In order to investigate the mechanism of mechanical performance enhancement and the curing mechanisms of acrylate emulsion (AE) in cement and magnesium slag (MS) composite-stabilized soil (AE-C-M), this study has conducted a comprehensive analysis of the compressive strength and microstructural characteristics of AE-C-M stabilized soil. The results show that the addition of AE significantly improves the compressive strength of the stabilized soil. When the AE content is 0.4%, the cement content is 3%, and the magnesium slag content is 3% (AE4-C3M3), the strength of the formula reaches 4.21 MPa, which meets the requirements of heavy traffic load conditions in the construction of high-speed or main road base layers. Some reactive groups on the polymer side chains (-COOH) engage in bridging with Ca2+ and RCOO− to form a chemically bonded interpenetrating network structure, thereby enabling the acrylate emulsion to enhance the water damage resistance of the specimens. The notable improvement in strength is attributed to the film-forming and solidifying actions of AE, the binding and filling effects of C-S-H gel, and the reinforcing effect of straw fibers. FT-IR and TG-DSC analysis reveals the presence of polar electrostatic interactions between AE and the soil matrix. AE enhances the bonding among soil particles and facilitates the attachment of C-S-H gel onto the surfaces of the straw fibers, thereby increasing the strength and toughness of the material. The application of MS in conjunction with straw fibers within polymer-modified stabilized soil serves to promote the recycling of waste materials, thereby providing an environmentally friendly solution for the engineering application of solid waste.
The limitations imposed by the inherent complexity of multi-component composition ratios in biological polymer-stabilized soils have hindered rapid and accurate performance prediction. To enhance the predictive accuracy for biopolymer–fiber-stabilized soils, an optimized GA-driven backpropagation (BP) neural network was developed. Three key factors influencing mechanical strength (guar gum (GG), xanthan gum (XG), and polybutylene succinate (PBS)) were identified. The global optimization capability of GA was utilized to construct an integrated GA-BP model, with these factors serving as inputs and 7d compressive strength as the output. Support vector machine (SVM) was also incorporated to provide a benchmark comparison of predictive performance. Validation was performed using 80% of the dataset, with the remaining 20% used for testing. The optimal biopolymer dosage was found to be within the range of 0.5% to 1.0%, and the maximum 7d compressive strength achieved was 466.67 kPa at the 0.5% XG–0.5% GG combination, representing a 273% increase over untreated soil. The GA-BP model demonstrated superior performance in terms of prediction accuracy and stability, as indicated by an R2 of 0.887—significantly higher than those of the BP (0.714) and SVM (0.554) models. The mean squared error was substantially reduced to 1413, compared to 2130 and 3113 for BP and SVM, respectively. Although MAPE approached those of the GA-BP, the overall predictive efficacy of SVM was found to be inferior. A reliable and robust methodology for forecasting the mechanical behavior of stabilized soils has thus been provided by this model, supporting advanced applications within geotechnical engineering.
Micro-surfacing is considered as an effective and economical preventive maintenance technique for asphalt pavement. Its performance largely depends on the material compositions of emulsified asphalt binders. To overcome the deficiencies of ordinary micro-surfacing, waterborne epoxy resin emulsified asphalt (WEREA) micro-surfacing can significantly enhance its pavement performance. This work investigated the preparation of waterborne epoxy resin emulsion (WER), solidification behavior, and rheological properties of the solidified WEREA (S-WEREA) by phase inversion method, viscosity, fluorescence microscopy (FM), Fourier-transform infrared (FTIR), and dynamic shear rheometer (DSR) tests, respectively. The results indicated that the optimal preparation conditions of WER were determined as SDS:Span-80 = 5:13 (HLB value 14.2), a 12% emulsifier dosage, a 4712 s−1 shear rate, and a 60 °C preparation temperature, based on the evaluation of laser particle size for all specimens. The viscosity, FM, and FTIR tests exhibited that a strong chemical reaction occurred between epoxy resin and curing agent to form abundant crosslinked structures and new functional groups, contributing to improving the high temperature stability of S-WEREA. Dynamic shear rheometer (DSR) tests, including frequency sweep, multiple stress creep and recovery (MSCR), and linear amplitude sweep (LAS), indicated that a 15% WER content could balance the high-temperature deformation resistance and anti-fatigue performance, while excessive WER could adversely affect the low-temperature performance of S-WEREA and also lead to macroscopic phase separation at high-temperature. This study is expected to lay an experimental foundation for the wide application of WEREA in micro-surfacing.