KRLS based EKF method for Commercial Aero-engine Onboard Adaptive Model and Health parameters Estimation

DOI

10.2991/aeecs-18.2018.55How to use a DOI?

Keywords

Aero-engine; Health Parameters; Kalman Filter; Kernel Recursive Least Squares

Abstract

Due to the fact that computational cost of aircraft engine component level model (CLM) is heavy while memory of engine monitoring unit (EMU) is limited, a machine learning algorithm: exponential weighted - sliding window - kernel recursive least squares (EW-SW-KRLS) algorithm is proposed to replace CLM for onboard application. The exponential weight character guarantees its tracking ability and the sliding window structure fixs its onboard memory budget so the KRLS based EKF method can be applied to track engine output measurements and estimate variations of engine components efficiencies and mass flow capacities which are referred to as health parameters. Several kinds of performance degradations of a commercial aircraft turbofan engine have been numerically simulated and both the combined method and the traditional CLM based EKF method are applied to. The simulation results reveal that the proposed method is close to the CLM based EKF method in term of estimation accuracy with much less computation time and capable of onboard using.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jiahui Gu
AU  - Jinquan Huang
AU  - Feng Lu
PY  - 2018/03
DA  - 2018/03
TI  - KRLS based EKF method for Commercial Aero-engine Onboard Adaptive Model and Health parameters Estimation
BT  - Proceedings of the 2018 2nd International Conference on Advances in Energy, Environment and Chemical Science (AEECS 2018)
PB  - Atlantis Press
SP  - 329
EP  - 334
SN  - 2352-5401
UR  - https://doi.org/10.2991/aeecs-18.2018.55
DO  - 10.2991/aeecs-18.2018.55
ID  - Gu2018/03
ER  -