Performance evaluation of feedforward neural networks for modeling a vehicle to pole central collision

Artificial Neural Networks (ANNs) have strong potential in modeling nonlinear systems. This paper presents application of a feedforward neural network which utilizes back-propagation learning algorithm, in the area of modeling a vehicle to pole central collision. Kinematics of a typical mid-size vehicle impacting a rigid pole is reproduced by the means of neural networks approach. Firstly, a network is trained with the appropriate data set (acceleration, velocity, and displacement) and subsequently it is tested and simulated. We also provide a comparison concerning the efficiency and performance of each ANN created in this research. It is judged which of them generates the most satisfactory output in the shortest time.

[1]  Hamid Reza Karimi,et al.  Comparative analysis of vehicle to pole collision models established using analytical methods and neural networks , 2010 .

[2]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[3]  A Deb,et al.  Development of a new lumped-parameter model for vehicle side-impact safety simulation , 2008 .

[4]  Z Moumni,et al.  Simplified modelling of vehicle frontal crashworthiness using a modal approach , 2004 .

[5]  Hamid Reza Karimi,et al.  Mathematical modeling and analysis of a vehicle crash , 2010 .

[6]  Azim Eskandarian,et al.  Finite element model and validation of a surrogate crash test vehicle for impacts with roadside objects , 1997 .

[7]  Tso-Liang Teng,et al.  Analysis of dynamic response of vehicle occupant in frontal crash using multibody dynamics method , 2008, Math. Comput. Model..

[8]  Ted Belytschko,et al.  On Computational Methods for Crashworthiness , 1988 .

[9]  Karl-Gustaf Sundin,et al.  Identification of lumped parameter automotive crash models for bumper system development , 2009 .

[10]  Roland S. Burns,et al.  Advanced control engineering , 2001 .

[11]  Matej Borovinšek,et al.  Simulation of crash tests for high containment levels of road safety barriers , 2007 .

[12]  W. Pawlus,et al.  Further results on mathematical models of vehicle localized impact , 2010, 2010 3rd International Symposium on Systems and Control in Aeronautics and Astronautics.

[13]  L. Ljung,et al.  Overtraining, regularization and searching for a minimum, with application to neural networks , 1995 .

[14]  Kjell G. Robbersmyr,et al.  Application of viscoelastic hybrid models to vehicle crash simulation , 2011 .

[15]  Alaa F. Sheta,et al.  Time-series forecasting using GA-tuned radial basis functions , 2001, Inf. Sci..

[16]  Ciro A. Soto,et al.  Structural topology optimization for crashworthiness , 2004 .

[17]  Hamid Reza Karimi,et al.  Development of lumped-parameter mathematical models for a vehicle localized impact , 2011 .

[18]  Nikolaos Kourentzes,et al.  Feature selection for time series prediction - A combined filter and wrapper approach for neural networks , 2010, Neurocomputing.

[19]  Dong-Chul Han,et al.  Vehicle Frontal Crashworthiness Analysis by Simplified Structure Modeling using Nonlinear Spring and Beam Elements , 1996 .

[20]  Hamid Reza Karimi,et al.  Development of Mathematical Models for Analysis of a Vehicle Crash , 2010 .