Developing health indicators and RUL prognostics for systems with few failure instances and varying operating conditions using a LSTM autoencoder

Most Remaining Useful Life (RUL) prognostics are obtained using supervised learning models trained with many labelled data samples (i.e., the true RUL is known). In aviation, however, aircraft systems are often preventively replaced before failure. There are thus very few labelled data samples avail...

Full description

Saved in:
Bibliographic Details
Published in:Engineering applications of artificial intelligence Vol. 117; p. 105582
Main Authors: de Pater, Ingeborg, Mitici, Mihaela
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.01.2023
Subjects:
Attention
Autoencoder
Health indicators
Remaining Useful Life prognostics
Unlabelled data samples
Varying operating conditions
Varying operating conditions
Remaining Useful Life prognostics
Autoencoder
Unlabelled data samples
Health indicators
Attention
ISSN:0952-1976, 1873-6769
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most Remaining Useful Life (RUL) prognostics are obtained using supervised learning models trained with many labelled data samples (i.e., the true RUL is known). In aviation, however, aircraft systems are often preventively replaced before failure. There are thus very few labelled data samples available. We therefore propose a Long Short-Term Memory (LSTM) autoencoder with attention to develop health indicators for an aircraft system instead. This autoencoder is trained with unlabelled data samples (i.e., the true RUL is unknown). Since aircraft fly under various operating conditions (varying altitude, speed, etc.), these conditions are also integrated in the autoencoder. We show that the consideration of the operating conditions leads to robust health indicators and improves significantly the monotonicity, trendability and prognosability of these indicators. These health indicators are further used to predict the RUL of the aircraft system using a similarity-based matching approach. We illustrate our approach for turbofan engines. We show that the consideration of the operating conditions improves the monotonicity of the health indicators by 97%. Also, our approach leads to accurate RUL estimates with a Root Mean Square Error (RMSE) of 2.67 flights only. Moreover, a 19% reduction in the RMSE is obtained using our approach in comparison to existing supervised learning models. •Unsupervised learning to create health indicators for systems with few failures.•LSTM autoencoder with attention to create health indicators.•LSTM autoencoder includes the operating conditions of the system.•Approach is applied to the aircraft engines (the new N-CMAPSS).•Accurate RUL prognostics with only one failure instance in the training set.
ISSN:0952-1976
1873-6769
DOI:10.1016/j.engappai.2022.105582