in enhancing the performance of an inline pipe turbine
(2024) Çelebioğlu, Kutay; Aylı, Ece; Çetintürk, Hüseyin; Taşçıoğlu, Yiğit; Aradağ, Selin; 265836
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.