Optimizing chute-flip bucket system based on meta-modelling approach

Abstract

Optimal design of chute-flip bucket (CFB) system depends on various parameters, among which energy dissipation and cavitation prevention are the most important. This study develops a simulation-optimization model based on a calibrated Flow-3D numerical model, multi-layer perceptron artificial neural network (MLP-ANN), and genetic algorithm (GA) optimization approach for determining the optimal geometry of the CFB system. To alleviate the computational time burden of the Flow-3D numerical model, a MLP-ANN meta-model is developed based on some limited simulations of Flow-3D. The meta-model framework is then coupled with GA to provide an efficient design framework for the CFB system. The proposed framework is employed to design optimal geometry of the CFB system of the Jareh dam in Ahvaz, Iran. The results show that the obtained optimal design increases the cavitation index up to 30% and energy dissipation up to 32% compared to the old engineering design already in place.

Metamodel-Based Simulation Optimization: A Systematic Literature Review

“…Many authors have also studied MBSO techniques to optimize product designs. Examples include applications related to the automotive (Fu and Sahin, 2004;Ivanova and Kuhnt, 2014;Stork et al, 2008), energy (Sharif and Hammad 2019;Storti et al, 2019), hydropower (Bananmah et al, 2020;Mooselu et al, 2019), and transit infrastructure (Yin et al, 2016) sectors. Many authors have also studied MBSO applied to resource allocation problems (e.g., (Coelho and Pinto 2018;Song et al, 2005;Yousefi and Yousefi 2019;Zeinali et al, 2015), to synthetic mathematical functions (e.g., Baquela and Olivera, 2019;Kim and Boukouvala, 2020;Gonzalez et al, 2020;Wang et al, 2020), and to urban traffic issues Chong and Osorio 2018;Osorio and Bierlaire 2013;Osorio and Chong 2015).…”

Conflict resolution in the multi-stakeholder stepped spillway design under uncertainty by machine learning techniques

“…Numerical simulation models such as Computational Fluid Dynamics (CFD) codes provided a proper context to evaluate the parameters, which were not explored/measured in physical models [12]. Further, soft computing methods were utilized to understand the non-linear relationships between design parameters and optimize the hydraulic properties [3,10,15,18,19].…”