Uncertainty Quantification for Remaining Useful Lifetime Prediction with Multi-Channel Sensory Data

Yingjun Deng; Huaming Wu; Chao Jiang

ICASSP 2020accepted0 citations

Uncertainty Quantification for Remaining Useful Lifetime Prediction with Multi-Channel Sensory Data

Abstract

For remaining useful lifetime (RUL) prediction with multi-channel sensory data, long-term prediction has more uncertainty than short-term prediction. In this paper, the ratio of mean to variance was considered to measure the uncertainty propagation rate (UPR) of RUL prediction over time. Furthermore, we use a recurrent neural network (RNN) as the linking function for the mean of inverse Gaussian distributed RUL to construct a two-stage hybrid model. Later the RNN and the UPR are jointly trained with sensory data and failure records via alternating minimization. Proposed algorithms are validated in a simulation test.

BibTeX

@inproceedings{icassp2020_uncertaintyquant,
  title = {Uncertainty Quantification for Remaining Useful Lifetime Prediction with Multi-Channel Sensory Data},
  author = {Yingjun Deng and Huaming Wu and Chao Jiang},
  booktitle = {ICASSP 2020},
  year = {2020}
}