Evaluation of novel-objective functions in the design optimization of a transonic rotor by using deep learning

Design optimization of transonic airfoils for rotary blades is a challenging subject that remarkably affects the stage and overall performance axial-flow compressors. This paper describes surrogate-based multi-objective process over blade. blade works in first high-pressure pre-designed industrial axial compressor. It experiences massive separation behind an impinging shock wave its suction side, resulting very low efficiency whole stage. The key components current approach involve application novel-objective functions pressure distribution airfoils, called location flat-roof-top factor, to design supercritical airfoils. Moreover, ensure advantages having attached boundary layer high efficient blade, area separated also defined alongside other well-known objective related polar loss diagram. Notably, sequential feed-forward multi-layer perceptron designed construct mapping between airfoil geometrical variables functions. A numerical simulation compressor has shown improvement about 10% 0.17% compressor, respectively, with when employing optimized rotor at