Application of Bayesian-Designed Artificial Neural Networks in Phase II Structural Health Monitoring Benchmark Studies

Abstract This paper presents the results of a study into the use of pattern recognition as a method for detecting damage in structures. Pattern recognition is achieved by the use of artificial neural networks (ANNs), however, these require careful design because the number of hidden layers and the number of neurons in each hidden layer are critical to the ANN’s performance. In the current study, a Bayesian model class selection method was employed to select an optimal ANN model class that avoids ad hoc assumptions and subjective decisions in the ANN design. The objective of the research was to provide an extended study of the proposed method using the IASC-ASCE Structural Health Monitoring Phase II Simulated Benchmark Structure. Damage-induced modal parameter changes were used as a pattern feature in damage detection. Analysis showed that the proposed method is able to successfully identify damages in the benchmark structure.

[1]  Hoon Sohn,et al.  A review of structural health monitoring literature 1996-2001 , 2002 .

[2]  J. Beck,et al.  Updating Models and Their Uncertainties. I: Bayesian Statistical Framework , 1998 .

[3]  Hong Hao,et al.  Vibration based damage detection using artificial neural network with consideration of uncertainties , 2007 .

[4]  Zhikun Hou,et al.  Application of Wavelet Approach for ASCE Structural Health Monitoring Benchmark Studies , 2004 .

[5]  James L. Beck,et al.  Two-Stage Structural Health Monitoring Approach for Phase I Benchmark Studies , 2004 .

[6]  J. Beck,et al.  Asymptotic Expansions for Reliability and Moments of Uncertain Systems , 1997 .

[7]  David P. Thambiratnam,et al.  Damage detection in truss bridges using vibration based multi-criteria approach , 2011 .

[8]  Heung-Fai Lam,et al.  Multicrack Detection on Semirigidly Connected Beams Utilizing Dynamic Data , 2008 .

[9]  C. Ng,et al.  Scattering characteristics of Lamb waves from debondings at structural features in composite laminates. , 2012, The Journal of the Acoustical Society of America.

[10]  J. Moll,et al.  Guided waves for autonomous online identification of structural defects under ambient temperature variations , 2012 .

[11]  Ching-Tai Ng.  Probabilistic Methods for Structural Safety Evaluation: Damage Detection and Reliability Analysis of Structures , 2011 .

[12]  Martin Veidt,et al.  Integrated piezoceramic transducers for imaging damage in composite laminates , 2009, International Conference on Smart Materials and Nanotechnology in Engineering.

[13]  Ka-Veng Yuen,et al.  On the complexity of artificial neural networks for smart structures monitoring , 2006 .

[14]  Ching-Tai Ng,et al.  The selection of pattern features for structural damage detection using an extended Bayesian ANN algorithm , 2008 .

[15]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[16]  K. D. Murphy,et al.  Bayesian identification of a cracked plate using a population-based Markov Chain Monte Carlo method , 2011 .

[17]  James L. Beck,et al.  New Bayesian Model Updating Algorithm Applied to a Structural Health Monitoring Benchmark , 2004 .

[18]  J. Beck,et al.  Model Selection using Response Measurements: Bayesian Probabilistic Approach , 2004 .

[19]  L. Rose,et al.  Analytical and finite element prediction of Lamb wave scattering at delaminations in quasi-isotropic composite laminates , 2012 .

[20]  J M W Brownjohn,et al.  Structural health monitoring of civil infrastructure , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[21]  Heung-Fai Lam,et al.  System identification of an enclosure with leakages using a probabilistic approach , 2009 .

[22]  Keith Worden,et al.  An introduction to structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[23]  C. Ng,et al.  Scattering of the fundamental anti-symmetric Lamb wave at delaminations in composite laminates. , 2011, The Journal of the Acoustical Society of America.

[24]  Martin Veidt,et al.  Influence of stacking sequence on scattering characteristics of the fundamental anti-symmetric Lamb wave at through holes in composite laminates. , 2011, The Journal of the Acoustical Society of America.

[25]  Martin Veidt,et al.  Guided wave damage characterisation in beams utilising probabilistic optimisation , 2009 .

[26]  Randall J. Allemang,et al.  A Correlation Coefficient for Modal Vector Analysis , 1982 .

[27]  Yi-Qing Ni,et al.  Constructing input vectors to neural networks for structural damage identification , 2002 .

[28]  David Polidori,et al.  Determination of Modal Parameters from Ambient Vibration Data for Structural Health Monitoring , 1994 .