The objective of this study is to investigate and develop an Artificial Neural Network approach based on vibration signals for the detection of wear, damage, and malfunction of an experimental gearbox. Three artificial defeets were introduced to the gearbox and these are; (1) tooth face wear, (2) full tooth breakage (missing tooth), (3) clearance or backlash. The signals, collected from extensive experimentation, are analyzed using time and frequency domain descriptors. The vibration fault symptoms were then used in developing a neural network-based estimator, for on-lfnemonitoring of the gearbox operational condition. The results were very useful in demonstrating the use of artificial intelligence for machine health monitoring and diagnostics. The proposed technique can be adopted for laboratory experiments to illustrate the monitoring of other machine malfunctions such as ball bearings, machine tools and hydraulic and pneumatic systems.
|Original language||English (US)|
|Number of pages||6|
|Journal||Computers in Education Journal|
|State||Published - Dec 1 2002|
All Science Journal Classification (ASJC) codes
- Computer Science(all)