Dynamic Analysis of Nonlinear Civil Engineering Structures using Artificial Neural Network with Adaptive Training (original) (raw)
2021, arXiv (Cornell University)
Dynamic analysis of structures subjected to earthquake excitation is a time-consuming process, particularly in the case of extremely small time step required, or in the presence of high geometric and material nonlinearity. Performing parametric studies in such cases is even more tedious. The advancement of computer graphics hardware in recent years enables efficient training of artificial neural networks that are well-known to be capable of learning highly nonlinear mappings. Traditional artificial neural networks are usually built on fixed architecture which consists of a fixed number of nodes and hidden layers, and consequently is more likely to get stuck in local minima during training. In this study, artificial neural networks are developed with adaptive training algorithms, which enables automatic nodes generation and layers addition. The hyperbolic tangent function is selected as the activation function. Stochastic Gradient Descent and Back Propagation algorithms are adopted to train the networks. The neural networks initiate with a small number of hidden layers and nodes. During training, the performance of the network is continuously tracked, and new nodes or layers are added to the hidden layers if the neural network reaches its capacity. At the end of the training process, the network with appropriate architecture is automatically formed. The performance of the networks has been validated for inelastic shear frames, as well as rocking structures, of which both are first built in finite element program for dynamic analysis to generate training data. Energy dissipation is considered during rocking motion using a Hilber-Hughes-Taylor numerically dissipative time step integration scheme. Results have shown the developed networks can successfully predict the time-history response of the shear frame systems subjected to real ground motion records. The response of rocking structures can be mostly well predicted although there exist small discrepancies at some instants. Furthermore, the efficiency of the proposed neural networks is also examined, which shows the computational time can be reduced by 43% than FE models, when the Graphical Processing Units acceleration is enabled. This indicates the trained networks can be utilized to generate rocking spectrums of structures more efficiently which demands a large number of time-history analyses.
Sign up for access to the world's latest research.
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.