This paper introduces a novel deep learning approach to predict the engineering properties of the ground improved by Rapid Impact Compaction (RIC), which is a ground improvement technique that uses a drop hammer to compact the soil and fill layers. The proposed approach uses transformer-based neural networks to capture the complex nonlinear relationships between the input features, such as the hammer energy, drop height, and number of blows, and the output variables, such as the cone resistance. The approach is applied to a real-world dataset from a trial test section for the new apron construction of the Utapao International Airport in Thailand. The results show that the proposed approach outperforms the existing methods in terms of prediction accuracy and efficiency and provides interpretable attention maps that reveal the importance of different features for RIC prediction. The paper also discusses the limitations and future directions of applying deep learning methods to RIC prediction.

该研究介绍了一种新颖的深度学习方法，用于预测通过快速冲击固土改良的工程性质。该方法使用基于Transformer的神经网络来捕捉输入特征（例如锤能量、下落高度和冲击次数）与输出变量（例如锥度阻力）之间的复杂非线性关系。该方法应用于泰国乌塔堡国际机场新停机坪建设的试验区的实际数据集。结果表明，该方法在预测准确性和效率方面优于现有方法，并提供了可解释的注意力图，显示了RIC预测中不同特征的重要性。该论文还讨论了将深度学习方法应用于RIC预测的限制和未来方向。

基于Transformer模型的快速压实结果预测：以乌塔堡国际机场为案例研究