Application of Hopfield neural network to structural health monitoring

Structural health monitoring (SHM) using artificial neural networks has received increasing attention due to robustness of neural networks, better performance compared to conventional damage detection methods, and influential pattern recognition capability. This article aims to introduce Hopfield neural network (HNN), for the first time, to the SHM community. On this basis, a novel damage identification method by the HNN is proposed to detect damage and estimate damage severity with the aid of measured mode shapes in undamaged and damaged conditions. In this method, these vibration characteristics measured from sensors are used as initial conditions in the HNN. A key benefit of the HNN is that this novel neural network is inherently able to define a threshold value in such a way that any deviation from this value is indicative of damage occurrence. The accuracy and performance of the damage detection problems by the HNN is experimentally verified by the I40 Bridge. Results show that the proposed method is potentially able to detect damage and estimate the damage severity based on the outputs of the HNN.

[1]  Jin-Hak Yi,et al.  Sequential damage detection approaches for beams using time-modal features and artificial neural networks , 2009 .

[2]  M.N.S. Swamy,et al.  Neural Networks and Statistical Learning , 2013 .

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

[4]  Y. Yana,et al.  Development in vibration-based structural damage detection technique , 2007 .

[5]  R. Ganguli.  A Fuzzy Logic System for Ground Based Structural Health Monitoring of a Helicopter Rotor Using Modal Data , 2001 .

[6]  Ranjan Ganguli,et al.  Damage assessment of composite plate structures with material and measurement uncertainty , 2016 .

[7]  James H. Garrett,et al.  Use of neural networks in detection of structural damage , 1992 .

[8]  Claudomiro Sales,et al.  A novel unsupervised approach based on a genetic algorithm for structural damage detection in bridges , 2016, Eng. Appl. Artif. Intell..

[9]  Ranjan Ganguli,et al.  Structural Damage Detection Using Modal Curvature and Fuzzy Logic , 2009 .

[10]  Pedro Ribeiro,et al.  A 2D Hopfield Neural Network approach to mechanical beam damage detection , 2015, Multidimens. Syst. Signal Process..

[11]  Hamid Reza Mirdamadi,et al.  An effective damage identification approach in thick steel beams based on guided ultrasonic waves for structural health monitoring applications , 2013 .

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

[13]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

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

[15]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[16]  Teresa Mendonça,et al.  Hopfield neural networks for on-line parameter estimation , 2009, Neural Networks.

[17]  S. Masri,et al.  Application of Neural Networks for Detection of Changes in Nonlinear Systems , 2000 .

[18]  John N. Ivan,et al.  Structural Damage Detection Using Artificial Neural Networks , 1998 .

[19]  X. Fang,et al.  Structural damage detection using neural network with learning rate improvement , 2005 .

[20]  David A. Nix,et al.  Vibration–based structural damage identification , 2001, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[21]  Ward Heylen,et al.  Damage Detection with Parallel Genetic Algorithms and Operational Modes , 2010 .

[22]  Li Cheng,et al.  Artificial Neural Network ( ANN )-based Crack Identification in Aluminum Plates with Lamb Wave Signals , 2008 .

[23]  S. Quek,et al.  An Application of a Plastic Optical Fiber Sensor and Genetic Algorithm for Structural Health Monitoring , 2006 .

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