Detection of incipient tooth defect in helical gears using multivariate statistics

Multivariate statistical techniques have been successfully used for monitor ing process plants and their associated instrumentation. These techniques e ffectively detect disturbances related to individual measurement sources an d consequently provide diagnostic information about the: process input. Thi s paper investigates and explores the use of multivariate statistical techn iques in a two-stage industrial helical gearbox, to detect localised faults by using vibration signals. The vibration signals, obtained From a number of sensors, are synchronously averaged and then the multivariate statistics , based on principal components analysis, is employed to form a normal (ref erence) condition model. Fault conditions, which are deviations From a refe rence model, are detected by monitoring Q- and T-2-statistics. Normal opera ting regions or confidence bounds, based on kernel density estimation (KDE) is introduced to capture the faulty conditions in the gearbox. It is Found that Q- and T-2-statistics based on PCA can detect incipient local faults at an early stage. The confidence regions, based on KDE can also reveal the growing faults in the gearbox. (C) 2001 Academic Press.