Motor Bearing Failure Identification Using Multiple Long Short-Term Memory Training Strategies

Authors

DOI:

https://doi.org/10.54327/set2024/v4.i2.155

Keywords:

Maintenance, Bearing, Fault, Deep Learning, Diagnosis, LSTM

Abstract

In the context of condition-based maintenance of rotating machines in manufacturing systems, the early diagnosis of possible faults related to rolling elements of the bearing is mainly based on techniques from artificial intelligence, namely, Machine Learning (ML) and Deep Learning (DL). Approaches based on using Deep Learning methods have been the most coveted in recent years. Among a variety of models, the type of architecture known as Long-Short-Term Memory (LSTM) of Recurrent Neural Network (RNN) has both the ability to capture long-term dependencies and to adapt to sequential data modeling. It is therefore able to work on data without any preprocessing. This paper studies using four types of LSTM networks to diagnose bearing faults in a classification approach. It aims to intervene on both the input parameters and the network architecture, to achieve high performance. The proposed method is carried out in two different ways. In the first case, the data inputs are raw frames of vibration signals. However, in the second case, the network inputs are pre-computed time-frequency features. The results clearly showed that LSTMs are more accurate with the latter.

Downloads

Download data is not yet available.

Author Biographies

  • Youcef Atmani, National High School of Advanced Technologies - ENSTA, LTI Laboratory, Dergana, Algiers, Algeria

    Doctor, teaching researcher in the department of mechanical engineering and production, at the National Higher School of Advanced Technologies in Algiers. My areas of expertise are mechanical design, structural dynamics, maintenance and artificial intelligence methods.

  • Ammar Mesloub, Polytechnic Military School -EMP, Bordj El Bahri, Algiers, Algeria

    Doctor-teacher-researcher in the department of electrical engineering at the Polytechnic Military School of Algiers. The areas of intervention are image and speech processing, telecommunications and digital techniques.

  • Said Rechak, National Polytechnic School -ENP, El Harrach, Algiers, Algeria

    Professor-teacher-researcher in the department of mechanical engineering and development at the National Polytechnic School of Algiers. The areas of intervention are structural mechanics, materials mechanics, maintenance and composite materials.

Downloads

Published

11.10.2024

Data Availability Statement

The datasets generated and/or analysed during the current study are available in the CWRU repository [34], https://engineering.case.edu/bearingdatacenter/welcome. Any other information about the findings of this study is available from the corresponding author, M. ATMANI (Youcef.atmani@ensta.edu.dz), upon request.

How to Cite

[1]
Y. Atmani, A. Mesloub, and S. Rechak, “Motor Bearing Failure Identification Using Multiple Long Short-Term Memory Training Strategies”, Sci. Eng. Technol., vol. 4, no. 2, pp. 24–38, Oct. 2024, doi: 10.54327/set2024/v4.i2.155.

Similar Articles

1-10 of 16

You may also start an advanced similarity search for this article.