Predicting the Energy and Exergy Performance of F135 PW100 Turbofan Engine via Deep Learning Approach

EasyChair Preprint 7957

Abstract

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

Keyphrases: Dual spool turbofan, Energy, Exergy, F135 PW100, Mixed-flow turbofan, deep learning

@booklet{EasyChair:7957,
  author    = {Mohammadreza Sabzehali and Amir Hossein Rabiee and Mahdi Alibeigia and Amir Mosavi},
  title     = {Predicting the Energy and Exergy Performance of F135 PW100 Turbofan Engine via Deep Learning Approach},
  howpublished = {EasyChair Preprint 7957},
  year      = {EasyChair, 2022}}