Bituminous Mixtures Experimental Data Modeling Using a Hyperparameters-Optimized Machine Learning Approach

This study introduces a machine learning approach based on Artificial Neural Networks (ANNs) for the prediction of Marshall test results, stiffness modulus and air voids data of different bituminous mixtures for road pavements. A novel approach for an objective and semi-automatic identification of the optimal ANN’s structure, defined by the so-called hyperparameters, has been introduced and discussed. Mechanical and volumetric data were obtained by conducting laboratory tests on 320 Marshall specimens, and the results were used to train the neural network. The k-fold Cross Validation method has been used for partitioning the available data set, to obtain an unbiased evaluation of the model predictive error. The ANN’s hyperparameters have been optimized using the Bayesian optimization, that overcame efficiently the more costly trial-and-error procedure and automated the hyperparameters tuning. The proposed ANN model is characterized by a Pearson coefficient value of 0.868.

Modification of a bituminous binder using waste products from the polymer industry

In this paper, we have investigated the possibilities of the modification of bituminous mixtures using recycled plastic. Waste from enterprises that process plastic is a serious danger to the environment, which is why the need to develop technologies for their processing is not in doubt. The economic advantages of using such additives are that the modifier used is the total waste of industrial enterprises that manufacture products from thermoplastics. Thus, it is possible to solve several problems at once: reducing the cost of production of bitumen; improvement of their physical and chemical characteristics and recycling of non-recycled waste. Patent information on the use of thermoplastics as a bitumen modifier was analyzed. During the work, waste from the extrusion industry of high-pressure polyethylene (LDPE) used. The influence of additives on the basic physical parameters of bitumen is shown. In the course of research, it was found that the addition of 2-3% polymers to the original formulation allows us to obtain bitumen, the main physical parameters of which (penetration, ductility, softening) meet the existing requirements. With this method of bitumen modification, the cost of their production is reduced without deterioration of the properties of the finished product. We also investigated the possibility of introducing up to 25% modifiers into the formulation, for maximum utilization of polymer waste. The bitumen obtained in this way can be used in regions with a hot climate. An important fact is the unification of the method of introducing additives into the existing technology, which does not require its change. The results of the study showed that thanks to the results obtained, it is possible to significantly reduce the cost of producing asphalt and bitumen products, expand the technological properties of finished road surfaces, and solve the problem of recycling plastic waste.