Estimating non-metallic coating thickness using artificial neural network modeled time-resolved thermography: capacity and constraints

Hongjin Wang; Sheng-Jen Hsieh

doi:10.1117/12.2049903

21 May 2014 Estimating non-metallic coating thickness using artificial neural network modeled time-resolved thermography: capacity and constraints

Hongjin Wang, Sheng-Jen Hsieh

Author Affiliations +

Proceedings Volume 9105, Thermosense: Thermal Infrared Applications XXXVI; 91050K (2014) https://doi.org/10.1117/12.2049903
Event: SPIE Sensing Technology + Applications, 2014, Baltimore, MD, United States

Abstract

Current studies suggest that thermography-based measurements may provide a feasible solution for measuring the thickness of non-metallic coatings. The focus of this research was to build an artificial neural network model to predict coating thickness using active thermography and thickness samples that have not previously been seen by the model. Best results (7.5% error) were achieved when using an ANN model with the derivative of a temperature increment’s real part Laplace transform over the real axis as the input, the gradient descent with momentum back-propagation training algorithm, and 20 hidden nodes.

Citation Download Citation

Hongjin Wang and Sheng-Jen Hsieh "Estimating non-metallic coating thickness using artificial neural network modeled time-resolved thermography: capacity and constraints", Proc. SPIE 9105, Thermosense: Thermal Infrared Applications XXXVI, 91050K (21 May 2014); https://doi.org/10.1117/12.2049903

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available