Matrix analysis of nonlinear trusses using Prandtl-2 Neural Networks

Abstract A new method, based on the concepts of matrix analysis as well as the learning capabilities of neural networks, for the analysis of nonlinear trusses under dynamic loading is presented. The method can be applied to static trusses too. While there have been attempts in the past to use neural networks to identify and model different structures based on data measured on structural response directly, the main feature and advantage of this new method is in its capability to model a nonlinear truss by assembling the data collected on the response of its members. The basics of the method are: (1) for each truss member, a neural network is trained to learn and simulate its load–response behavior, (2) the member neural networks are then assembled to build another neural network which can simulate the load–response behavior of the whole truss. Noticing test at member level is generally easier than at structure level, this can make the building of a neural network to simulate the response of the truss more affordable. Also this has potential application when it is hard to find a mathematical model from experimental data to describe the internal force vector for a truss, as well as identification and control of trusses where precise modeling of the structure is a key point to the success of the application. Prandtl Neural Network, developed recently by the authors for modeling of nonlinear hysteretic materials, has been improved and used in this study too. The improved version has been called Prandtl-2 Neural Network (PNN2) in this paper. The method has been applied to the static and dynamic analysis of a 3-bar and a 10-bar benchmark truss successfully, the results of which are reported in this paper.

[1]  Hava T. Siegelmann,et al.  Computational capabilities of recurrent NARX neural networks , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[2]  H. M. Chen,et al.  Neural Network for Structural Dynamic Model Identification , 1995 .

[3]  A. Visintin.  Differential models of hysteresis , 1994 .

[4]  O. Nelles.  Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models , 2000 .

[5]  Bin Xu,et al.  Direct identification of structural parameters from dynamic responses with neural networks , 2004, Eng. Appl. Artif. Intell..

[6]  Stefania Tomasiello.  An application of neural networks to a non-linear dynamics problem , 2004 .

[7]  B. Schrefler,et al.  ANN approach to sorption hysteresis within a coupled hygro‐thermo‐mechanical FE analysis , 2001 .

[8]  Sami F. Masri,et al.  Identification of structural systems by neural networks , 1996 .

[9]  S. Masri,et al.  Identification of Nonlinear Dynamic Systems Using Neural Networks , 1993 .

[10]  S. Masri,et al.  Robust Adaptive Neural Estimation of Restoring Forces in Nonlinear Structures , 2001 .

[11]  Abdolreza Joghataie,et al.  Dynamic Analysis of Nonlinear Frames by Prandtl Neural Networks , 2008 .

[12]  Fereidoun Amini,et al.  Neural Network for Structure Control , 1995 .

[13]  Abdolreza Joghataie,et al.  Designing a General Neurocontroller for Water Towers , 2000 .

[14]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[15]  Abdolreza Joghataie.  Neuro-finite element static analysis of structures by assembling elemental neuro-modelers , 2003, EUSFLAT Conf..

[16]  Chuen-Tsai Sun,et al.  Constructing hysteretic memory in neural networks , 2000, IEEE Trans. Syst. Man Cybern. Part B.

[17]  François M. Hemez,et al.  NEURAL IDENTIFICATION OF NON-LINEAR DYNAMIC STRUCTURES , 2001 .

[18]  R. Clough,et al.  Dynamics Of Structures , 1975 .

[19]  Chung Bang Yun,et al.  Substructural identification using neural networks , 2000 .

[20]  Jamshid Ghaboussi,et al.  Active Control of Structures Using Neural Networks , 1995 .

[21]  K. Bathe.  Finite Element Procedures , 1995 .

[22]  Jamshid Ghaboussi,et al.  Neural network constitutive model for rate-dependent materials , 2006 .

[23]  Elias B. Kosmatopoulos,et al.  Analysis and modification of Volterra/Wiener neural networks for the adaptive identification of non-linear hysteretic dynamic systems , 2004 .