Deep Health Indicator Extraction: A Method based on Auto-encoders and Extreme Learning Machines

Yang Hu, Thomas Palmé, and Olga Fink
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmc_16_055.pdf647.25 KBSeptember 1, 2016 - 2:49am

In this paper, we propose a novel deep learning method for feature extraction in prognostics and health management applications. The proposed method is based on Extreme Learning Machines (ELM) and Auto-Encoders (AE), which have demonstrated very good performance and very short training time compared to other deep learning methods on several applications, including image recognition problems. The proposed approach is applied to vibration condition monitoring data to extract features from normal operation (i.e. fault free conditions) without any additional expert knowledge or prior information on the type of signals and the information content in the datasets. The approach demonstrates a better performance in terms of trendability and monotonicity compared to commonly applied feature extraction methods.

Publication Year: 
2016
Publication Volume: 
7
Publication Control Number: 
055
Page Count: 
7
Submission Keywords: 
feature learning
deep learning
Bearing
Extreme Learning Machines
Stacked Auto-Encoders
Submission Topic Areas: 
Data-driven methods for fault detection, diagnosis, and prognosis
Submitted by: 
  
 
 
 

follow us

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