Neural network based material identification and part thickness estimation from two radiographic images

Authors:
Ibrahim N. Tansel;Reen Nripjeet Singh;Peng Chen;Claudia V. Kropas-Hughes
Affiliations:
Mechanical Engineering Department, Florida International University, Miami, FL;Mechanical Engineering Department, Florida International University, Miami, FL;Mechanical Engineering Department, Florida International University, Miami, FL;Air Force Research Laboratory, MLLP, Wright-Patterson AFB, Ohio
Venue:
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Year:
2003

Citing 3
Cited 0

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
A comparison between neural networks and decision trees based on data from industrial radiographic testing

Pattern Recognition Letters - Special issue on machine learning and data mining in pattern recognition
Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM

Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM

Quantified Score

Hi-index	0.00

Visualization

Abstract

Radiographic inspection provides extensive information about the characteristics and conditions of parts even if they are hidden behind the walls. A dual energy method is originally proposed to estimate the thickness of parts from two radiographic images by using analytical expressions. Use of neural networks is proposed when the material properties have nonlinear characteristics. Aluminum and brass test pieces were identified and their thickness was estimated from two images obtained at different energy levels.