Bearing fault diagnosis using multiclass support vector machines with binary particle swarm optimization and regularized Fisher’s criterion

Condition monitoring of rotating machinery has attracted more and more attention in recent years in order to reduce the unnecessary breakdowns of components such as bearings and gears which suffer frequently from failures. Vibration based approaches are the most commonly used techniques to the condi...

Full description

Saved in:
Bibliographic Details
Published in:Journal of intelligent manufacturing 2017-02, Vol.28 (2), p.405-417
Main Authors: Ziani, Ridha, Felkaoui, Ahmed, Zegadi, Rabah
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Bearing
Business and Management
Condition monitoring
Control
Criteria
Discriminant analysis
Failure
Fault diagnosis
Feature selection
Genetic algorithms
Machine learning
Machines
Manufacturing
Manufacturing execution systems
Mechatronics
Neural networks
Optimization
Pattern recognition systems
Performance evaluation
Principal components analysis
Processes
Production
Robotics
Studies
Support vector machines
Swarm intelligence
Teaching methods
Vibration
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Condition monitoring of rotating machinery has attracted more and more attention in recent years in order to reduce the unnecessary breakdowns of components such as bearings and gears which suffer frequently from failures. Vibration based approaches are the most commonly used techniques to the condition monitoring tasks. In this paper, we propose a bearing fault detection scheme based on support vector machine as a classification method and binary particle swarm optimization algorithm (BPSO) based on maximal class separability as a feature selection method. In order to maximize the class separability, regularized Fisher’s criterion is used as a fitness function in the proposed BPSO algorithm. This approach was evaluated using vibration data of bearing in healthy and faulty conditions. The experimental results demonstrate the effectiveness of the proposed method.
ISSN:0956-5515
1572-8145
DOI:10.1007/s10845-014-0987-3