Life prediction model for turbofan engines based on XGBoost

Junwei Diao; Shubo Jiang; Xianbin Zhao; Kunzhang Wang

doi:10.1117/12.3030155

5 June 2024 Life prediction model for turbofan engines based on XGBoost

Junwei Diao, Shubo Jiang, Xianbin Zhao, Kunzhang Wang

Proceedings Volume 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024); 131632P (2024) https://doi.org/10.1117/12.3030155
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 2024, Xi'an, China

Abstract

Aiming at the problem that a single model will be insufficient for predicting the remaining life of the equipment, a life prediction model with multi-model integration for turbofan engine is designed. Firstly, the turbofan engine dataset is discretized by the clustering algorithm, and the unbalanced sample data are oversampled; then the dataset is split according to the discretization results; the feature set is filtered by the information gain method; then the XGBoost algorithm is used to establish the Regression-Classification-Regression (R-C-R) life prediction model; finally, the predicted value of life span was derived by the integration method. The results show that the model designed in this paper is much better than the single XGBoost algorithm model, in which the root mean square error (RMSE) is reduced by 26% and the accuracy is improved by 31.2%.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Junwei Diao, Shubo Jiang, Xianbin Zhao, and Kunzhang Wang "Life prediction model for turbofan engines based on XGBoost", Proc. SPIE 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 131632P (5 June 2024); https://doi.org/10.1117/12.3030155

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available