Loading...

Hybrid stacked neural network empowered by novel loss function for structural response history prediction using input excitation and roof acceleration

Karami, R ; Sharif University of Technology | 2024

97 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.engappai.2024.108984
  3. Publisher: 2024
  4. Abstract:
  5. This paper presents a framework to predict the entire displacement time histories of all floors of buildings using a novel double-head neural network composed of causal Convolution Neural Network layers and Long Short-Term Memory layers. State-of-the-art deep techniques have been effectively employed to construct a surrogate model as an alternative to traditional time-consuming and expert-reliant approaches in evaluating damages and response modeling. An innovative loss function is introduced, facilitating the concurrent implementation of stacking, normalization, and multi-task learning capabilities, directing the network to simultaneously learn the time-series data and its rate of variation at every time step. This approach proves beneficial, particularly in maximum displacement and residual displacement predictions, and when dealing with displacement time series predictions in highly nonlinear regions. A comprehensive database is developed including ground motions and roof floor accelerations of steel buildings with eccentrically braced frames (EBF) and moment-resisting frames (MRF) as inputs and displacement time histories of all floors as outputs. The database involves 2,210,000 and 1,092,000 time steps, for EBF and MRF resulting from 44 far-field and 40 large magnitude-small distance ground motions, respectively, through incremental dynamic analysis. The performance of the proposed method is evaluated on scaled new ground motions in different damage states. Results confirm that the proposed stacked network predicts displacement time histories of the case study buildings with 95% accuracy for unseen datasets. In addition, the suggested loss function enhances the prediction performance by a minimum of 12.5% compared to other state-of-the-art loss functions when using the same deep learning architecture advanced in this research. Finally, a graphical user interface is developed to make the proposed approach time-efficient and expert-needless. © 2024 Elsevier Ltd
  6. Keywords:
  7. Graphics processing unit-accelerated long short-term memory ; Computer graphics ; Computer graphics equipment ; Convolution ; Floors ; Forecasting ; Graphical user interface ; Long short-term memory ; Multilayer neural networks ; Network layers ; Program processors ; Roofs ; Structural frames ; Causal convolution neural network ; Causal convolutions ; Convolution neural network ; Differentiation loss ; Displacement-time history ; Graphic processing unit-accelerated long short-term memory ; Loss functions ; Response prediction ; Structural time series response prediction ; Time series ; Graphics processing unit
  8. Source: Engineering Applications of Artificial Intelligence ; Volume 136 , 2024 ; 09521976 (ISSN)
  9. URL: https://www.sciencedirect.com/science/article/abs/pii/S0952197624011424