Estimating non-metallic coating thickness using artificial neural network modeled time-resolved thermography: capacity and constraints
Conference Paper
Overview
Research
Identity
Additional Document Info
Other
View All
Overview
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. 2014 Copyright SPIE.