A hybrid numerical/neurocomputing strategy for sensitivity analysis of nonlinear structures

Abstract A hybrid numerical/neurocomputing (HN/N) strategy is presented for the evaluation of selective sensitivity coefficients of nonlinear structures. In the hybrid strategy, multilayer feedforward neural networks are used to extend a range of the validity of predictions of sensitivity coefficients made by Pade approximants. To further increase the accuracy and the range of network predictions, a data expansion strategy is used in which additional training data are generated by using extrapolated values of the coefficients in a Taylor series. Within this strategy a number of techniques are examined for evaluating derivatives of response functions. The effectiveness of the HN N strategy is assessed by performing numerical experiments for composite panels subjected to combined thermal and mechanical loads. It is shown that the HN N strategy reduces the number of full-system analyses and allows obtaining selective information about the structural response and the sensitivity coefficients.

[1]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[2]  No Value,et al.  Proceedings of IJCNN'98 , 1998 .

[3]  Yih-Fang Huang,et al.  Bounds on the number of hidden neurons in multilayer perceptrons , 1991, IEEE Trans. Neural Networks.

[4]  Prabhat Hajela,et al.  Function extrapolation in structural reanalysis using neural networks , 1994 .

[5]  James H. Garrett,et al.  Knowledge-Based Modeling of Material Behavior with Neural Networks , 1992 .

[6]  P. D. Panagiotopoulos,et al.  Neural networks for computing in structural analysis: Methods and prospects of applications , 1993 .

[7]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[8]  José Herskovits,et al.  Advances in structural optimization , 1995 .

[9]  Alan F. Murray.  Applications of Neural Networks , 1994 .

[10]  Jeffrey R. Carter,et al.  Removing and adding network connections with recursive-error-minimization equations , 1990, Defense, Security, and Sensing.

[11]  Ahmed K. Noor,et al.  Recent Advances and Applications of Reduction Methods , 1994 .

[12]  P. J. Haley,et al.  Extrapolation limitations of multilayer feedforward neural networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[13]  Ahmed K. Noor,et al.  A hybrid neurocomputing/numerical strategy for nonlinear structural analysis , 1996 .

[14]  Ahmed K. Noor,et al.  Sensitivity analysis for large-deflection and postbuckling responses on distributed-memory computers , 1995 .

[15]  A. Noor.  Recent advances in reduction methods for nonlinear problems. [in structural mechanics , 1981 .

[16]  Chris R. Fuller,et al.  The prediction of nonlinear dynamic loads on helicopters from flight variables using artificial neural networks , 1992 .

[17]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[18]  I. G. Kevrekidis,et al.  Application of neural nets to system identification and bifurcation analysis of real world experimental data , 1990 .

[19]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[20]  Ahmed K. Noor,et al.  Bifurcation and post-buckling analysis of laminated composite plates via reduced basis technique , 1981 .

[21]  Duc T. Nguyen,et al.  Parallel-Vector Design Sensitivity Analysis in Structural Dynamics , 1991 .

[22]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

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

[24]  James L. Rogers,et al.  Reducing neural network training time with parallel processing , 1995 .