Offer preparation has always been a specific part of a building process which has significant impact on company business. Due to the fact that income greatly depends on offer’s precision and the balance between planned costs, both direct and overheads, and wished profit, it is necessary to prepare a precise offer within required time and available resources which are always insufficient. The paper presents a research of precision that can be achieved while using artificial intelligence for estimation of cost and duration in construction projects. Both artificial neural networks (ANNs) and support vector machines (SVM) are analysed and compared. The best SVM has shown higher precision, when estimating costs, with mean absolute percentage error (MAPE) of 7.06% compared to the most precise ANNs which has achieved precision of 25.38%. Estimation of works duration has proved to be more difficult. The best MAPEs were 22.77% and 26.26% for SVM and ANN, respectively.

The management of roads, as well as their maintenance, calls for an adequate assessment of the load-bearing capacity of the pavement structure. This serves as the basis on which future maintenance requirements are planned and plays a significant role in determining whether the rehabilitation or reconstruction of the pavement structure is required. The stability of the pavement structure depends on a large number of parameters, and it is not possible to fully assess all of them when making an estimation. One of the most significant parameters is the modulus of elasticity of asphalt layers (E_AC). The goal of this study is to use models based on machine learning to perform a quick and efficient assessment of the modulus of elasticity of asphalt layers, as well as to compare the formed models. The paper defines models for E_AC estimation using machine learning, in which the input data include the measured deflections and the temperature of the upper surface of the asphalt layer. Analyses of modeling using artificial neural networks (ANNs), support vector machines (SVMs) and boosted regression trees (BRT) were compared. The SVM method showed a higher accuracy in estimating the E_AC modulus, with a mean absolute percentage error (MAPE) of 7.64%, while the ANN method and the BRT achieved accuracies of 9.13% and 8.84%, respectively. Models formed in this way can be practically implemented in the management and maintenance of roads. They enable an adequate assessment of the remaining load-bearing capacity and the level of reliability of the pavement structure using non-destructive methods, at the same time reducing the financial costs.

The aim of the research presented in this paper is the experimental confirmation of the numerically defined shapes of the Strut-and-Tie models, designed according to the EN 1992-1-1 recommendations, and obtained from the software “ST method”. Three reinforced concrete deep beams with openings were tested. Each of them had the same dimensions and quality of the material characteristics. The specimens, constructed as simply supported beams, were loaded with two concentrated forces and were tested for bending until failure. Each specimen was reinforced with different reinforcement layout determined by variation parameter β, incorporated in the software “ST method”. For the determination of the Strut-and-Tie models, all of the reinforcement layouts were equally favored in the first specimen (β = 1.0 for 0°, 45°, and 90°), only the horizontal direction was favored in the second (β = 1.0 for 0°), while in the third specimen the one at the angle of 45° (β = 1.0 for 45°). Based on the results of experimental research, it was concluded that the behavior of loaded members was in agreement with the proposed shapes of the Strut-and-Tie models that were used for their design, and it was confirmed that the program “ST method” can be used for obtaining Strut–and-Tie models.

This paper presents an analysis of the stabilization of different soil types using a hydraulic binder. A study was carried out on soils that can be classified into two groups: cohesive and non-cohesive soils. Clay soils of medium and low plasticity according to the USCS classification were used as cohesive materials, while the sandy material containing dust was considered as non-cohesive material. Samples were taken from fifteen locations in Vojvodina province, Serbia. A hydraulic binder was used as a binder based on cement and lime. The amounts of the binder were estimated at 3, 5, 7, and 9%. In order to determine the basic physical and mechanical characteristics of the specimens, the following tests were performed: unconfined compressive strength after 7 and 28 days, indirect tensile strength after 7 and 28 days, as well as the California Bearing Ratio. Based on the obtained results, it can be concluded that increasing the amount of binder results in an increase in the subgrade load-bearing capacity. However, it should be emphasized that the subgrade containing non-cohesive material had a lower growth in the load-bearing capacity than those with the cohesive material.

Earlier researches have established that the measurement of pavement longitudinal roughness expressed through International Roughness Index (IRI) is one of the most important indicators for overall evaluation of road network condition....

(1) Background: The construction industry continuously seeks sustainable alternatives to traditional materials for subgrade material in pavement construction, aiming to mitigate environmental impact while maintaining performance standards. This study investigates the feasibility of incorporating phosphogypsum (PG) and contaminated sediment into subgrade materials, focusing on their physico-chemical and physico-mechanical properties. (2) Methods: The physico-chemical and physico-mechanical properties, performance, and mechanisms of solidified sediment with phosphogypsum (3% and 5% of phosphogypsum in mixture) were studied using long-term leaching tests (ANS 16.1), uniaxial compressive strength (UCS), California Bearing Ratio (CBR), X-ray fluorescence (XRF), and thermogravimetric analysis (TGA). (3) Results: Based on the pseudo-total metal content (Cr, Ni, Cu, Zn, As, Cd, Pb), the sediment is classified as third- and fourth-class, indicating it is polluted and requires treatment before disposal in the environment. To assess the long-term behavior of the sediment treated with phosphogypsum (S/S), a semi-dynamic ANS 16.1 leaching test was performed. The results showed that the metals exhibit moderate mobility, with average diffusion coefficients (De) ranging from 10⁻⁸ cm²/s for Zn (in both mixtures) to 10⁻¹² cm²/s for Cr (in mixture F-3). The leaching index (LX) values for both mixtures were above 9 for most metals, confirming their suitability for “controlled” use. Granulometric analysis indicated a predominance of fine particles, which enhances the material’s plasticity and mechanical properties. Atterberg consistency tests showed that increasing phosphogypsum content improved both the Liquid Limit and Plastic Index. However, UCS tests indicated that neither the 3% nor 5% phosphogypsum mixtures met the minimum strength requirements for subgrade material. On the other hand, CBR values demonstrated promising performance, with 12.5% for the 3% phosphogypsum mixture and 22.9% for the 5% phosphogypsum mixture. Overall, phosphogypsum positively influenced the strength development of the sediment-PG mixtures, as confirmed by XRF and TGA analyses. (4) Conclusions: Environmental considerations, such as leachability of contaminants, were investigated to ensure the sustainability of the proposed subgrade materials. Leaching tests indicated minimal pollutant release, suggesting the potential for safe utilization of PG and sediment in subgrade material. This study provides valuable insights into the physico-chemical and physico-mechanical properties of pavement mixes incorporating PG and sediment, supporting the feasibility of using these alternative materials in sustainable subgrade material for pavement construction and offering a viable solution to mitigate waste generation while enhancing pavement performance.