This paper evaluates the influences of variations in asphalt mixture parameters during construction on the variations of pavement performance using back-propagation (BP) neural networks. The variations of gradation () and asphalt-aggregate ratio () were assessed through a variability analysis. The influences of and propagation were analyzed via BP neural networks and a sensitivity analysis. A reliability assessment was conducted to evaluate the joint effects of and . Results illustrate that the and during transportation are more severe than those during other processes. BP neural networks can precisely and robustly trace the influences of the and . Pavement performance exhibits greater sensitivity to and at sieve sizes of 0.075 mm and 2.36 mm. The joint effects of and significantly degrade permanent deformation more than fatigue life. High-quality paving effectively mitigates the negative impacts of segregation during transportation.

中文翻译：

---

使用反向传播神经网络研究骨料级配和沥青骨料比对施工过程中路面性能的影响


本文利用反向传播（BP）神经网络评估了施工过程中沥青混合料参数的变化对路面性能变化的影响。通过变异性分析评估级配 () 和沥青骨料比 () 的变化。通过BP神经网络和敏感性分析来分析其影响和传播。进行可靠性评估以评估 和 的联合效应。结果表明，运输过程中的 和 比其他过程中的情况更为严重。 BP 神经网络可以精确而稳健地追踪 和 的影响。路面性能对 0.075 毫米和 2.36 毫米的筛子尺寸表现出更高的敏感性。与疲劳寿命相比，联合效应显着降低永久变形。高质量的铺装有效减轻了运输过程中离析的负面影响。