This paper aims to provide a methodology in determining the deterioration conditions of flexible pavements using the Long‐Term Pavement Performance (LTPP) database and artificial intelligence (AI)‐based finite element (FE) model updating. A new term quantifying the effects of the aging and load repetitions on the modulus gradient of the asphalt layer was defined. The modulus gradient change was captured by a two‐step calibration process. The proposed method combines the laboratory and field tests on the characterizations of the material properties and structural behaviors. Furthermore, it considers the effects of the environmental and loading conditions on the pavement behaviors and the gap between the laboratory and field tests on the same material characterizations. In this paper, the equivalent frequency in the asphalt layer for typical falling weight deflectometer (FWD) load was determined using the AI‐based FE model updating as well. This paper extends the applications of the FE model updating in the pavement structures and discusses the performance of the modulus as an indicator of the pavement condition.

中文翻译：

---

使用长期路面性能数据库和基于人工智能的有限元模型更新来确定柔性路面的劣化条件

本文旨在提供一种使用长期路面性能（LTPP）数据库和基于人工智能（AI）的有限元（FE）模型更新来确定柔性路面劣化条件的方法。定义了一个新术语，用于量化老化和载荷重复对沥青层模量梯度的影响。模量梯度变化通过两步校准过程捕获。所提出的方法结合了实验室和现场测试对材料特性和结构行为的表征。此外，它还考虑了环境和负载条件对路面性能的影响以及在相同材料特性下实验室测试和现场测试之间的差距。在本文中，同样使用基于AI的有限元模型更新来确定典型的落锤挠度计（FWD）负载在沥青层中的等效频率。本文扩展了有限元模型更新在路面结构中的应用，并讨论了模量作为路面状况指标的性能。