During shield tunneling through existing steel reinforced concrete structures, superstructure deformation is an important parameter that reflects the disturbance degree of engineering construction to existing structure. Precisely predicting structural deformation can help engineers adjust shield machine operational parameters and ensure the success of the project. There has been no attempt to study the feasibility and applicability of machine learning for predicting structural deformation when shield machine cut through existing structure. To address this problem, this paper proposes a novel hybrid model (DSGCN-TCN), combining dynamic spatial graph convolutional network (DSGCN) and temporal convolutional network (TCN), to predict structural deformation. First, dynamic adjacency matrix is constructed based on correlation coefficient and attention mechanism to describe the dynamic change of irregular graph structure. Then dynamic adjacency matrices and feature matrices as the input of the GCN model to extract the dynamic spatial feature of structural deformation data. Followed by TCN and attention layer to capture the temporal correlation of structural deformation data. Finally, the prediction performance of the proposed method is verified using measured data from practical engineering. The experiment results show that compared with the selected baseline models and sub-models, the proposed model can predict the structural deformation more accurately.

中文翻译：

---

盾构隧道施工过程中基于图卷积网络的结构变形预测新方法


盾构隧道穿越既有钢筋混凝土结构时，上部结构变形是反映工程施工对既有结构扰动程度的重要参数。精确预测结构变形可以帮助工程师调整盾构机运行参数，确保工程的成功。目前还没有尝试研究机器学习在盾构机切割现有结构时预测结构变形的可行性和适用性。为了解决这个问题，本文提出了一种新颖的混合模型（DSGCN-TCN），结合动态空间图卷积网络（DSGCN）和时间卷积网络（TCN）来预测结构变形。首先，基于相关系数和注意力机制构建动态邻接矩阵来描述不规则图结构的动态变化。然后动态邻接矩阵和特征矩阵作为GCN模型的输入，提取结构变形数据的动态空间特征。接下来是 TCN 和注意力层来捕获结构变形数据的时间相关性。最后，利用实际工程实测数据验证了该方法的预测性能。实验结果表明，与所选的基线模型和子模型相比，该模型能够更准确地预测结构变形。