Shape optimization of impingement and film cooling holes on a flat plate using a feedforward ANN and GA

Numerical simulations of a three-dimensional model of impingement and film cooling on a flat plate are presented and validated with the available experimental data. Four different turbulence models were utilized for simulation, in which SST  had the highest precision, resulting in less than 4% maximum error in temperature estimation. A simplified geometry with periodic boundary conditions is designed, based on the main geometry, and is used for the optimization procedure. Six geometrical parameters related to impingement and film holes are selected as design variables. To further reduce the time required for optimization, a feedforward neural network is implemented for the function estimation, and 584 CFD observations were performed for randomly generated design points. The data from CFD simulations were fed to network for training and test operations, and the results with good consistency were extracted from the network. The objective of the optimization is to minimize the coolant mass flow rate, subject to maximum temperature and maximum temperature gradient in solid domain being equal to or lower than their values in base design. A genetic algorithm (GA) with 100 population and 50 iterations, coupled with an artificial neural network (ANN), was used for optimization. Finally, the optimum design is simulated numerically to find the exact values of the output parameters. The CFD results for optimum design shows 44% less coolant mass flow rate while both optimization constraints are satisfied. Such a reduction in the coolant flow rate has a huge impact on the overall performance of a typical gas turbine, which is discussed in this paper.