Fault classification in gearboxes using neural networks
Conference
·
OSTI ID:382799
- Brunel Univ., Uxbridge (United Kingdom)
- Univ. of Hertfordshire, Hatfield (United Kingdom)
The purpose of condition monitoring, and fault diagnostics are to detect faults occurring in machinery, in order to reduce operational and maintenance costs, and provide a significant improvement in plant economy. The condition of a model drive-line was investigated. This model drive-line consists of various interconnected rotating parts, including a gearbox, two bearing blocks, and an electric motor, all connected via flexible coupling and loaded by a disc brake. The drive-line was run in its normal condition, and then single and multiple faults were intentionally introduced to the gearbox, and bearing block. The faults investigated on the drive-line were typical bearing and gear faults, which may develop during normal and continuous operation of this kind of machinery. This paper presents the investigation carried out in order to study both bearing and gear faults introduced together to the drive-line. It is shown that, by using multilayer artificial neural networks on the condition monitoring data, single and multiple faults were successfully classified. The real time domain signals obtained from the drive-line were pre-processed by Wavelet transforms for the network to perform fault classification.
- OSTI ID:
- 382799
- Report Number(s):
- CONF-960154--; ISBN 0-9648731-8-4
- Country of Publication:
- United States
- Language:
- English
Similar Records
Neural network based fault detection using different signal processing techniques as pre-processor
Bearing Fault Detection on Wind Turbine Gearbox Vibrations Using Generalized Likelihood Ratio-Based Indicators: Preprint
Analysis of the vibratory excitation of gear systems for fault detection in rotating machinery
Book
·
Fri Sep 01 00:00:00 EDT 1995
·
OSTI ID:94404
Bearing Fault Detection on Wind Turbine Gearbox Vibrations Using Generalized Likelihood Ratio-Based Indicators: Preprint
Conference
·
Tue Aug 30 20:00:00 EDT 2022
·
OSTI ID:1885698
Analysis of the vibratory excitation of gear systems for fault detection in rotating machinery
Conference
·
Tue Jul 01 00:00:00 EDT 1997
·
OSTI ID:485115