Structural damage detection using neural network with learning rate improvement

In this research, we explore the structural damage detection using frequency response functions (FRFs) as input data to the back-propagation neural network (BPNN). Such method is non-model based and thus could have advantage in many practical applications. Neural network based damage detection generally consists of a training phase and a recognition phase. Error back-propagation algorithm incorporating gradient method can be applied to train the neural network, whereas the training efficiency heavily depends on the learning rate. While various training algorithms, such as the dynamic steepest descent (DSD) algorithm and the fuzzy steepest descent (FSD) algorithm, have shown promising features (such as improving the learning convergence speed), their performance is hinged upon the proper selection of certain control parameters and control strategy. In this paper, a tunable steepest descent (TSD) algorithm using heuristics approach, which improves the convergence speed significantly without sacrificing the algorithm simplicity and the computational effort, is investigated. A series of numerical examples demonstrate that the proposed algorithm outperforms both the DSD and FSD algorithms. With this as basis, we implement the neural network to the FRF based structural damage detection. The analysis results on a cantilevered beam show that, in all considered damage cases (i.e., trained damage cases and unseen damage cases, single damage cases and multiple-damage cases), the neural network can assess damage conditions with very good accuracy.

[1]  M. L. Wang,et al.  Structural Damage Detection Using an Iterative Neural Network , 2000 .

[2]  Qing Hu,et al.  Fuzzy logic controlled neural network learning , 1994 .

[3]  Daniel J. Inman,et al.  Impedance-Based Structural Health Monitoring with Artificial Neural Networks , 2000 .

[4]  H. Luo,et al.  Dynamic Learning Rate Neural Network Training and Composite Structural Damage Detection , 1997 .

[5]  Grant P. Steven,et al.  VIBRATION-BASED MODEL-DEPENDENT DAMAGE (DELAMINATION) IDENTIFICATION AND HEALTH MONITORING FOR COMPOSITE STRUCTURES — A REVIEW , 2000 .

[6]  Lefteri H. Tsoukalas,et al.  MATLAB Supplement to Fuzzy and Neural Approaches in Engineering , 1997 .

[7]  M. Imregun,et al.  Combined neural network and reduced FRF techniques for slight damage detection using measured response data , 2001 .

[8]  Poyu Tsou,et al.  Structural damage detection and identification using neural networks , 1993 .

[9]  H. Luo,et al.  FUZZY LEARNING RATE NEURAL NETWORK TRAINING AND STRUCTURAL HEALTH MONITORING , 1997 .

[10]  Shih-Lin Hung,et al.  Detection of structural damage via free vibration responses generated by approximating artificial neural networks , 2003 .

[11]  Leonard Ziemiański,et al.  Neural networks in mechanics of structures and materials – new results and prospects of applications , 2001 .

[12]  N. T. Khiem,et al.  THE DYNAMIC STIFFNESS MATRIX METHOD IN FORCED VIBRATION ANALYSIS OF MULTIPLE-CRACKED BEAM , 2002 .

[13]  Mark J. Schulz,et al.  Locating Structural Damage Using Frequency Response Reference Functions , 1998 .

[14]  Manfred Weck,et al.  Design of an adaptive control system for DC servo motor , 1995, SAC '95.

[15]  Vassilis P. Plagianakos,et al.  An Improved Backpropagation Method with Adaptive Learning Rate , 1998 .

[16]  Mehmet Imregun,et al.  FREQUENCY–DOMAIN CRITERIA FOR CORRELATING AND UPDATING DYNAMIC FINITE ELEMENT MODELS , 2001 .

[17]  Ward Heylen,et al.  FRAC: a consistent way of comparing frequency response functions , 1996 .

[18]  Damodar R. Ambur,et al.  AN ARTIFICIAL NEURAL NETWORK BASED DAMAGE DETECTION SCHEME FOR ELECTRICALLY CONDUCTIVE COMPOSITE STRUCTURES , 2003 .

[19]  Jonathan E. Cooper,et al.  IDENTIFICATION OF RESTORING FORCES IN NON-LINEAR VIBRATION SYSTEMS USING FUZZY ADAPTIVE NEURAL NETWORKS , 2001 .

[20]  Cornelius T. Leondes.  Algorithms and Architectures , 1997 .

[21]  R. J. Kuo.  Fuzzy parameter adaptation for error backpropagation algorithm , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[22]  Keith Worden,et al.  DAMAGE DETECTION USING OUTLIER ANALYSIS , 2000 .

[23]  Norris Stubbs,et al.  Crack detection in beam-type structures using frequency data , 2003 .

[24]  Jaycee H. Chung,et al.  DETECTING STRUCTURAL DAMAGE USING FREQUENCY RESPONSE FUNCTIONS , 1998 .

[25]  Pan Zeng,et al.  Neural Computing in Mechanics , 1998 .

[26]  G. W. Ng.  application of Neural Networks to Adaptive Control of Nonlinear Systems , 1997 .

[27]  A. S. Naser,et al.  Structural Health Monitoring Using Transmittance Functions , 1999 .

[28]  S. S. Law,et al.  DAMAGE LOCALIZATION BY DIRECTLY USING INCOMPLETE MODE SHAPES. TECHNICAL NOTE , 2000 .

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

[30]  Kenji Fukumizu,et al.  Adaptive natural gradient learning algorithms for various stochastic models , 2000, Neural Networks.

[31]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[32]  Amir F. Atiya,et al.  An accelerated learning algorithm for multilayer perceptron networks , 1994, IEEE Trans. Neural Networks.

[33]  Keith Worden,et al.  Structural fault diagnosis and isolation using neural networks based on response-only data , 2003 .

[34]  Nikola Kasabov,et al.  Foundations Of Neural Networks, Fuzzy Systems, And Knowledge Engineering [Books in Brief] , 1996, IEEE Transactions on Neural Networks.

[35]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..