Stacked Convolutional Bidirectional LSTM Recurrent Neural Network for Bearing Anomaly Detection in Rotating Machinery Diagnostics

Kwangsuk Lee, Jae Kyeong Kim, Jaehyong Kim, Kyeon Hur, Hagbae Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper proposes a multi-layered anomaly detection scheme to train feature extraction and to test anomaly prediction by using Convolutional Neural Networks (CNNs) layer, Bidirectional and Unidirectional Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs), which is one of a novel deep architecture named stacked convolutional bidirectional LSTM network (SCB-LSTM). In the proposed model, the stacked CNNs perform feature extraction of vibration sensor signal patterns, and the result is used to feature learning with the stacked bidirectional LSTMs (SB-LSTMs). After this procedure, the stacked unidirectional LSTMs (SU-LSTMs) enhance the feature learning, and a regression layer finally predicts anomaly detections. The experimental results of bearing data not only show the accuracy of the proposed model in anomaly detection for rotating machinery diagnostics, but also suggest the better performance than other state-of-the-art algorithms such as a plain uni-LSTM or Bi-LSTM.

Original languageEnglish
Title of host publication1st IEEE International Conference on Knowledge Innovation and Invention, ICKII 2018
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages98-101
Number of pages4
ISBN (Electronic)9781538652671
DOIs
Publication statusPublished - 2018 Dec 7
Event1st IEEE International Conference on Knowledge Innovation and Invention, ICKII 2018 - Jeju Island, Korea, Republic of
Duration: 2018 Jul 232018 Jul 27

Publication series

Name1st IEEE International Conference on Knowledge Innovation and Invention, ICKII 2018

Other

Other1st IEEE International Conference on Knowledge Innovation and Invention, ICKII 2018
CountryKorea, Republic of
CityJeju Island
Period18/7/2318/7/27

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems and Management
  • Media Technology

Fingerprint Dive into the research topics of 'Stacked Convolutional Bidirectional LSTM Recurrent Neural Network for Bearing Anomaly Detection in Rotating Machinery Diagnostics'. Together they form a unique fingerprint.

Cite this