Application of Vector Time Series Modeling and T-squared Control Chart to Detect Early Gearbox Deterioration
Volume 10, Number 1, January 2014 - Paper 11 - pp. 105-114
CHEN LIN and VILIAM MAKISDepartment of Mechanical and Industrial Engineering, University of Toronto, 5 King’s College Road, Toronto, ON M5S 3G8, CANADA
(Received on January 27, 2013, revised on August 13, 2013)
Condition monitoring vibration data is widely used to assess the health condition of the gearbox. The objective of this paper is to develop a scheme for early fault detection of a gearbox under varying load condition by considering multi-sensor vibration data. Time synchronous averaging (TSA) method is used to reduce the noise and then remove the periodic signals from the data. Several vector auto-regressive (VAR) models are fitted to the historical data obtained in healthy gearbox condition considering different load levels. After testing the independence and multivariate normality of residual data, a multivariate Hotelling’s T-squared control chart is applied to detect the early fault occurrence of a gearbox.
Click here to download the paper.
Please note : You will need Adobe Acrobat viewer to view the full articles.