Data-driven Prognostics with Predictive Uncertainty Estimation using Ensemble of Deep Ordinal Regression Models

Vishnu TV, Diksha, Pankaj Malhotra, Lovekesh Vig, and Gautam Shroff
Publication Target: 
IJPHM
Publication Issue: 
Special Issue on Deep Learning and Emerging Analytics
Submission Type: 
Full Paper
AttachmentSizeTimestamp
ijphm_19_027.pdf1.87 MBDecember 29, 2019 - 9:03pm

Prognostics or Remaining Useful Life (RUL) Estimation from multi-sensor time series data is useful to enable condition-based maintenance and ensure high operational availability of equipment. We propose a novel deep learning based approach for Prognostics with Uncertainty Quantification that is useful in scenarios where: (i) access to labeled failure data is scarce due to rarity of failures (ii) inherent noise is present in the sensor readings. The two scenarios mentioned are unavoidable sources of uncertainty in the RUL estimation process, often resulting in unreliable RUL estimates. To address (i), we formulate RUL estimation as an Ordinal Regression (OR) problem and propose LSTM-OR: deep Long Short Term Memory (LSTM) network-based approach to learn the OR function. We show that LSTM-OR naturally allows for the incorporation of censored operational instances in training along with the failed instances, leading to more robust
learning. To address (ii), we propose a simple yet effective approach to quantify predictive uncertainty in the RUL estimation models by training an ensemble of LSTM-OR models. Through empirical evaluation on the publicly available turbofan engine benchmark datasets, we demonstrate that LSTM-OR is at par with commonly used deep metric regression-based approaches for RUL estimation when sufficient failed instances are available for training. Importantly, LSTM-OR outperforms these metric regression-based approaches in the practical scenario where failed training instances are scarce, but sufficient operational (censored) instances are additionally available. Furthermore, our uncertainty quantification
approach yields high-quality predictive uncertainty estimates while also leading to improved RUL estimates compared to single best LSTM-OR models.

Publication Year: 
2019
Publication Volume: 
10
Publication Control Number: 
027
Page Count: 
16
Submission Keywords: 
Remaining Useful Life Estimation
uncertainty estimation
deep learning
recurrent neural networks
Ordinal Regression
censored data
Submission Topic Areas: 
Data-driven methods for fault detection, diagnosis, and prognosis
Uncertainty Quantification and Management in PHM
Submitted by: 
  
 
 
 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed