Data-driven modeling of fuel consumption for turboprop-powered civil airliners

Abstract

Next to empirical correlations for the specific range, fuel flow rate, and specific fuel consumption, a response surface model for estimates of the fuel consumption in early design stages is presented and validated. The response-surface's coefficients are themselves predicted from empirical correlations based solely on the operating empty weight. The model and correlations are all derived from fuel consumption data of nine current civil turbo-propeller aircraft and are validated on a separate set. The model can accurately predict fuel weights of new designs for any combination of payload and range within the current range of efficiency of the propulsion. The accuracy of the model makes it suited for preliminary and conceptual design of near-in-kind turbopropeller aircraft. The model can shorten the design cycle by delivering fast and accurate fuel weight estimates from the first design iteration once the operating empty weight is known. Since it is based solely on the operating empty weight and it is accurate, the model is a sound variant to the Breguet range equation in order to make accurate fuel weight estimates.