Machine Learning and Infrared Thermography for Fiber Orientation Assessment on Randomly-Oriented Strands Parts
Henrique Fernandes,
Hai Zhang,
Alisson Figueiredo,
Fernando Malheiros,
Luis Henrique Ignacio,
Stefano Sfarra,
Clemente Ibarra-Castanedo,
Gilmar Guimaraes,
Xavier Maldague
Affiliations
Henrique Fernandes
School of Computer Science, Federal University of Uberlandia, Uberlandia 38408-100, Brazil
Hai Zhang
Department of Electrical and Computer Engineering, Computer Vision and Systems Laboratory (CVSL), Laval University, Quebec City, QC G1V 0A6, Canada
Alisson Figueiredo
Department of Mechanical Engineering, Laboratory of Teaching and Researching on Heat Transfer, Federal University of Uberlandia, Uberlandia 38408-100, Brazil
Fernando Malheiros
Department of Mechanical Engineering, Laboratory of Teaching and Researching on Heat Transfer, Federal University of Uberlandia, Uberlandia 38408-100, Brazil
Luis Henrique Ignacio
Department of Mechanical Engineering, Laboratory of Teaching and Researching on Heat Transfer, Federal University of Uberlandia, Uberlandia 38408-100, Brazil
Stefano Sfarra
Department of Industrial and Information Engineering and Economics, University of L’Aquila, Roio Poggio, L’Aquila (AQ) 67100, Italy
Clemente Ibarra-Castanedo
Department of Electrical and Computer Engineering, Computer Vision and Systems Laboratory (CVSL), Laval University, Quebec City, QC G1V 0A6, Canada
Gilmar Guimaraes
Department of Mechanical Engineering, Laboratory of Teaching and Researching on Heat Transfer, Federal University of Uberlandia, Uberlandia 38408-100, Brazil
Xavier Maldague
Department of Electrical and Computer Engineering, Computer Vision and Systems Laboratory (CVSL), Laval University, Quebec City, QC G1V 0A6, Canada
The use of fiber reinforced materials such as randomly-oriented strands has grown in recent years, especially for manufacturing of aerospace composite structures. This growth is mainly due to their advantageous properties: they are lighter and more resistant to corrosion when compared to metals and are more easily shaped than continuous fiber composites. The resistance and stiffness of these materials are directly related to their fiber orientation. Thus, efficient approaches to assess their fiber orientation are in demand. In this paper, a non-destructive evaluation method is applied to assess the fiber orientation on laminates reinforced with randomly-oriented strands. More specifically, a method called pulsed thermal ellipsometry combined with an artificial neural network, a machine learning technique, is used in order to estimate the fiber orientation on the surface of inspected parts. Results showed that the method can be potentially used to inspect large areas with good accuracy and speed.
