Multivariate statistics process control for dimensionality reduction in structural assessment

This paper presents advantages of using techniques like principal component analysis (PCA), partial least square (PLS) and some extensions called multiway PCA (MPCA) and multiway PLS (MPLS) for reducing dimensionality in damage identification problem, in particular, detecting and locating impacts in a part of a commercial aircraft wing flap. It is shown that applying MPCA and MPLS is convenient in systems which many sensors are monitoring the structures, because the reciprocal relation between signals is considered. The methodology used for detecting and locating the impact uses the philosophy of case-based reasoning, where single PCA and PLS are used also for organizing previous knowledge in memory. Sixteen approaches combining those techniques have been performed. Results from all of them are presented, compared and discussed. (c) 2007 Elsevier Ltd. All rights reserved.

[1]  Hoon Sohn,et al.  Structural Health Monitoring Using Statistical Process Control , 2000 .

[2]  Brian F. Feeny,et al.  APPLICATION OF PROPER ORTHOGONAL DECOMPOSITION TO STRUCTURAL VIBRATION ANALYSIS , 2003 .

[3]  Gaëtan Kerschen,et al.  PROPER ORTHOGONAL DECOMPOSITION FOR MODEL UPDATING OF NON-LINEAR MECHANICAL SYSTEMS , 2001 .

[4]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[5]  Keith Worden,et al.  Damage identification using multivariate statistics: Kernel discriminant analysis , 2000 .

[6]  I. Jolliffe.  Principal Component Analysis , 2002 .

[7]  Enric Plaza,et al.  CasedBased Reasoningc an overview , 1997 .

[8]  Brian F. Feeny,et al.  Part 1: Dynamical Characterization of a Frictionally Excited Beam , 2000 .

[9]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[10]  Gaëtan Kerschen,et al.  Structural damage diagnosis under varying environmental conditions—Part I: A linear analysis , 2005 .

[11]  Charles R. Farrar,et al.  A summary review of vibration-based damage identification methods , 1998 .

[12]  W. Staszewski.  WAVELET BASED COMPRESSION AND FEATURE SELECTION FOR VIBRATION ANALYSIS , 1998 .

[13]  Hoon Sohn,et al.  Statistical Damage Classification Under Changing Environmental and Operational Conditions , 2002 .

[14]  Richard D. Braatz,et al.  Data-driven Methods for Fault Detection and Diagnosis in Chemical Processes , 2000 .

[15]  John F. MacGregor,et al.  Multi-way partial least squares in monitoring batch processes , 1995 .

[16]  Wieslaw J. Staszewski,et al.  Monitoring on-line integrated technologies for operational reliability — monitor , 2000 .

[17]  Gaëtan Kerschen,et al.  Structural damage diagnosis under varying environmental conditions - Part II: local PCA for non-linear cases , 2005 .

[18]  Hoon Sohn,et al.  VIBRATION-BASED DAMAGE DETECTION USING STATISTICAL PROCESS CONTROL , 2001 .

[19]  S. Wold,et al.  Multi‐way principal components‐and PLS‐analysis , 1987 .

[20]  J. Morris,et al.  Monitoring process manufacturing performance , 2002 .

[21]  Gürkan Sin,et al.  INFLUENCE OF SCALING AND UNFOLDING IN PCA BASED MONITORING OF NUTRIENT REMOVING BATCH PROCESS , 2006 .

[22]  Josep Vehí,et al.  A hybrid approach of knowledge-based reasoning for structural assessment , 2005 .

[23]  Keith Worden,et al.  Impact Location and Quantification on a Composite Panel using Neural Networks and a Genetic Algorithm , 2000 .

[24]  Keith Worden,et al.  Fail-safe sensor distributions for impact detection in composite materials , 2000 .

[25]  J. Macgregor,et al.  Monitoring batch processes using multiway principal component analysis , 1994 .

[26]  A. Vakakis,et al.  PROPER ORTHOGONAL DECOMPOSITION (POD) OF A CLASS OF VIBROIMPACT OSCILLATIONS , 2001 .

[27]  A. Höskuldsson.  PLS regression methods , 1988 .

[28]  Josep Vehí,et al.  Two Approaches to Structural Damage Identification: Model Updating versus Soft Computing , 2006 .

[29]  Christian Boller,et al.  Health Monitoring of Aerospace Structures , 2003 .

[30]  W. Staszewski,et al.  Impact damage location in composite structures using optimized sensor triangulation procedure , 2003 .

[31]  Barry M. Wise,et al.  A comparison of principal component analysis, multiway principal component analysis, trilinear decomposition and parallel factor analysis for fault detection in a semiconductor etch process , 1999 .

[32]  Lindsay I. Smith,et al.  A tutorial on Principal Components Analysis , 2002 .

[33]  Gaëtan Kerschen,et al.  Sensor validation using principal component analysis , 2005 .

[34]  James S. Sirkis,et al.  Location and magnitude of impact detection in composite plates using neural networks , 1995, Smart Structures.

[35]  Daniel J. Inman,et al.  Sensor Validation for Smart Structures , 1999 .

[36]  Keith Worden,et al.  Impact Damage Detection in Aircraft Composites Using Knowledge-based Reasoning , 2008 .

[37]  Mehmet Imregun,et al.  STRUCTURAL DAMAGE DETECTION USING ARTIFICIAL NEURAL NETWORKS AND MEASURED FRF DATA REDUCED VIA PRINCIPAL COMPONENT PROJECTION , 2001 .

[38]  Jean-Claude Golinval,et al.  Principal Component Analysis of a Piezosensor Array for Damage Localization , 2003 .

[39]  Theodora Kourti,et al.  Comparing alternative approaches for multivariate statistical analysis of batch process data , 1999 .

[40]  Keith Worden,et al.  An automatic impact monitor for a composite panel employing smart sensor technology , 2005 .