Escuela de Politécnica Superior

The resilient modulus (MR) of different pavement materials is one of the most important input parameters for the mechanistic-empirical pavement design approach. The dynamic triaxial test is the most often used method for evaluating the MR, although it is expensive, time-consuming, and requires specialized lab facilities. The purpose of this study is to establish a new model based on Long Short-Term Memory (LSTM) networks for predicting the MR of stabilized base materials with various additives during wet-dry cycles (WDC). A laboratory dataset of 704 records has been used using input parameters, including WDC, ratio of calcium oxide to silica, alumina, and ferric oxide compound, Maximum dry density to the optimal moisture content ratio (DMR), deviator stress (σd), and confining stress (σ3). The results demonstrate that the LSTM technique is very accurate, with coefficients of determination of 0.995 and 0.980 for the training and testing datasets, respectively. The LSTM model outperforms other developed models, such as support vector regression and least squares approaches, in the literature. A sensitivity analysis study has determined that the DMR parameter is the most significant factor, while the σd parameter is the least significant factor in predicting the MR of the stabilized base material under WDC. Furthermore, the SHapley Additive exPlanations approach is employed to elucidate the optimal model and examine the impact of its features on the final result.

The use of supplementary cementitious materials has been widely accepted due to increasing global carbon emissions resulting from demand and the consequent production of Portland cement. Moreover, researchers are also working on complementing the strength deficiencies of concrete; fiber reinforcement is one of those techniques. This study aims to assess the influence of recycling wheat straw ash (WSA) as cement replacement material and coir/coconut fibers (CF) as reinforcement ingredients together on the mechanical properties, permeability and embodied carbon of concrete. A total of 255 concrete samples were prepared with 1:1.5:3 mix proportions at 0.52 water-cement ratio and these all-concrete specimens were cured for 28 days. It was revealed that the addition of 10 % WSA and 2 % CF in concrete were recorded the compressive, splitting tensile and flexural strengths by 33 MPa, 3.55 MPa and 5.16 MPa which is greater than control mix concrete at 28 days respectively. Moreover, it was also observed that the permeability of concrete incorporating 4 % of coir fiber and 20 % of WSA was reduced by 63.40 % than that of the control mix after 28 days which can prevent the propagation of major and minor cracks. In addition, the embodied carbon of concrete is getting reduced when the replacement level of cement with WSA along with CF increases in concrete. Furthermore, based on the results obtained, the optimum amount of WSA was suggested to be 10 % and that of coir fiber reinforcement was suggested to be 2 % for improved results.

Researchers are investigating eco-friendly binders like coconut shell ash (CSA), metakaolin (MK), and calcined clay (CC) as supplementary cementitious materials (SCM) in high-strength concrete (HSC). Abundantly available as industrial or agricultural waste, these materials, when combined with Portland cement (PC), offer synergistic benefits. This not only improves concrete performance but also addresses waste disposal issues, presenting a sustainable and environmentally friendly solution for long-term use in HSC production. However, this study performed on fresh and mechanical characteristics of HSC blended with CSA, MK, and CCA alone and together as SCM after 28 days of curing. A total of 504 samples of standard concrete were cast and the cubical samples were tested to achieve the targeted compressive strength about 80 MPa after 28 days. The experimental results indicated that the rise in tensile, flexural and compressive strengths of 9.62%, 8.27%, and 10.71% at 9% of CSA, MK, and CC as SCM after 28 days of curing. As SCM content increases, the density, porosity and water absorption of concrete decrease. Moreover, the workability of fresh concrete is getting reduced when the concentration of SCMs increases in HSC. In addition, the concrete’s sustainability assessment revealed that employing 18% MK, CC, and CSA as SCM reduced carbon emissions by approximately 11.78%. It is suggested that using 9% CC, MK and CSA together in HSC yields the best results for practical applications in civil engineering.

A new logistic model tree (LMT) model is developed to predict slope stability status based on an updated database including 627 slope stability cases with input parameters of unit weight, cohesion, angle of internal friction, slope angle, slope height and pore pressure ratio. The performance of the LMT model was assessed using statistical metrics, including accuracy (Acc), Matthews correlation coefficient (Mcc), area under the receiver operating characteristic curve (AUC) and F-score. The analysis of the Acc together with Mcc, AUC and F-score values for the slope stability suggests that the proposed LMT achieved better prediction results (Acc = 85.6%, Mcc = 0.713, AUC = 0.907, F-score for stable state = 0.967 and F-score for failed state = 0.923) as compared to other methods previously employed in the literature. Two case studies with ten slope stability events were used to verify the proposed LMT. It was found that the prediction results are completely consistent with the actual situation at the site. Finally, risk analysis was carried out, and the result also agrees with the actual conditions. Such probability results can be incorporated into risk analysis with the corresponding failure cost assessment later.