ESN-based Combination Method for Turbine Condition Prediction

DOI

10.2991/acaai-18.2018.5How to use a DOI?

Keywords

Turbine; health prediction; echo state network (ESN); wavelet analysis; principal components analysis (PCA)

Abstract

As a nonlinear time series prediction method, echo state network (ESN) attracts more attention because of its good approximation capability for the nonlinear system. Aiming at the characters of nonlinear time series in the Turbine's condition prediction analysis, such as including noise and presenting chaos, etc. a combination method based on ESN was proposed. Firstly, the noise contained in nonlinear time series was reduced by the wavelet analysis. Then the training sample data were yielded via phase space reconstruction of the time series. After reducing the dimension of the training sample data by principal component analysis, all principal data were sent into the ESN prediction model. An actually dynamic pressure time series of aircraft power were conducted. The experiments compare the proposed method with traditional ESN prediction model on prediction accuracy and time cost. The results show that the proposed method can both effectively improve the prediction accuracy and efficiency, and it is an effective nonlinear time series prediction method in practice.

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  - Yanyan Liu
AU  - Yangming Guo
AU  - Aihua Wang
PY  - 2018/03
DA  - 2018/03
TI  - ESN-based Combination Method for Turbine Condition Prediction
BT  - Proceedings of the 2018 International Conference on Advanced Control, Automation and Artificial Intelligence (ACAAI 2018)
PB  - Atlantis Press
SP  - 17
EP  - 22
SN  - 1951-6851
UR  - https://doi.org/10.2991/acaai-18.2018.5
DO  - 10.2991/acaai-18.2018.5
ID  - Liu2018/03
ER  -