Aircraft initial mass estimation using Bayesian inference method

Sun, Junzi; Ellerbroek, Joost; Hoekstra, Joris

doi:10.1016/j.trc.2018.02.022

Cited by 44 publications

(30 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study is an extension of our previous preliminary research of Sun et al (2018a), with an improved system model and new insights. Unlike Alligier et al (2015) where the machine learning models use mass estimations from regression methods as training input, or Chati and Balakrishnan (2018) where the machine learning model uses flight recorder data as training input, our method is a purely model-based state estimation approach.…”

Section: Introductionmentioning

confidence: 81%

“…However, regression analysis requires the exploitation of model linearity. Recently Sun et al (2018b) has shown that ADS-B data availability makes it worthwhile to use Bayesian inference methods for the estimation of aircraft mass. The goal of this article is to extend this Bayesian inference approach such that it can incorporate non-linear aircraft evolution equations for the nonlinear Bayesian filtering of aircraft mass, based on ADS-B and Enhanced Mode-S surveillance data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Particle filter for aircraft mass estimation and uncertainty modeling

Sun

Blom

Ellerbroek

2019

Transportation Research Part C: Emerging Technologies

Self Cite

View full text Add to dashboard Cite

A B S T R A C TThis article investigates the estimation of aircraft mass and thrust settings of departing aircraft using a recursive Bayesian method called particle filtering. The method is based on a nonlinear state-space system derived from aircraft point-mass performance models. Using only aircraft surveillance data, flight states such as position, velocity, wind speed, and air temperature are collected and used for the estimations. With the regularized Sample Importance Re-sampling particle filter, we are able to estimate the aircraft mass within 30 seconds once an aircraft is airborne. Using this short flight segment allows the assumption of constant mass and thrust setting. The segment at the start of the climb also represents the time when maximum thrust setting is most likely to occur. This study emphasizes an important aspect of the estimation problem, the observation noise modeling. Four observation noise models are proposed, which are all based on the native navigation accuracy parameters that have been obtained automatically from the surveillance data. Simulations and experiments are conducted to test the theoretical model. The results show that the particle filter is able to quantify uncertainties, as well as determine the noise limit for an accurate estimation. The method of this study is tested with a dataset consisting of 50 Cessna Citation II flights where true masses were recorded. The approaches by Alligier et al. (2013) and Chati and Balakrishnan (2018) have in common that they make use of regression

show abstract

Section: Introductionmentioning

confidence: 81%

Section: Introductionmentioning

confidence: 99%

Particle filter for aircraft mass estimation and uncertainty modeling

Sun

Blom

Ellerbroek

2019

Transportation Research Part C: Emerging Technologies

Self Cite

View full text Add to dashboard Cite

show abstract

“…We consider the mass as a uniformly distributed random variable at each time step. Unlike the informed mass assumption addressed in Sun et al (2018a), the uniformed distribution considers all masses as equally possible. It is sampled together with all other parameters.…”

Section: Uncertaintiesmentioning

confidence: 99%

Estimating aircraft drag polar using open flight surveillance data and a stochastic total energy model

Sun

Ellerbroek

2020

Transportation Research Part C: Emerging Technologies

Self Cite

View full text Add to dashboard Cite

A B S T R A C TIn air traffic management research, aircraft performance models are often used to generate and analyze aircraft trajectories. Although a crucial part of the aircraft performance model, the aerodynamic property of aircraft is rarely available for public research purposes, as it is protected by aircraft manufacturers for commercial reasons. In many studies, a simplified quadratic drag polar model is assumed to compute the drag of an aircraft based on the required lift. In this paper, using surveillance data, we take on the challenge of estimating the drag polar coefficients based on a novel stochastic total energy model that employs Bayesian computing. The method is based on a stochastic hierarchical modeling approach, which is made possible given accurate open aircraft surveillance data and additional analytical models from the literature. Using this proposed method, the drag polar models for 20 of the most common aircraft types are estimated and summarized. By combining additional data from the literature, we propose additional methods allowing aircraft total drag to be calculated under other configurations, such as when flaps and landing gears are deployed. We also include additional models allowing the calculation of wave drag caused by compressibility at high Mach number. Though uncertainties exist, it has been found that the estimated drag polars agree with existing models, as well as CFD simulation results. The trajectory data, performance models, and results related to this study are shared publicly.

show abstract

“…Delahaye et al proposed estimations of the True Air Speed and the wind using radar data [11], [12]. Sun et al estimate the aircraft mass using Bayesian inference methods [13]. Chati et al proposed different learning model types such as Gaussian Process regression [14] and tree-based classification [15] to predict the aircraft fuel flow rate.…”

Section: State Of the Artmentioning

confidence: 99%

Approach and Landing Aircraft On-Board Parameters Estimation with LSTM Networks

Jarry

Delahaye

Féron

2020

2020 International Conference on Artificial Intelligence and Data Analytics for Air Transportation (AIDA-At)

View full text Add to dashboard Cite

This paper addresses the problem of estimating aircraft on-board parameters using ground surveillance available parameters. The proposed methodology consists in training supervised Neural Networks with Flight Data Records to estimate target parameters. This paper investigates the learning process upon three case study parameters: the fuel flow rate, the flap configuration, and the landing gear position. Particular attention is directed to the generalization to different aircraft types and airport approaches.From the Air Traffic Management point of view, these additional parameters enable a better understanding and awareness of aircraft behaviors. These estimations can be used to evaluate and enhance the air traffic management system performance in terms of safety and efficiency.

show abstract

Aircraft initial mass estimation using Bayesian inference method

Cited by 44 publications

References 10 publications

Particle filter for aircraft mass estimation and uncertainty modeling

Particle filter for aircraft mass estimation and uncertainty modeling

Estimating aircraft drag polar using open flight surveillance data and a stochastic total energy model

Approach and Landing Aircraft On-Board Parameters Estimation with LSTM Networks

Contact Info

Product

Resources

About