Abstract The accurate determination of resilient modulus (Mr) of pavement subgrade soils is an important factor for the successful design of pavement system. The important soil property Mr is complex in nature as it is dependent on several influential factors, such as soil physical properties, applied stress conditions, and environmental conditions. The aim of this study is to explore the potential of an evolutionary algorithm, i.e., genetic algorithm (GA), and a hybrid intelligent approach combining neural network with GA (ANN-GA), to estimate the Mr of cohesive pavement subgrade soils. To achieve this aim, a reliable database containing the results of repeated load triaxial tests (RLT) and other index properties of subgrade soils was utilized. GA was employed to develop a precise equation for predicting Mr of subgrade soils. In addition, GA was used as a tool for determining the optimal values of the weights and the bias of the ANN-GA approach. The developed ANN-GA model was then transferred to a functional relationship for further application and analyses. Several validation and verification phases were conducted to examine the performance of the developed models. The results indicated that both GA and ANN-GA models could accurately predict the Mr of cohesive subgrade soils, and performed better than other models in the literature. Finally, a sensitivity analysis was conducted to evaluate the effect of the utilized parameters on Mr.

中文翻译：

---

用于预测粘性路面路基土弹性模量的遗传模型的开发

摘要 路面路基土回弹模量（Mr）的准确测定是路面系统设计成功的重要因素。重要的土壤特性 Mr 在本质上是复杂的，因为它取决于几个影响因素，例如土壤物理特性、施加的应力条件和环境条件。本研究的目的是探索进化算法，即遗传算法 (GA) 和结合神经网络与遗传算法 (ANN-GA) 的混合智能方法的潜力，以估计粘性路面路基土壤的 Mr。为了实现这一目标，使用了一个可靠的数据库，其中包含重复荷载三轴试验 (RLT) 和路基土的其他指标特性的结果。GA 被用来开发一个精确的方程来预测路基土壤的 Mr。此外，GA 被用作确定权重的最佳值和 ANN-GA 方法的偏差的工具。然后将开发的 ANN-GA 模型转换为函数关系，以便进一步应用和分析。进行了几个验证和验证阶段来检查开发模型的性能。结果表明，GA和ANN-GA模型均能准确预测粘性路基土的Mr，且性能优于文献中的其他模型。最后，进行了敏感性分析以评估所使用的参数对 Mr. 的影响。进行了几个验证和验证阶段来检查开发模型的性能。结果表明，GA和ANN-GA模型均能准确预测粘性路基土的Mr，且性能优于文献中的其他模型。最后，进行了敏感性分析以评估所使用的参数对 Mr. 的影响。进行了几个验证和验证阶段来检查开发模型的性能。结果表明，GA和ANN-GA模型均能准确预测粘性路基土的Mr，且性能优于文献中的其他模型。最后，进行了敏感性分析以评估所使用的参数对 Mr. 的影响。