An intelligent method using neural networks for Depth detection by standard thermal contrast in active thermography

Abstract

Today the infrared thermography is among the nondestructive testing methods (NDT) most used for detection and characterization of internal defects in materials. It has become a reference method in industrial installations control. As the interpretation of thermal images provided by the infrared cameras is often difficult; therefore, it is necessary; to seek new methods fast and reliable for intelligent nondestructive evaluation. In our work we propose a fast method using artificial neural networks for internal defects depth evaluation from the thermal contrast. Experimental results have confirmed the method efficiency in predicting the defects depths.