Power Setting Estimation of Departing Civil Jet Aircraft Based on Machine Learning
Author:
- 1 July 2024
- journal article
- research article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Aircraft
- Vol. 61 (4) , 1195-1204
Abstract
This paper presents an approach for estimating the power setting, indicated as N1, the rotational speed of the low-pressure shaft, of departing civil jet aircraft to be used as input for accurate noise calculations. The method utilizes the machine learning approach random forest regression and is trained using flight data recorder data divided into three departure sections. Each section uses a unique set of three to four model features based on easily accessible data, such as position and airport meteorological data. Unlike previous methods, neither fixed configuration altitudes, aerodynamic coefficients, or engine coefficients, nor takeoff mass or wind information are required as inputs. To assess the performance of the method, noise calculations for departures of five aircraft types, including narrow- and wide-body jet aircraft, were performed. Comparing overall and aircraft-specific noise levels, calculated from estimated N1 versus recorded N1 values from flight data recorder data, revealed small differences of less than 1 dB. Overall, the present machine-learning-based approach provides reliable estimates of power settings for departing civil jet aircraft, offering improved accuracy and avoiding the need for numerous assumptions and hardly accessible data.Keywords
Funding Information
- Federal Office of Civil Aviation FOCA (SFLV 2019-054)
This publication has 16 references indexed in Scilit:
- Validation of the sonAIR aircraft noise simulation modelNoise Mapping, 2021
- Estimation of Flight-Phase-Specific Jet Aircraft Parameters for Noise SimulationsJournal of Aircraft, 2020
- Hyperparameters and tuning strategies for random forestWIREs Data Mining and Knowledge Discovery, 2019
- Aircraft Noise Emission Model Accounting for Aircraft Flight ParametersJournal of Aircraft, 2018
- Learning the aircraft mass and thrust to improve the ground-based trajectory prediction of climbing flightsTransportation Research Part C: Emerging Technologies, 2013
- Aircraft Noise2011
- The Elements of Statistical Learning2009
- Hypertension and Exposure to Noise Near Airports: the HYENA StudyEnvironmental Health Perspectives, 2008
- Random ForestsMachine Learning, 2001
- An Introduction to the Bootstrap1993