Intelligent system for material quality control using impact-echo testing

This paper introduces an intelligent system to discern the quality of materials inspected by the impact-echo technique. The system includes a hardware setup to inspect parallelepiped-shape materials and a procedure to classify the material depending on its quality condition. Four levels of classification with different grades of knowledge about the material defects are approached: material condition, kind of defect, defect orientation, and defect dimension. The number of classes (material qualities) in the lowest classification level is 12. The procedure is applied on signals coming from 3D finite element simulations and lab experiments with aluminium specimens. The classification procedure is performed using frequency features and the classification algorithms: LDA, MLP, and an algorithm based on mixtures of independent component analyzers. We show the best performance to model the impact-echo data is obtained by the ICA mixture model.

[1]  J. Cardoso,et al.  Blind beamforming for non-gaussian signals , 1993 .

[2]  Nicholas J. Carino,et al.  Transient stress waves interaction with planar flaws , 1988 .

[3]  R. Xu,et al.  Application of principal component analysis to the FTIR spectra of disk lubricant to study lube-carbon interactions , 2004, IEEE Transactions on Magnetics.

[4]  Luis Vergara,et al.  A Blind Source Separation Technique for Extracting Sinusoidal Interferences in Ultrasonic Non-Destructive Testing , 2004, J. VLSI Signal Process..

[5]  Andrzej Cichocki,et al.  Adaptive Blind Signal and Image Processing - Learning Algorithms and Applications , 2002 .

[6]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[7]  Ted von Hippel,et al.  Automated classification of stellar spectra - II. Two-dimensional classification with neural networks and principal components analysis , 1998, astro-ph/9803050.

[8]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[9]  J. Gosálbez,et al.  Blind source separation for classification and detection of flaws in impact-echo testing , 2005 .

[10]  J. Igual,et al.  DATA CLUSTERING METHODS BASED ON MIXTURE OF INDEPENDENT COMPONENT ANALYZERS , 2006 .

[11]  Mary Sansalone,et al.  Impact-echo : nondestructive evaluation of concrete and masonry , 1997 .

[12]  Addisson Salazar,et al.  ICA Model Applied to Multichannel Non-destructive Evaluation by Impact-Echo , 2004, ICA.

[13]  Addisson Salazar,et al.  Neural Networks for Defect Detection in Non-destructive Evaluation by Sonic Signals , 2007, IWANN.

[14]  Nicholas J. Carino,et al.  The Impact-Echo Method: An Overview , 2001 .

[15]  Addisson Salazar,et al.  Two Applications of Independent Component Analysis for Non-destructive Evaluation by Ultrasounds , 2006, ICA.

[16]  Terrence J. Sejnowski,et al.  ICA Mixture Models for Unsupervised Classification of Non-Gaussian Classes and Automatic Context Switching in Blind Signal Separation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  C. F. Morabito,et al.  Independent component analysis and feature extraction techniques for NDT data , 2000 .

[18]  Stephen J. Roberts,et al.  Variational Mixture of Bayesian Independent Component Analyzers , 2003, Neural Computation.