Rolling Bearing Fault Feature Extraction Based on Bacteria Foraging Optimization
- 107 Downloads
Resonance demodulation technology has been widely applied in the fault diagnosis of rolling bearings because of the high sensitivity, the high reliability, and the effective identification of early damage. Its process includes collecting vibration signals, filtering, envelope demodulation analysis, and judge fault condition, while filtering as the key link directly affects the accuracy and efficiency of fault diagnosis based on resonance demodulation technology. So, there is an important problem in the resonance demodulation technology, which is how to select the optimal filter band rapidly to ensure the least amount of noise in the filter signal. To solve this problem, this paper applies bacteria foraging optimization algorithm (BFO) in the selection of the optimal filtering band. The kurtosis is used as evaluation function to judge the quality of the filter signals. Through the loop operation of three operators (migration, breeding, and chemotaxis), the algorithm converges to the global optimal solution quickly. In the last part of the paper, the feasibility and effectiveness of the application of BFO are tested by simulation signals and practical signals, and the relative merits of the application are concluded.
KeywordsRolling bearing Fault diagnosis Resonance demodulation technology Bacteria foraging optimization algorithm
The work described in this paper was supported by a grant from the Naval University of Engineering researching fund (No. 425517k144).
- 1.L.I. Guo-hua, The mechanical fault diagnosis (Chemical Industry Press, Beijing, 2002)Google Scholar