This research investigates a novel data driven approach to condition monitoring of Electro-Mechanical Actuators (EMAs) consisting of feature extraction and fault classification. Since many common faults in rotating machinery produce unique frequency components, the approach is based on signal analysis in the frequency domain of both inherent EMA signals and accelerometers. The feature extraction process exposes fault frequencies in signal data that are synchronous with motor position through a series of signal processing techniques consisting of digital re-sampling, Power Spectral Density (PSD) computation, and feature reduction. The resulting reduced dimension feature is then used to determine the condition of the EMA with a trained Bayesian Classifier. Signal data collected from EMAs in known health configurations is used to train the algorithms so that the condition of EMA’s with unknown health may be predicted. Laboratory results show that EMA condition can be determined over multiple non-steady operating conditions and is capable of isolating multiple faults that produce unique fault signatures.

Library of Congress Subject Headings

Actuators--Data processing; Flight control; Mechatronics

Publication Date


Document Type


Student Type


Degree Name

Mechanical Engineering (MS)

Department, Program, or Center

Mechanical Engineering (KGCOE)


Jason Kolodziej

Advisor/Committee Member

Mark Kempski

Advisor/Committee Member

Ferat Sahin


Physical copy available from RIT's Wallace Library at TJ223.A25 C45 2012


RIT – Main Campus