A prediction model for the bearing capacity estimation of strip and ring footing embedded in layered sand is proposed using soft computing approaches, namely, artificial neural network (ANN) and random forest regression (RFR). The required data for the model preparation were generated by performing lower- and upper-bound finite-elements limit analysis by varying the properties of the top and bottom layers. Two types of layered sand conditions are considered in the study: (a) dense on loose sand; (b) loose on dense sand. The investigation for strip footing was carried out by varying the thickness of the top layer, embedment depth of the foundation and friction angles of top and bottom layers. For a ring footing, the internal-to-external diameter ratio forms an additional variable. In total, 1222 and 4204 data sets were generated for strip and ring footings, respectively. The performance measures obtained during the training and testing phase suggest that the RFR model outperforms the ANN. Also, following the literature, an analytical model was developed to predict the bearing capacity of strip footing on layered sand. The ANN and the generated analytical model predictions agreed with the published experimental data in the literature.

中文翻译：

---

嵌在层状砂中的条形和环形基础承载力预测

采用软计算方法，即人工神经网络 (ANN) 和随机森林回归 (RFR)，提出了嵌在层状砂中的条形和环形基础承载力估计的预测模型。模型准备所需的数据是通过改变顶层和底层的属性来执行下限和上限有限元极限分析生成的。研究中考虑了两种类型的层状砂条件：( a ) 密实的松散砂；(乙) 松散在密实的沙子上。通过改变顶层厚度、地基埋入深度和顶、底层摩擦角，对条形基础进行了研究。对于环形基础，内外径比构成了一个附加变量。总共为条形和环形基础分别生成了 1222 和 4204 个数据集。在训练和测试阶段获得的性能指标表明 RFR 模型优于 ANN。此外，根据文献，开发了一个分析模型来预测条形基础在层状沙地上的承载能力。人工神经网络和生成的分析模型预测与文献中公布的实验数据一致。