An Improved Particle Filter Method for Accurate Remaining Useful Life Prediction

Dengshan Huang, Meinan Wang, Shuai Zhao, Pengfei Wen, Shaowei Chen, Zhi Dou

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Abstract

The prognostics method that updates the parameters of degradation model using particle filter to predict the remaining useful life (RUL) of equipment is widely used in recent years. However, most of the traditional methods that use this strategy for prognostics do not establish the state transition equation and measurement equation of particle filter from the aspect of degradation trend, which makes the predicted curve may not conform to the degradation trend of the known data because of the loss of information. This paper proposes a prognostics method based on degeneration trajectory, which updates model parameters using particle filter and makes the predicted curve which depends on the updated parameters conform to the known degradation trend by establishing the measurement equation of particle filter different from the traditional method. The proposed method is verified by using the turbine engine degradation data published by NASA and the experiment shows that this method is superior to the traditional method in prediction accuracy and precision.
OriginalsprogEngelsk
Titel2019 IEEE International Conference on Prognostics and Health Management (ICPHM)
Antal sider8
ForlagIEEE
Publikationsdatojun. 2019
Artikelnummer8819414
ISBN (Trykt)978-1-5386-8358-3
DOI
StatusUdgivet - jun. 2019
Begivenhed2019 IEEE International Conference on Prognostics and Health Management (ICPHM) - San Francisco, CA, USA
Varighed: 17 jun. 201920 jun. 2019

Konference

Konference2019 IEEE International Conference on Prognostics and Health Management (ICPHM)
LokationSan Francisco, CA, USA
Periode17/06/201920/06/2019

Fingeraftryk

Dyk ned i forskningsemnerne om 'An Improved Particle Filter Method for Accurate Remaining Useful Life Prediction'. Sammen danner de et unikt fingeraftryk.

Citationsformater