Determining Displacement in Concrete Reinforcement Building with using Evolutionary Artificial Neural Networks

After the occurrence of an earthquake, the issues such as making decision promptly on building safety, making possibility to keep on utilizing from a building, locating the ruined place and the rate of the destruction is crucial. Today a new technique is the application of evolutionary artificial neural network models based on artificial intelligence, which is widely used in various scientific fields, especially in structure and earthquake engineering. In this article, a wall concrete frame with 4-stories and 4-bays, is studied in nonlinear dynamic analysis by software IDARC2D (ver.6.0) for 30 records of 0.1g to 1.5 g acceleration and the rate of total damage of the frame in each records and each accelerations are calculated, then the rate of damage are determined by using evolutionary artificial neural network models. To determine the number of effective lag times and input data of earthquake in the artificial neural network model, it is used Cross-Correlation of time series. Using genetic algorithm, the structure of the artificial neural network model were optimized in terms of cases such as number of layers and number of nodes through the hidden layer, type of transfer function and the learning algorithm of the network. All stages of training, validity and testing models were conducted by using NeuroSolutions Software. The results indicated that the number of effective lag times and input data were determined by applying Cross- Correlation method. Additionally, comparing outputs of MLP (MultiLayer perceptron) model as the best nonlinear regression model with the values of damage indicator for Park-Ang, it can be concluded that MLP model has more suitable abilities, accuracy and flexibility, than others.

[1]  Cheng-Wu Chen,et al.  Modeling and control for nonlinear structural systems via a NN-based approach , 2009, Expert Syst. Appl..

[2]  Bernice W. Polemis.  Nonparametric Statistics for the Behavioral Sciences , 1959 .

[3]  Hojjat Adeli,et al.  Neuro‐genetic algorithm for non‐linear active control of structures , 2008 .

[4]  C. M. Wen,et al.  A neural network approach for structural identification and diagnosis of a building from seismic response data , 2003 .

[5]  Yuyin Qian,et al.  Acceleration-based damage indicators for building structures using neural network emulators , 2008 .

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

[7]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 1—background and methodology , 2005 .

[8]  Elif Derya íbeyli,et al.  Estimation of radiation damage at the structural materials of a hybrid reactor by probabilistic neural networks , 2009 .

[9]  Andrei M. Reinhorn,et al.  IDARC2D, Version 4.0: A Computer Program for the Inelastic Damage Analysis of Buildings , 1996 .

[10]  Usik Lee,et al.  A frequency response function-based structural damage identification method , 2002 .

[11]  W. R. Buckland,et al.  Statistical Theory and Methodology in Science and Engineering. , 1960 .

[12]  George C. Lee,et al.  A Structural Damage Neural Network Monitoring System , 1994 .

[13]  Elif Derya Übeyli,et al.  Estimation of radiation damage at the structural materials of a hybrid reactor by probabilistic neural networks , 2009, Expert Syst. Appl..

[14]  Charles R. Farrar,et al.  Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics: A literature review , 1996 .

[15]  Hong Hao,et al.  Damage identification of structures with uncertain frequency and mode shape data , 2002 .

[16]  Steven C. Wheelwright,et al.  Forecasting methods and applications. , 1979 .

[17]  Dikai Liu,et al.  Modelling of structural response and optimization of structural control system using neural network and genetic algorithm , 2000 .

[18]  Jiann-Shiun Lew,et al.  Using transfer function parameter changes for damage detection of structures , 1995 .