Optimum Design of a Single Circumferential Groove to Improve the Compressor Performance with CFD, Neural Networks and Multi-Objective Genetic Algorithm

The aim of this paper is the optimum design of a single circumferential groove for NASA Rotor 37, a transonic compressor. The design variables are the width, the depth and the position of the groove. Also the objective functions are the stall margin and the peak efficiency. The total pressure ratio at the near stall condition is used as a criterion to choose the optimum design. Neural networks are used to model the relation between design variables and objective functions. 123 various design points are simulated by CFD and the results are used to train the networks. Afterwards, a multi-objective genetic algorithm is used to optimize the design based on the maximum stall margin and the minimum reduction of the peak efficiency. After sorting the Pareto front according to the stall margin value, the first design point whose total pressure ratio is larger than the smooth wall condition, is selected as the optimum design. Simulation of the compressor with optimum groove shows the increase of the stall margin by 6.2 percent with negligible effect on the efficiency.