Skip to main content
padlock icon - secure page this page is secure

Automatic classification of heat-treated bearing rings based on the swept frequency eddy current technique

Buy Article:

$22.00 + tax (Refund Policy)

Hardness is one of the critical indexes for the quality control of bearing rings. This paper presents an eddy current-based method to identify bearing rings after heat treatment with respect to hardness as qualified, unqualified and non-heat treated via a support vector machine (SVM). After assigning a swept frequency range, eddy current impedance signals were recorded. Then, the recorded impedance signals from one of the qualified rings were adopted as the reference signals and the difference signals were derived for the other bearing rings. The results show that the eddy current technique is basically able to classify the prepared heat-treated bearing rings in terms of hardness and the classification accuracy largely depends on the excitation frequency. However, the accuracy from single point testing is not satisfactory due to the non-uniformity of heat treatment. In response to this, the signals from multiple points were averaged. As a result, there are good margins between the averaged features from three types of the prepared bearing rings, which indicates a lower probability of misclassification. Therefore, the prepared bearing rings are accurately and reliably recognised in the frequency range from 800 Hz to 4 kHz.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
No Metrics

Keywords: BEARING RING; CLASSIFICATION; HARDNESS; SUPPORT VECTOR MACHINE; SWEPT FREQUENCY EDDY CURRENT

Document Type: Research Article

Publication date: July 1, 2019

More about this publication?
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more