NN-Based Damage Detection in Multilayer Composites

The discrete-time system of multilayer composite plate is modeled using neural network (NN) to produce a nonlinear exogenous autoregressive moving-average model (NARMAX). The model is implemented by training a NN with input-output experimental data. Each damaged sample can be modeled by a parameter governed by the propagation behaviors of the NN. A residual signal is evaluated from the difference between the output of the model and that of the real system. A threshold function is used to detect the damaged behavior of the system. The results show that a three-layer neural network can be a general type of and suitable for the nonlinear input-output mapping problems of multilayer composite system.

[1]  Rolf Isermann.  Process Fault Diagnosis with Parameter Estimation Methods , 1985 .

[2]  Hong Wang,et al.  An approach to fault detection using nonlinear modelling and estimation , 1993 .

[3]  Jie Zhang,et al.  On-line process fault diagnosis using neural network techniques , 1992 .

[4]  David Rees,et al.  Frequency-domain identification of gas turbine dynamics , 1998, IEEE Trans. Control. Syst. Technol..

[5]  George Z. Voyiadjis,et al.  Damage in composite materials , 1993 .

[6]  Ron J. Patton,et al.  Robust Model-Based Fault Diagnosis: The State of the ART , 1994 .

[7]  Y. Ousset,et al.  Numerical analysis of delamination in multilayered composite plates , 1997 .

[8]  S. Billings,et al.  A prediction-error and stepwise-regression estimation algorithm for non-linear systems , 1986 .

[9]  S. Tsai,et al.  Introduction to composite materials , 1980 .

[10]  Paul M. Frank,et al.  Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results , 1990, Autom..

[11]  D. Roylance.  INTRODUCTION TO COMPOSITE MATERIALS , 2000 .

[12]  I. J. Leontaritis,et al.  Input-output parametric models for non-linear systems Part II: stochastic non-linear systems , 1985 .

[13]  S. Billings,et al.  Correlation based model validity tests for non-linear models , 1986 .

[14]  S. A. Billings,et al.  Spectral analysis for non-linear systems, Part I: Parametric non-linear spectral analysis , 1989 .

[15]  R. Gadelrab,et al.  THE EFFECT OF DELAMINATION ON THE NATURAL FREQUENCIES OF A LAMINATED COMPOSITE BEAM , 1996 .

[16]  P. Boggs,et al.  A Stable and Efficient Algorithm for Nonlinear Orthogonal Distance Regression , 1987 .

[17]  Rolf Isermann.  PROCESS FAULT DIAGNOSIS WITH PARAMETER ESTIMATION METHODS , 1986 .