Purpose

The time-varying equivalent linear temperature gradient (ELTG) significantly affects the development of faulting and must therefore be accounted for in pavement design. The same is true for faulting of bonded concrete overlays of asphalt (BCOA) with slabs larger than 3 x 3 m. However, the evaluation of ELTG in Mechanistic-Empirical (ME) BCOA design is highly time-consuming. The use of an effective ELTG (EELTG) is an efficient alternative to calculating ELTG. In this study, a model to quickly evaluate EELTG was developed for faulting in BCOA for panels 3 m or longer in size, whose faulting is sensitive to ELTG.

Design/methodology/approach

A database of EELTG responses was generated for 144 BCOAs at 169 locations throughout the continental United States, which was used to develop a series of prediction models. Three methods were evaluated: multiple linear regression (MLR), artificial neural networks (ANNs), and multi-gene genetic programming (MGGP). The performance of each method was compared, considering both accuracy and model complexity.

Findings

It was shown that ANNs display the highest accuracy, with an R² of 0.90 on the validation dataset. MLR and MGGP models achieved R² of 0.73 and 0.71, respectively. However, these models consisted of far fewer free parameters as compared to the ANNs. The model comparison performed in this study highlights the need for researchers to consider the complexity of models so that their direct implementation is feasible.

Originality/value

This research produced a rapid EELTG prediction model for BCOAs that can be incorporated into the existing faulting model framework.

中文翻译：

---

沥青路面粘结混凝土覆盖层有效等效线性温度梯度的预测

目的

随时间变化的等效线性温度梯度（ELTG）显着影响断层的发展，因此在路面设计中必须予以考虑。对于板尺寸大于 3 x 3 m 的沥青粘合混凝土覆盖层 (BCOA) 的断层也是如此。然而，机械经验 (ME) BCOA 设计中的 ELTG 评估非常耗时。使用有效 ELTG (EELTG) 是计算 ELTG 的有效替代方法。在这项研究中，开发了一种快速评估 EELTG 的模型，用于 3 m 或更长尺寸面板的 BCOA 故障，其故障对 ELTG 敏感。

设计/方法论/途径

为美国大陆 169 个地点的 144 个 BCOA 生成了 EELTG 反应数据库，用于开发一系列预测模型。评估了三种方法：多元线性回归（MLR）、人工神经网络（ANN）和多基因遗传编程（MGGP）。考虑到准确性和模型复杂性，比较了每种方法的性能。

发现

结果表明，人工神经网络显示出最高的准确度，验证数据集上的R ²为 0.90。 MLR 和 MGGP 模型的R ²分别为 0.73 和 0.71。然而，与人工神经网络相比，这些模型包含的自由参数要少得多。本研究中进行的模型比较强调了研究人员需要考虑模型的复杂性，以便其直接实施是可行的。

原创性/价值

这项研究产生了 BCOA 的快速 EELTG 预测模型，可以将其纳入现有的断层模型框架中。