A comparative study of vibrational response based impact force localization and quantification using radial basis function network and multilayer perceptron

Application of Radial Basis Function Network (RBFN) to impact force identification.Application of Multilayer Perceptron (MLP) to the same task.Accuracy, success rate and error range comparison between RBFN and MLP.Estimation of accuracy improvement for using RBFN in place of MLP. Impact force identification from response sensors is important especially when force measurement using force sensor is not possible due to the installation or dynamic characteristic altering problems. For example, the bump-excited impact force acting on vehicle wheel or ship collision on an offshore structure. Among various existing impact identification approaches, neural network based force identification method has received great attention because one does not need to have a system model. Thus, it is less likely to be affected by ill-posed problem that often occurs during the inversion process. So far, previous studies focused on solving the impact force identification problem using only the conventional Multilayer Perceptron (MLP). Thus, there is a room for improvement to find an alternate algorithm that has great advantage over MLP. For this reason, this study proposes Radial Basis Function Network (RBFN) for possible further improvement in impact identification task. A comparative study between these two algorithms was conducted via experimental approach. Impact forces were made on a Perspex plate structure which was designed to produce similar dynamic behavior of a typical vehicle. Impact locations were fixed at four edges of the test rig to simulate impact events at a vehicle's wheels. Time-domain peak-to-peak and peak arrival time features were extracted from accelerometer data to use as network inputs. Few training data were taken in the way that they represent the entire range of magnitudes of all trial impacts made throughout the experiment. In overall, RBFN improved the impact localization and quantification accuracies by decreasing 32.98% and 40.91% error respectively compared to MLP. The improvement was mainly due to the RBFN's strong approximation ability and its superior tolerance to experimental noises/uncertainties.

[1]  Simon Haykin,et al.  Regularized radial basis functional networks: theory and applications , 2001 .

[2]  K. Chandrashekhara,et al.  Estimation of Contact Force on Composite Plates Using Impact-Induced Strain and Neural Networks , 1998 .

[3]  Yoon Young Kim,et al.  Detection of Impact Location for Composite Stiffened Panel Using FBG Sensors , 2010 .

[4]  H. Abdul Razak,et al.  Modal parameters based structural damage detection using artificial neural networks - a review , 2014 .

[5]  James S. Sirkis,et al.  Detection of Impact Location and Magnitude for Isotropic Plates Using Neural Networks , 1997 .

[6]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

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

[8]  Z. Sharif-Khodaei,et al.  Determination of impact location on composite stiffened panels , 2012 .

[9]  Sang-Kwon Lee,et al.  Experimental identification for inverse problem of a mechanical system with a non-minimum phase based on singular value decomposition , 2008 .

[10]  Zubaidah Ismail,et al.  Impact Force Identification With Pseudo-Inverse Method on a Lightweight Structure for Under-Determined, Even-Determined and Over-Determined Cases , 2014 .

[11]  David Thompson,et al.  The Quantification of Structure-Borne Transmission Paths by Inverse Methods - Part 2: Use of Regularization Techniques , 2003 .

[12]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[13]  Yang-Hann Kim,et al.  Impact source localization on an elastic plate in a noisy environment , 2006 .

[14]  T. Kundu,et al.  Locating point of impact in anisotropic fiber reinforced composite plates. , 2008, Ultrasonics.

[15]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[16]  Li Zhou,et al.  Impact load identification of composite structure using genetic algorithms , 2009 .

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

[18]  Tao Zhu,et al.  Force identification in time domain based on dynamic programming , 2014, Appl. Math. Comput..

[19]  Jie Pan,et al.  Prediction of Impact Forces in a Vibratory Ball Mill Using an Inverse Technique , 1997 .

[20]  Yi Liu,et al.  Dynamic force identification based on enhanced least squares and total least-squares schemes in the frequency domain , 2005 .

[21]  Stephen P. Timoshenko,et al.  Vibration problems in engineering , 1928 .

[22]  K. Worden,et al.  The application of machine learning to structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[23]  David Thompson,et al.  The quantification of structure-borne transmission paths by inverse methods. Part 1: Improved singular value rejection methods , 2003 .

[24]  Keith Worden,et al.  Detection of impacts in composite materials using piezoceramic sensors and neural networks , 1998, Smart Structures.

[25]  Dong Liang,et al.  Distributed coordination algorithm for impact location of preciseness and real-time on composite structures , 2013 .

[26]  J. F. Doyle.  A wavelet deconvolution method for impact force identification , 1997 .

[27]  Z. Sharif-Khodaei,et al.  Identification of impact force for smart composite stiffened panels , 2013 .

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

[29]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[30]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[31]  Stefan Hurlebaus,et al.  IDENTIFICATION OF THE IMPACT LOCATION ON A PLATE USING WAVELETS , 1998 .

[32]  Keith Worden,et al.  Impact detection in an aircraft composite panel—A neural-network approach , 2007 .

[33]  Marcelo Braga dos Santos,et al.  Identification of rotary machines excitation forces using wavelet transform and neural networks , 2002 .

[34]  Bogdan Wilamowski,et al.  Comparison between traditional neural networks and radial basis function networks , 2011, 2011 IEEE International Symposium on Industrial Electronics.