Predicting the energy and exergy performance of F135 PW100 turbofan engine via deep learning approach

In the present study, effects of flight-Mach number, flight altitude, fuel types, and intake air temperature on thrust specific consumption, thrust, mass flow rate, thermal propulsive efficiecies, as well exergetic efficiency exergy destruction rate in F135 PW100 engine are investigated. Based results obtained first phase, to model thermodynamic performance aforementioned cycle, Flight-Mach number altitude considered be 2.5 30,000 m, respectively; due operational advantage supersonic flying at high conditions, higher hydrogen fuel. Accordingly, second taking into account mentioned an intelligent has been predict output parameters (i.e., overall efficiency) using deep learning method. attained neural model, pressure ratio high-pressure turbine, fan ratio, turbine inlet temperature, bypass input parameters. The provided datasets randomly divided two sets: one contains 6079 samples for training set 1520 testing. particular, Adam optimization algorithm, cost function mean square error, active rectified linear unit used train network. show that error percentage is equal 5.02%, 1.43%, 2.92% efficiency, respectively, which indicates success estimating problem.