| Autor: |
Lokesha, M., Kumar, Sujesh, M. V., Kiran Kumar |
| Předmět: |
|
| Zdroj: |
Academic Journal of Manufacturing Engineering; 2021, Vol. 19 Issue 2, p61-68, 8p |
| Abstrakt: |
Recently, Machine Learning concepts are progressively applied for the fault diagnosis and classification in rotating machinery's condition monitoring. Vibration based condition monitoring provide useful and reliable information, hence, it is well accepted in condition monitoring of machines. The realistic vibration signals in time domain are collected from the gear fault simulator in healthy and induced faulty condition of gears in stages. The collected vibration signals are filtered to remove the noise and to support for the enhancement required features. The filtered signals are processed using wavelet enveloped power spectrum to detect the fault in the gears. This paper presents the strategy to use machine learning methods for the classification and diagnosis of gears fault. The time features extracted from wavelet transform are used as input to train the KNN and SVM classifiers. The results demonstrate that the proposed method can reliably separate the fault condition of gears. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
