Bearing Fault Diagnosis Based on Multi-Scale CNN and Bidirectional GRU

Taher Saghi, Danyal Bustan* (Corresponding Author), Sumeet S. Aphale

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)
7 Downloads (Pure)


Finding a reliable approach to detect bearing faults is crucial, as the most common rotating machine defects occur in its bearings. A convolutional neural network can automatically extract the local features of the mechanical vibration signal and classify the patterns. Nevertheless, these types of networks suffer from the extraction of the global feature of the input signal as they utilize only one scale on their input. This paper presents a method to overcome the above weakness by employing a combination of three parallel convolutional neural networks with different filter lengths. In addition, a bidirectional gated recurrent unit is utilized to extract global features. The CWRU-bearing dataset is used to prove the performance of the proposed method. The results show the high accuracy of the proposed method even in the presence of noise.
Original languageEnglish
Pages (from-to)11-28
Number of pages18
Issue number1
Early online date30 Dec 2022
Publication statusPublished - 2023

Bibliographical note

This research received no external funding.

Data Availability Statement

Data Availability Statement: The data generated and/or analyzed during the current study are available from the corresponding author on reasonable request.


  • bearing fault diagnosis
  • multi-scale
  • convolutional neural network
  • bidirectional GRU


Dive into the research topics of 'Bearing Fault Diagnosis Based on Multi-Scale CNN and Bidirectional GRU'. Together they form a unique fingerprint.

Cite this