Remaining useful life estimation using long short-term memory deep learning

Che Sheng Hsu, Jehn Ruey Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

79 Scopus citations

Abstract

This paper proposes a deep learning method to estimate the remaining useful life (RUL) of aero-propulsion engines. The proposed method is based on the long short-term memory (LSTM) structure of the recurrent neural network (RNN). LSTM can effectively extract the relationship between data items that are far separated in the time series. The proposed method is applied to the NASA C-MAPSS data set for RUL estimation accuracy evaluation and is compared with the methods using the multi-layer perceptron (MLP), support vector regression (SVR), relevance vector regression (RVR) and convolutional neural network (CNN). Comparisons show that the proposed method is better than others in terms of the root mean squared error (RMSE) and the value of a scoring function.

Original languageEnglish
Title of host publicationProceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018
EditorsArtde Donald Kin-Tak Lam, Stephen D. Prior, Teen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages58-61
Number of pages4
ISBN (Electronic)9781538643426
DOIs
StatePublished - 22 Jun 2018
Event4th IEEE International Conference on Applied System Innovation, ICASI 2018 - Chiba, Japan
Duration: 13 Apr 201817 Apr 2018

Publication series

NameProceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018

Conference

Conference4th IEEE International Conference on Applied System Innovation, ICASI 2018
Country/TerritoryJapan
CityChiba
Period13/04/1817/04/18

Keywords

  • deep learning
  • long short-term memory
  • recurrent neural network
  • remaining useful life

Fingerprint

Dive into the research topics of 'Remaining useful life estimation using long short-term memory deep learning'. Together they form a unique fingerprint.

Cite this