Energy-absorption forecast of thin-walled structure by GA-BP hybrid algorithm

In order to analyze the influence rule of experimental parameters on the energy-absorption characteristics and effectively forecast energy-absorption characteristic of thin-walled structure, the forecast model of GA-BP hybrid algorithm was presented by unifing respective applicability of back-propagation artificial neural network (BP-ANN) and genetic algorithm (GA). The detailed process was as follows. Firstly, the GA trained the best weights and thresholds as the initial values of BP-ANN to initialize the neural network. Then, the BP-ANN after initialization was trained until the errors converged to the required precision. Finally, the network model, which met the requirements after being examined by the test samples, was applied to energy-absorption forecast of thin-walled cylindrical structure impacting. After example analysis, the GA-BP network model was trained until getting the desired network error only by 46 steps, while the single BP-ANN model achieved the same network error by 992 steps, which obviously shows that the GA-BP hybrid algorithm has faster convergence rate. The average relative forecast error (ARE) of the SEA predictive results obtained by GA-BP hybrid algorithm is 1.543%, while the ARE of the SEA predictive results obtained by BP-ANN is 2.950%, which clearly indicates that the forecast precision of the GA-BP hybrid algorithm is higher than that of the BP-ANN.

[1]  A Scholes,et al.  Development of Crashworthiness for Railway Vehicle Structures , 1993 .

[2]  Z. Zhong.  Finite Element Procedures for Contact-Impact Problems , 1993 .

[3]  W. Abramowicz,et al.  Thin-walled structures as impact energy absorbers , 2003 .

[4]  Przemysław Kołakowski,et al.  The effect of selected parameters on ship collision results by dynamic FE simulations , 2003 .

[5]  J. Navarro-Esbrí,et al.  Time series analysis and forecasting techniques for municipal solid waste management , 2002 .

[6]  Norman Jones.  Some recent developments in the dynamic inelastic behaviour of structures , 2006 .

[7]  Hsiao-Tien Pao,et al.  A comparison of neural network and multiple regression analysis in modeling capital structure , 2008, Expert Syst. Appl..

[8]  Muddu Sekhar,et al.  Non-linear regression model for spatial variation in precipitation chemistry for South India , 2009 .

[9]  Mark White,et al.  Experimental study into the energy absorbing characteristics of top-hat and double-hat sections subjected to dynamic axial crushing , 1999 .

[10]  Comparison of hot rolled steel mechanical property prediction models using linear multiple regression, non-linear multiple regression and non-linear artificial neural networks , 2005 .

[11]  T. Wierzbicki,et al.  Relative merits of single-cell, multi-cell and foam-filled thin-walled structures in energy absorption , 2001 .

[12]  H. R. Zarei,et al.  Multiobjective crashworthiness optimization of circular aluminum tubes , 2006 .

[13]  Sushil Kumar,et al.  Efficient real coded genetic algorithm to solve the non-convex hydrothermal scheduling problem , 2007 .

[14]  Hui-Chen Su,et al.  A nonlinear time series analysis using two‐stage genetic algorithms for streamflow forecasting , 2008 .

[15]  Jianguo Yu,et al.  Gray correlation analysis and prediction models of living refuse generation in Shanghai city. , 2007, Waste management.

[16]  Jürgen Bode,et al.  Neural networks for cost estimation: Simulations and pilot application , 2000 .

[17]  Eric Markiewicz,et al.  Evaluation of different simplified crash models: application to the under-frame of a railway driver's cab , 2001 .

[18]  Avraham Shtub,et al.  Estimating the cost of steel pipe bending, a comparison between neural networks and regression analysis , 1999 .

[19]  Qing Li,et al.  Design optimization of regular hexagonal thin-walled columns with crashworthiness criteria , 2007 .

[20]  Yuan Cao,et al.  RS-SVM forecasting model and power supply-demand forecast , 2011 .