To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
A GA-based Feature Optimization Technique for Bearing Fault Diagnostics |
|
Author |
Jie Liu, Wilson Wang, Farid Golnaraghi |
| Citation |
Vol. 7 No. 9 pp. 62-68 |
|
Abstract |
Rolling-element bearings are widely used in various mechanical and electrical systems. A reliable online bearing fault diagnostic technique is critically needed in industries to detect the occurrence of a fault so as to prevent system’s performance degradation and malfunction. To improve the fault diagnostic reliability and efficiency, a genetic algorithm based feature optimization technique is proposed in this work. In this scheme, the discrete wavelet packet analysis is utilized to decompose the raw vibration signal into several constituent signatures, from which the bearing health condition related features are formulated. Taking these features as a fundamental search space, the genetic algorithm based technique is adopted to choose the representative features that carry more discriminatory information for bearing health condition assessment. This optimization process is guided by a suggested fitness function. A neural fuzzy system is utilized for diagnostic classification operations. The performance of the proposed technique is evaluated by experimental tests. |
|
Keywords |
Genetic algorithm, Feature optimization, Fault classification, Rolling element bearing |
|
URL |
