Premium
A probabilistic Bayesian recurrent neural network for remaining useful life prognostics considering epistemic and aleatory uncertainties
Author(s) -
Caceres Jose,
Gonzalez Danilo,
Zhou Taotao,
Droguett Enrique Lopez
Publication year - 2021
Publication title -
structural control and health monitoring
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.587
H-Index - 62
eISSN - 1545-2263
pISSN - 1545-2255
DOI - 10.1002/stc.2811
Subject(s) - prognostics , frequentist inference , uncertainty quantification , artificial intelligence , probabilistic logic , machine learning , computer science , recurrent neural network , artificial neural network , dropout (neural networks) , robustness (evolution) , surrogate model , bayes' theorem , bayesian probability , monte carlo method , bayesian inference , engineering , mathematics , data mining , statistics , biochemistry , chemistry , gene
Summary Deep learning‐based approach has emerged as a promising solution to handle big machinery data from multi‐sensor suites in complex physical assets and predict their remaining useful life (RUL). However, most recent deep learning‐based approaches deliver a single‐point estimate of RUL as these models represent the weights of a neural network as a deterministic value and hence cannot convey uncertainty in the RUL prediction. This practice usually provides overly confident predictions that might cause severe consequences in safety‐critical industries. To address this issue, this paper proposes a probabilistic Bayesian recurrent neural network (RNN) for RUL prognostics considering epistemic and aleatory uncertainties. The epistemic uncertainty is handled by Bayesian RNN layers as extensions from the Frequentist RNN layers using the Flipout method. The aleatory uncertainty is covered by a probabilistic output that follows a Gaussian distribution parameterized by the two neurons in the output layer. The network is trained using Bayes by backprop with the Flipout method. The proposed model is demonstrated by the open‐access Commercial Modular Aero‐Propulsion System Simulation (C‐MAPSS) dataset of turbofan engines and a comparative study of the Frequentist RNN counterparts, the Monte Carlo Dropout‐based RNN, and the state‐of‐the‐art models for C‐MAPSS datasets. The results demonstrate the promising performance and robustness of the proposed model in RUL prognostics.