Non-destructive determination of the remaining life of coatings of gas turbine parts is highly desirable. The present paper describes early attempts to prove the feasibility of doing this based on the optical measurement of the stress in the oxide that attaches the coating to the metal component. Both standard regression methods and neural network methods are compared and it was found that the neural network approach was superior for the case where multiple signal features were present. All methods provide useful predictions for the idealized case considered
Published in:
AUTOTESTCON Proceedings, 2001. IEEE Systems Readiness Technology Conference
Date of Conference: 2001