Intelligent Diagnosis Algorithm for Bearing Faults Based on Artificial Intelligence Deep Learning

Authors

  • Zhaoyang Han College of Engineering, Caofeidian College of Technology, Tangshan 063200, Hebei, China
  • Chenglong Zong College of Engineering, Caofeidian College of Technology, Tangshan 063200, Hebei, China

Abstract

The performance and dependability of mechanical equipment have always been greatly impacted by bearing failure, which has long been a regular issue. The manual monitoring and analysis that is often required by the traditional Bearing Fault Diagnosis (abbreviated as BFD for convenience) procedures is inefficient and prone to error. In order to address this issue, this study examines the BFD method based onArtificial Intelligence (AI) Deep Learning (DL) and create a BFD model that maximizes BFD efficiency and accuracy by utilizing CNN-ETR (Convolutional Neural Networks-Extreme Randomized Trees Regression) under DL technology. The research results indicated that under the same other conditions, for three different types of faults, the diagnostic time of the experimental group was below 2.5 seconds, while the diagnostic time of the control group was between 2.5 seconds and 5 seconds. The diagnostic time of the experimental group was significantly lower than that of the control group, indicating a positive relationship between DL and the efficiency of the BFD algorithm.

Keywords: intelligent diagnosis algorithm for bearing faults; deep learning; artificial intelligence; diagnosis time; energy consumption

Cite As

Z. Han, C. Zong, "Intelligent Diagnosis Algorithm for Bearing Faults Based on Artificial Intelligence Deep Learning",
Engineering Intelligent Systems, vol. 33 no. 5, pp. 581-589, 2025.


Downloads

Published

2025-09-01

Issue

Vol. 33 No. 5 (2025): International Journal of Engineering Intelligent Systems

Section

Article

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.