Waste glass (WG) is unsustainable due to its nonbiodegradable property. However, its main ingredient is silicon dioxide, which can be utilised as a supplementary cementitious material. Before reusing WG, the flexural strength (FS) and alkali–silica reaction (ASR) expansion of WG concrete are two essential properties that must be investigated. This study produced mortar containing activated glass powder using mechanical, chemical, and mechanical–chemical (combined) approaches. The results showed that mortar containing 30% WG powder using the combined method was optimal for improving the FS and mitigating the ASR expansion. The microstructure analysis was implemented to explore the activation effect on the glass powder and mortar. Moreover, a random forest (RF) model was proposed with hyperparameters tuned by beetle antennae search (BAS), aiming at predicting FS and ASR expansion precisely. A large database was established from the experimental results based on 549 samples prepared for the FS test and 183 samples produced for the expansion test. The BAS-RF model presented high correlation coefficients for both FS (0.9545) and ASR (0.9416) data sets, showing much higher accuracy than multiple linear regression and logistic regression. Finally, a sensitivity analysis was conducted to rank the variables based on importance. Apart from the curing time, the particle granularity and content of WG were demonstrated to be the most sensitive variable for FS and expansion, respectively.

High-strength concrete (HSC) is a functional material possessing superior mechanical performance and considerable durability, which has been widely used in long-span bridges and high-rise buildings. Unconfined compressive strength (UCS) is one of the most crucial parameters for evaluating HSC performance. Previously, the mix design of HSC is based on the laboratory test results which is time and money consuming. Nowadays, the UCS can be predicted based on the existing database to guide the mix design with the development of machine learning (ML) such as back-propagation neural network (BPNN). However, the BPNN’s hyperparameters (the number of hidden layers, the number of neurons in each layer), which is commonly adjusted by the traditional trial and error method, usually influence the prediction accuracy. Therefore, in this study, BPNN is utilised to predict the UCS of HSC with the hyperparameters tuned by a bio-inspired beetle antennae search (BAS) algorithm. The database is established based on the results of 324 HSC samples from previous literature. The established BAS-BPNN model possesses excellent prediction reliability and accuracy as shown in the high correlation coefficient (R = 0.9893) and low Root-mean-square error (RMSE = 1.5158 MPa). By introducing the BAS algorithm, the prediction process can be totally automatical since the optimal hyperparameters of BPNN are obtained automatically. The established BPNN model has the benefit of being applied in practice to support the HSC mix design. In addition, sensitivity analysis is conducted to investigate the significance of input variables. Cement content is proved to influence the UCS most significantly while superplasticizer content has the least significance. However, owing to the dataset limitation and limited performance of ML models which affect the UCS prediction accuracy, further data collection and model update must be implemented.

Construction and demolition (C&D) waste has become a research hotspot due to the need for environmental sustainability and strength enhancement of cementitious materials. However, wider applications of C&D waste are limited, as its non-homogeneous surface nature limits its workability. This research evaluated the feasible utilization of C&D waste as aggregates in polypropylene-fiber-reinforced cement-stabilized soil (CSS) under sulfate-alkali activation. CSS specimens incorporated Portland cement and C&D waste in 10%, 20%, and 30% proportions. Also, polypropylene fiber after alkali activation by sodium sulfate (at 0.2%, 0.4%, and 0.8% dosing level) was defined as 1%, 2%, and 4%. Strength enhancement was examined through unconfined compressive strength (UCS) and flexural strength tests at 7, 14 and 28 days. Test results indicated that mechanical properties showed significant improvement with increasing levels of Portland cement and sodium sulfate, while the improvement dropped after excessive addition of C&D waste and polypropylene fiber. Optimal proportioning was determined as 30%, 4%, 20%, and 0.8% for Portland cement, polypropylene fiber, C&D waste, and sodium sulfate, respectively. Scanning electron microscope (SEM) analysis attributed the enhancement to hydration product (ettringite) formation, bridging effect and increased particle friction. Additionally, the decrease in amplification was ascribed to the destruction of interface transition-zone (ITZ) strength, resulting in premature failure.

The geographical distribution of discontinuous graded soil-rock mixtures is extensive，and these materials are commonly used as backfill materials in subgrade and slope engineering. The discontinuous grading effect on their shear mechanical properties is a critical factor influencing compaction quality control. This study proposes a discontinuity indexDcthat effectively quantifies the discontinuous grading characteristics of soil-rock mixtures. Large-scale triaxial standard specimens of soil-rock mixtures with different discontinuity indices were prepared，and triaxial shear tests were conducted using the DJSZ–150 large-scale triaxial testing apparatus. The influence ofDcand confining pressureσ3on the strength and deformation characteristics of soil-rock mixtures was analyzed. Subsequently，intrinsic relationships between the parameters of the composite power-exponential model and the deviatoric stress strength，Dcandσ3were investigated，leading to the development of the CPE model，which accounts for the effects of varying interrupted grain fractions and stress states. Finally，the impact of changes in discontinuous particle size fractions on the mesoscopic structural characteristics of soil-rock mixtures was explored，elucidating the discontinuous gradation effect on their shear mechanical properties. The results indicate that under triaxial compression，discontinuous graded soil-rock mixtures typically exhibit strain hardening characteristics. The deviatoric stress strength increases with the increase inσ3，while the internal friction angle initially increases and then decreases with the increase inDc. In contrast，the cohesion exhibits an opposite trend. The parameters k，b，and n showing linear relationships with theσ3. Both k and n show a linear relationship with theDc，while b follows a quadratic function relationship withDc. The improved CPE model not only accurately predicts the strength and deformation characteristics of soil-rock mixtures，but also effectively reflects the influence of discontinuous grading features and stress state on their deformational mechanical behavior of soil-rock mixtures. Different discontinuous particle groups constitute distinct mesostructural characteristics of soil-rock mixtures. Under axial compression loading，an increase in the content of the largest particle group enhances the overall deformational mechanical properties of the soil-rock mixture. However，excessive amounts of large particles can increase the voids between coarse particles，leading to an initial increase in deviatoric stress strength followed by a decrease.

This study investigates the thermo-mechanical response of geocell-reinforced concrete pavements through scaled model tests and three-dimensional finite element analyses. Static, thermal, traffic, and coupled temperature–loading tests were conducted to clarify the deformation evolution, strain distribution, and damage-related response of the reinforced structure. The results show that, under static loading, pavement settlement evolves through three stages, namely initial compaction, plastic development, and stable strengthening, indicating progressive mobilization of geocell confinement. Under thermal loading, slab strain exhibits pronounced spatial and temporal non-uniformity, and the slab center is identified as the thermally sensitive zone. Under coupled temperature–loading conditions, both strain and settlement show a non-monotonic response near 1.1–1.3 kN, suggesting a potential damage-initiation range. Post-test crack observations further provide direct qualitative evidence that local cracking damage occurred in the slab under representative loading conditions. Under traffic loading, permanent deformation accumulates with load repetitions and is highly sensitive to load amplitude, indicating a load-sensitive transition in cumulative deformation behavior rather than a definitive fatigue threshold. Numerical results further show that geocell reinforcement reduces central settlement by 17.4% relative to plain concrete pavement and by 7.6% relative to doweled pavement, while producing a smoother deflection basin and a more uniform stress distribution. Parametric analyses indicate that the optimum geocell height is approximately one-third of the slab thickness; beyond this range, the marginal reinforcement benefit decreases. Overall, the results demonstrate that geocell reinforcement can effectively improve load transfer, deformation compatibility, and thermo-mechanical stability of concrete pavements under the investigated conditions.

Aiming at the problem that it is difficult to consider the prediction of foundation settlement in the case of multi-parameter coupling effect by theoretical formulas and numerical analysis, the fireworks algorithm with gravitational search operator (FAGSO) is introduced into the BP neural network model, and the FAGSO algorithm aims to enhance the neural network’s weight and threshold adjustment process; so, a new soft ground settlement prediction model was developed which uses a fireworks algorithm integrated with a gravitational search operator to optimize a BP neural network (referred to as FAGSO-BP). The FAGSO-BP neural network forecasting model is used to predict the soft foundation settlement of Hunan Wuyi Expressway Project. In the soft foundation settlement prediction analysis of Hunan Wuyi Expressway Project, the average relative error of the FAGSO-BP neural network test set was 6.06%, with an RMSE of 1.6, an MAE of 1.2, a MAPE of 0.12% and an MSE of 2.56, which compared to the traditional BP, GA-BP and FWA-BP neural models, had smaller error and higher model stability.