An Evolutionary Algorithm using ANN (EASY) was used to drive the optimization ... Design of a Francis Turbine Runner using Global Optimization Algorithms”.
Finally, evolutionary algorithms represented by multi-objective genetic algorithm (MOGA) are applied to determine optimum shapes for the turbine
An optimization algorithm is proposed and applied to the runner of a low specific speed Francis turbine, with an optimization strategy specifically constructed
The present paper focuses on the application of the multi-objective optimization algorithm to the design of a small Francis turbine runner. The optimization
Based on this, this study uses the Analytic Hierarchy Process (AHP)-entropy weight method and Multi-Objective Lichtenberg Algorithm (MOLA) to optimize the
# Machine Learning for Hydraulic Francis Runner Design Optimization. A new methodology uses **3D Inverse Design** technology coupled with **Reactive Response Surface (RRS) Machine Learning** to rapidly optimize Francis hydraulic turbine runners. This approach requires only **10 input parameters** to explore a vast design space and, in just a few hours, discovered optimized designs that showed significant performance gains, including **5-9 percentage points higher efficiency** and an **8-28% increase in shaft power** over the baseline model. In this blog we look at how ADT’s Reactive Response Surface + CAE technology (RRS+CAE) is driving better hydraulic turbine design through Machine Learning. ## • The Francis Runner performance challenge - and the solution • Where to start - Generate a meanline Francis runner design • 3D Inverse Design is the enabling technology for Machine Learning • How to establish a baseline for turbine performance • Optimization of a Francis runner via Machine Learning • RRS gives design choices and performance gains • Final validation of the Machine Learning solution • Conclusions.
et al.: Development of High Specific Speed Francis Turbine for Low Head HPP blade, the automatic mesh generation, CFD calculations with post-processing and the own optimization cycle with defined objective function. ed., Kluwer Academic Publishers, Dordrecht, 1992, 500 p., ISBN 0-7923-1505-7 [2] Obrovsky J., Seda B., Zouhar J.: Experience with hydraulic design of low specific speed turbine, 4th IAHR International Meeting of the Workgroup on Cavitation and Dynamic Problems, 2011, Belgrade, Serbia [3] Sado K., ShyangMaw L., Yasuyuki E.: Virtual model test for a Francis turbine, 25th IAHR Symposium on Hydraulic Machinery and Systems, 2010, Timisoara, Romania [4] Skotak A., Obrovsky J.: The utilization of optimization for water turbine blade shape uprating, Fluent Userˇ zs Meeting, 2006, Hrotovice, Czech Republic [5] Skotak A., Obrovsky J.: Shape Optimization of a Kaplan Turbine Blade, 23rd IAHR Sympo-sium on Hydraulic Machinery and Systems, 2006, Yokohama, Japan, paper 233 [6] Skotak A., Obrovsky J.: Analysis of the flow in the water turbine draft tube in Fluent and CFX, 25th CADFEM Userˇ zs Meeting, 2007, Dresden, Germany [7] Storn R., Price K.: Differential Evolution – A Simple and Efficient Heuristic for Global Op-timization over Continuous Spaces, Journal of Global Optimization, Kluwer Academic Pub-lishers, 1997, vol.
# Conceptual Design Optimization of Francis Turbines. ## Uploaded by. Hydraulic turbines have been studied, designed, built and put into operation for nearly 250 years. This work presents a conceptual design methodology for Francis turbines. It combines simplified models for the turbomachine fluid flow with numerical optimization techniques. ## Share this document. ## Footer menu. ## Support. ## Legal. ## Social. ## Get our free apps. Scribd - Download on the App Store. Scribd - Get it on Google Play.