Modeling of Mechanical Properties of Recycled Foamed Asphalt Mix by Nonlinear Regression and Artificial Neural Network and Ranking of Different Designs Using TOPSIS Method

Foamed asphalt mixtures, created using reclaimed asphalt pavement (RAP) and foamed bitumen, offer energy savings, reduced use of virgin materials, and lower transportation costs, combining the characteristics of rigid and flexible pavements. This study evaluated the mechanical performance of foamed asphalt mixtures with varying bitumen content (1–3 %) and cement content (0–2 %) to identify the optimal combination for pavement applications. Samples were tested for uniaxial compressive strength (UCS), indirect tensile strength (ITS), resilient modulus (RM), and tensile strength ratio (TSR) under laboratory conditions. To predict the results, a nonlinear regression model and an artificial neural network (ANN) were employed. The ANN model demonstrated greater accuracy with significantly lower prediction errors compared to the nonlinear regression model. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method was then used to select the optimal combination of materials. TOPSIS prioritizes mixtures with the shortest geometric distance to the positive ideal solution (best values for all attributes) and the longest distance from the negative ideal solution. The results showed that UCS and RM increased as the bitumen content increased from 1 % to 2 %, but these properties decreased when the bitumen content exceeded 2 %. In contrast, ITS (dry and saturated) showed continuous improvement with an increase in bitumen content from 1 % to 3 %. TOPSIS analysis identified the mixture with 3 % bitumen and 2 % cement as the optimal combination, achieving the best overall performance in the UCS, ITS, RM, and TSR tests. This study highlights the utility of foamed asphalt mixtures for sustainable construction, demonstrating that ANN predictions and TOPSIS can effectively guide material selection to achieve superior mechanical performance while reducing environmental impact.