This paper presents the potential energy savings and how to achieve sustainability by predicting the temperature of aggregate stockpiles in the production process of asphalt mixtures. A possible way to achieve energy efficiency and therefore sustainability is to preheat the mineral mixture, i.e. the aggregate, before it enters the production process in the asphalt mixing plant, thus resulting in lower energy consumption per ton of asphalt. The main objective of the conducted research was to develop and test an artificial neural network (ANN) model and analyse the influence of three independent variables (hour in the day, season, air temperature) on the one dependent variable (temperature of the mineral mixture). The impact of the observed independent variables on the temperature of the mineral mixture is analysed in a standard uncovered aggregate stockpile and in a solar aggregate stockpile. From the obtained modelling results, it can be concluded that it is possible to successfully use ANN in the process of predicting the temperature of aggregate stockpiles in the processes of aggregate production and storage as part of the whole production process of asphalt mixtures.

本文介绍了潜在的节能效果，以及如何通过预测沥青混合料生产过程中骨料的温度来实现可持续性。实现能源效率并因此实现可持续性的一种可能方法是在矿物混合物（即骨料）进入沥青混合设备的生产过程之前对其进行预热，从而降低每吨沥青的能源消耗。进行研究的主要目的是开发和测试人工神经网络（ANN）模型，并分析三个自变量（一天中的小时，季节，气温）对一个因变量（矿物混合物的温度）的影响）。在标准的未覆盖集料堆和太阳能集料堆中分析了观察到的独立变量对矿物混合物温度的影响。从获得的建模结果可以得出结论，在骨料生产和储存过程中作为沥青混合料整个生产过程的一部分，可以成功地在预测骨料温度的过程中成功使用ANN。