Artificial intelligence (AI) has been increasingly applied to solve complex real-world problems. One of the most significant challenges in AI lies in selecting and fine-tuning the optimal algorithm for a given task. Automated Machine Learning (AutoML) models have emerged as a promising solution to address this challenge by systematically exploring hyperparameter spaces to identify optimal configurations efficiently. This study addresses critical gaps in the current literature by conducting a comprehensive comparative analysis of AutoML frameworks for hyperparameter optimization and evaluating the effectiveness of various explainability techniques for enhancing model interpretability. For this purpose, Random forest (RF) is selected as the base model and integrated with nine different AutoML frameworks, namely Random search (RS), Grid search (GS), Hyperopt, TPOT, Optuna, GP Minimize, Forest Minimize, GBRT Minimize, and Dummy Minimize. The study focuses on predicting the ultimate moment capacity of Ultra-High-Performance Concrete (UHPC) beams and U-shaped girders. Furthermore, the insights from SHapley Additive exPlanations (SHAP) are also compared with those derived from alternative explainability methods, including Local interpretable model-agnostic explanations (LIME), partial dependence plots (PDP), and sklearn permutation importance rankings to examine the contributions of individual parameters to the ultimate moment capacity predictions of UHPC beams using the best-performing AutoML model. The findings demonstrate that Optuna consistently outperforms its counterparts, achieving the highest predictive accuracy and the lowest computational training time. The findings also highlight SHAP’s superiority in offering detailed, consistent, and actionable insights, making it the preferred method for both global feature importance and individual feature analysis in high-stakes engineering applications.

The increasing demand for high-performance pumpable concrete in large-scale infrastructure projects necessitates optimizing workability and strength while reducing environmental impact. This research explores the rheological, workability, and mechanical behavior of pumpable concrete with fractional substitution of cement by Ground Granulated Blast Furnace Slag (GGBS), aiming to enhance sustainability and performance. A total of 30 mix designs with GGBS replacements ranging from 0% to 90% were prepared, systematically optimizing the water-binder ratio (W/B) and superplasticizer dosage to maintain constant workability (i.e., 130 ± 15 mm slump value) to achieve the required pumpability. A total of 810 samples were prepared and tested to evaluate compressive strength (450 specimens at 7, 14, 21, 28, and 56 days), splitting tensile strength (180 specimens at 28 and 56 days), and flexural strength (180 specimens at 28 and 56 days). The findings show that GGBS enhances the rheological behavior of fresh concrete by lowering both plastic viscosity and yield stress, which in turn improves its flowability and pumpability. The optimal GGBS replacement level was found to be in the range of 30%–50%, where the best balance between workability and strength development was achieved. Compressive strength tests showed that while higher GGBS levels resulted in delayed early-age strength gain, long-term strength development was significantly enhanced due to pozzolanic reactions. The splitting tensile and flexural strength results followed similar trends, demonstrating optimal performance at 40% GGBS replacement. This study confirms that the controlled use of GGBS in pumpable concrete enhances both fresh and hardened properties while promoting sustainability by reducing OPC consumption and associated carbon emissions. The findings provide valuable insights for optimizing mix designs to achieve high-performance, eco-friendly pumpable concrete suitable for modern construction applications.

An aqueduct is a bridge-like structure that supports a canal passing over a river or low ground, and it is an important part of a water conveyance system. Aqueduct piers are extremely vulnerable to damage during strong earthquakes that can result in structural collapse. Further, excessive seismic displacement will also fracture an aqueduct’s rubber water-stop and interrupt the normal service of an aqueduct after an earthquake. Therefore, improving the seismic capacity and post-earthquake resilience of aqueducts is of great importance. In this paper, a new type of self-centering seismic isolation bearing, the inclined plane guide bearing (IPGB), is proposed for the seismic design of aqueducts, and it is studied both experimentally and numerically. Firstly, a typical aqueduct project and the setting of the IPGBs are introduced. Then, the test design, test cases, and test results of shaking table tests for two different pier-height aqueducts are presented. The seismic responses of the two models are studied, and the results show that the aqueduct that used IPGBs has a smaller bearing displacement and better post-earthquake resilience. Finally, a numerical simulation method applicable to aqueducts using IPGBs is proposed, and its accuracy is verified by comparing the results of the numerical simulation and the shaking table test.

Soil stabilization using Portland cement is a widely adopted technique. Previous research has demonstrated that molasses, which contains sugars, enhances the reaction between cement and aggregates. This study investigates the impact of adding molasses to soil stabilized with Ordinary Portland Cement (OPC) on geotechnical properties. Expansive clay soil samples from Taru Jabba, District Nowshera, Pakistan, were treated with various combinations of molasses and cement. The concentrations of each stabilizer were varied at 0%, 4%, 8%, and 12% by dry weight of the soil. Additionally, the soil was treated with constant molasses contents of 4%, 8%, and 12%, while varying the cement content at 4%, 8%, and 12% by dry weight. Geotechnical tests, including Proctor compaction, Atterberg limits, Unconfined Compressive Strength (UCS), California Bearing Ratio (CBR), and swelling potential, were conducted to assess the effects of the stabilizers. The results indicated that the addition of molasses improved soil strength, mitigated shrinkage cracks, and reduced brittleness. Specifically, the CBR value increased from 3.2% in the native soil to 12.3% with 12% molasses and 12% cement. The Plasticity Index (PI) decreased from 14.23% to 8.12%, and the CBR swell value reduced from 9.66% to 3.82%. Furthermore, the UCS of the stabilized soil increased by 64.7% compared to the untreated soil after a 7 day curing period.

High damping rubber (HDR) bearings are extensively used in seismic design for bridges due to their remarkable energy dissipation capabilities, which is critical during earthquakes. A thorough assessment of crucial factors such as temperature, rate, experienced maximum amplitude, and the Mullins effect of HDR on the mechanics-based constitutive model of HDR is lacking. To address this issue, we propose a deep learning approach that integrates the Gate Recurrent Unit (GRU) and attention mechanism to identify time series characteristics from compression-shear test data of HDR specimens. It is shown that the combination of GRU and attention mechanism enables accurate prediction of the mechanical behavior of HDR specimens. Compared to the sole use of GRU, this suggested method significantly reduces model complexity and computation time while maintaining good prediction performance. Therefore, it offers a new approach to constructing the HDR constitutive model. Finally, the HDR constitutive model was used to analyze the impact of experienced maximum amplitudes and cycles on following processes. It was observed that maximum amplitudes directly influence the stress-strain relationship of HDR during subsequent processes. Consequently, a solid foundation is laid for evaluating the responses of HDR bearings under earthquakes.