Intelligent condition monitoring method for bearing faults from highly compressed measurements using sparse over-complete features

•Uses compressive sensing and sparse over-complete feature learning.•Uses the unsupervised sparse autoencoder for learning feature representations.•Achieved high classification accuracy even from highly compressed measurements.•Our method needs significantly less computation time compared to other m...

Full description

Saved in:
Bibliographic Details
Published in:Mechanical systems and signal processing 2018-01, Vol.99, p.459-477
Main Authors: Ahmed, H.O.A., Wong, M.L.D., Nandi, A.K.
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Back propagation
Bearing
Bearing fault classification
Bearings
Classification
Compressed sensing
Condition monitoring
Deep neural network
Fault detection
Faults
Machine condition monitoring
Machine learning
Machinery and equipment
Machinery condition monitoring
Neural networks
Representations
Rotating machinery
Rotating machines
Sparse autoencoder
Sparse over-complete representations
Studies
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Uses compressive sensing and sparse over-complete feature learning.•Uses the unsupervised sparse autoencoder for learning feature representations.•Achieved high classification accuracy even from highly compressed measurements.•Our method needs significantly less computation time compared to other methods.•Our method improves the classification accuracy in machine fault diagnosis. Condition classification of rolling element bearings in rotating machines is important to prevent the breakdown of industrial machinery. A considerable amount of literature has been published on bearing faults classification. These studies aim to determine automatically the current status of a roller element bearing. Of these studies, methods based on compressed sensing (CS) have received some attention recently due to their ability to allow one to sample below the Nyquist sampling rate. This technology has many possible uses in machine condition monitoring and has been investigated as a possible approach for fault detection and classification in the compressed domain, i.e., without reconstructing the original signal. However, previous CS based methods have been found to be too weak for highly compressed data. The present paper explores computationally, for the first time, the effects of sparse autoencoder based over-complete sparse representations on the classification performance of highly compressed measurements of bearing vibration signals. For this study, the CS method was used to produce highly compressed measurements of the original bearing dataset. Then, an effective deep neural network (DNN) with unsupervised feature learning algorithm based on sparse autoencoder is used for learning over-complete sparse representations of these compressed datasets. Finally, the fault classification is achieved using two stages, namely, pre-training classification based on stacked autoencoder and softmax regression layer form the deep net stage (the first stage), and re-training classification based on backpropagation (BP) algorithm forms the fine-tuning stage (the second stage). The experimental results show that the proposed method is able to achieve high levels of accuracy even with extremely compressed measurements compared with the existing techniques.
ISSN:0888-3270
1096-1216
DOI:10.1016/j.ymssp.2017.06.027