Development of Neural Network Based Hysteretic Models for Steel Beam-Column Connections Through Self-Learning Simulation

Beam-column connections are zones of highly complex actions and deformations interaction that often lead to failure under the effect of earthquake ground motion. Modeling of the beam-column connections is important both in understanding the behavior and in design. In this article, a framework for developing a neural network (NN) based steel beam-column connection model through structural testing is proposed. Neural network based inelastic hysteretic model for beam-column connections is combined with a new component based model under self-learning simulation framework. Self-learning simulation has the unique advantage in that it can use structural response to extract material models. Self-learning simulation is based on auto-progressive algorithm that employs the principles of equilibrium and compatibility, and the self-organizing nature of artificial neural network material models. The component based model is an assemblage of rigid body elements and spring elements which represent smeared constitutive behaviors of components; either nonlinear elastic or nonlinear inelastic behavior of components. The component based model is verified by a 3-D finite element analysis. The proposed methodology is illustrated through a self-learning simulation for a welded steel beam-column connection. In addition to presenting the first application of self-learning simulation to steel beam-column connections, a framework is outlined for applying the proposed methodology to other types of connections.

[1]  W. Ramberg,et al.  Description of Stress-Strain Curves by Three Parameters , 1943 .

[2]  Xiping Wu.  Neural network-based material modeling , 1992 .

[3]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[4]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[5]  Faris Albermani,et al.  Cyclic and seismic response of flexibly jointed frames , 1994 .

[6]  Mark W. Wales,et al.  Coupled Moment‐Axial Force Behavior in Bolted Joints , 1983 .

[7]  Kurt H. Gerstle,et al.  Analysis and Tests of Flexibly Connected Steel Frames , 1986 .

[8]  Martin A. Riedmiller,et al.  Advanced supervised learning in multi-layer perceptrons — From backpropagation to adaptive learning algorithms , 1994 .

[9]  F. Arbabi,et al.  Drift of flexibly connected frames , 1982 .

[10]  G. N. Pande,et al.  On self-learning finite element codes based on monitored response of structures , 2000 .

[11]  Jamshid Ghaboussi,et al.  Autoprogressive training of neural network constitutive models , 1998 .

[12]  Mingfu Michael Zhang.  Neural Network Material Models Determined From Structural Tests , 1997 .

[13]  David A. Nethercot,et al.  Effect of semi-rigid connections on steel column strength , 1980 .

[14]  Masayoshi Nakashima,et al.  Strain-Hardening Behavior of Shear Panels Made of Low-Yield Steel. I: Test , 1995 .

[15]  Youssef M A Hashash,et al.  Numerical implementation of a neural network based material model in finite element analysis , 2004 .

[16]  Masayoshi Nakashima,et al.  Tests of Welded Beam-Column Subassemblies. I: Global Behavior , 1998 .

[17]  Eric M. Lui,et al.  Behavior of braced and unbraced semi-rigid frames , 1988 .

[18]  Roberto T. Leon,et al.  Component Modeling of Partially Restrained Composite Joints under Cyclic and Dynamic Loading , 2004 .

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

[20]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[21]  Ahmad A. Ghosn,et al.  Governing Stresses in Z-Purlin Lap Joints , 1995 .

[22]  Jamshid Ghaboussi,et al.  Constitutive modeling of geomaterials from non-uniform material tests , 1998 .

[23]  H Krawinkler,et al.  Shear in Beam-Column Joints in Seismic Design of Steel Frames , 1978, Engineering Journal.

[24]  Ralph M. Richard,et al.  Versatile Elastic-Plastic Stress-Strain Formula , 1975 .

[25]  M. John Frye,et al.  Analysis of Flexibly Connected Steel Frames , 1975 .