Fault Diagnosis of Motor Bearing Using Ensemble Learning Algorithm with FFT-based Preprocessing

Niloy Sikder, Kangkan Bhakta, Abdullah Al Nahid, M M Manjurul Islam

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

27 Citations (Scopus)


Rolling bearings are one of the pivotal mechanical elements in rotating machines like the electric motor. However, they are liable for the majority of the faults encountered by rotating machines. Detection or estimation of these faults at an early stage can help to eliminate them and prevent the machine from malfunctioning or failing during operation. The recent developments in the field of Machine Learning (ML) have brought a radical change in the way we interpret and analyze these faults, and certain learning techniques have enabled us to predict motor bearing faults almost impeccably. This paper proposes a method to diagnose bearing fault signals that employ an ensemble learning method named Random Forest (RF). The procedure associated with this method requires simple preprocessing using Fast Fourier Transform (FFT) that explore bearing vibration signal to reveal intrinsic features about fault which are used with RF for classifying fault types. The potency of the proposed method is demonstrated using the practical motor vibration data obtained from the Case Western Reserve University (CWRU) Lab. This supervised learning algorithm is able to classify and predict various types of bearing faults with almost 99% accuracy.
Original languageEnglish
Title of host publication2019 International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST)
ISBN (Electronic)978-1-5386-8014-8, 978-1-5386-8013-1
ISBN (Print)978-1-5386-8012-4, 978-1-5386-8015-5
Publication statusPublished (in print/issue) - 21 Feb 2019


  • bearing fault
  • ensemble learning
  • fault diagnosis
  • FFT
  • feature extraction
  • Machine Learning


Dive into the research topics of 'Fault Diagnosis of Motor Bearing Using Ensemble Learning Algorithm with FFT-based Preprocessing'. Together they form a unique fingerprint.

Cite this