Abstract:

Existing methods struggle to accurately predict the structural response of buildings to dynamic loads， such as earthquakes， facing challenges such as the inability to effectively learn the cyclic variation of seismic waves and insufficient feature fusion. To address these challenges， a deep learning model for structural response prediction based on a frequency-domain attention mechanism was proposed. By combining the frequency-domain augmented attention mechanism with Gated Recurrent Units （GRUs）， the sparse nature of seismic wave time-series data in the frequency domain was exploited to mine its feature information deeply， and the high efficiency of GRU in time-series tasks was also retained， thereby enabling the efficient encoding of potential seismic wave features. Furthermore， a pyramid network structure with weight stacking was introduced to address the problem of training deep networks by facilitating shortcuts across layers. Additionally， an autoregressive prediction framework was proposed to enrich the feature space and enhance the prediction accuracy of the network by utilizing historical structural responses as auxiliary features. Experimental results of three case studies demonstrate that the proposed model outperforms existing approaches， such as the Residual Long Short-Term Memory （ResLSTM） network and the Physics-informed LSTM （PhyLSTM） network.

Key words: structural response prediction, time series prediction, deep learning, Gated Recurrent Unit (GRU), frequency domain attention enhancement, frequency domain feature fusion

摘要：

现有方法难以准确预测建筑物对地震等动态载荷的结构响应，存在无法有效学习地震波周期性变化以及解决特征融合不充分等问题。因此，提出一种基于频域注意力机制的结构响应深度学习预测模型。该模型结合频域增强的注意力机制与门控递归单元（GRU），利用地震波时间序列数据在频域上稀疏的特点，深度挖掘地震波在频域上的特征信息；并且保留了GRU在时间序列任务上的高效性，从而可有效编码地震波的潜在特征。同时引入权重堆叠的金字塔网络结构，通过跨层的捷径解决了深层网络训练困难的问题。此外，还提出了一种自回归的预测框架，借助历史结构响应作为辅助特征，进一步丰富特征空间，提高网络的预测精度。针对3个案例的实验结果表明，所提模型在预测的准确性和可靠性方面均超越了残差长短时记忆（ResLSTM）网络、物理知识嵌入的长短时记忆（PhyLSTM）网络等。

关键词: 结构响应预测, 时间序列预测, 深度学习, 门控递归单元, 频域注意力增强, 频域特征融合