Duc-Kien Thai

Accurately predicting the failure of reinforced concrete (RC) structures under impact loads is critical for ensuring structural safety and resilience. This study addresses this challenge by developing a robust machine learning framework to classify impact damage in RC panels into four primary modes: no damage, penetration, scabbing, and perforation, using a diverse experimental dataset of 254 tests. To solve this classification problem, a suite of ensemble models was developed and evaluated, primarily a Separate Stacking Model (SSM) architecture utilizing Deep Artificial Neural Networks (DANNs) as base learners. The framework’s performance was benchmarked against standard algorithms, and model interpretability was achieved using the SHAP (SHapley Additive exPlanations) framework. Using a rank-sum aggregation across different metrics, the SSM-AdaBoost and SSM-GaussianNB models emerged as top-performing. Furthermore, SHAP analysis identified panel geometry and impactor characteristics as the most significant physical drivers of failure. In conclusion, this work presents a highly accurate and interpretable predictive tool. The integration of optimized ensemble methods with explainability provides a reliable solution that not only enhances predictive capabilities but also offers actionable insights, contributing to the safer and more efficient design of impact-resistant structures.

Fly ash-based geopolymer concrete (FAGC) is a sustainable alternative to Portland cement concrete, offering significant reductions in carbon emissions while maintaining sufficient strength. This study proposes a three-stage framework for developing empirical formulae to accurately and interpretably predict FAGC compressive strength. In the first stage, predictive models were developed using linear regression (LR), deep neural network (DNN), and residual neural network (ResNet) approaches. Among these, the ResNet model achieved the highest predictive accuracy and effectively captured the complex nonlinear relationship between mix components, curing conditions, and compressive strength. In the second stage, global sensitivity analysis identified sodium silicate content, curing time, sodium hydroxide molarity, and water content as the most influential variables. Additionally, the interaction between fine aggregate content and curing temperature was found to have a substantial effect on strength development. In the final stage, an empirical formula was developed based on key variables and their interactions, providing a simple yet reliable tool for practical strength prediction with reduced computational requirements. The proposed framework is expected to bridge the gap between machine-learning prediction and applicability to support mix design optimisation and promote the wider adoption of sustainable geopolymer concrete in construction applications.

This study presents a closed-form solution for the dynamic response of a sandwich beam subjected to arbitrary impact loading, with a particular focus on energy harvesting from an attached piezoelectric layer. A thin piezoelectric patch is bonded to the bottom surface of the beam to convert mechanical vibrations into electrical energy. The governing equations of motion are derived using Hamilton’s principle, considering a non-symmetric sandwich cross-section and incorporating higher-order shear deformation effects. The state–space method is employed to obtain the exact dynamic response of the beam under impact excitation. The differential equations governing the output voltage and harvested power are solved analytically based on the derived response. The natural frequencies and dynamic responses are validated against classical beam theory, highlighting the significance of shear deformation. Numerical examples are provided to evaluate the generated voltage and energy harvesting efficiency. The results demonstrate the strong potential for energy harvesting from sandwich beam vibrations and elucidate the influence of impact loading conditions, distributed load amplitude, and the geometric dimensions of the beam on the harvested output.

This paper presents a numerical study of a blast-resistant design of reinforced concrete panels with a novel auxetic reinforcement layout inspired by auxetic materials, which have a negative Poisson’s ratio, i.e., shrink under compression and expand under tension. A series of two-way supported panels reinforced with re-entrant auxetic-shaped rebars were numerically tested under a TNT explosion. The high-fidelity multi-physics explicit solver of LS-DYNA was utilized to analyze the efficiency of the proposed design. Firstly, the incident pressure of a TNT explosion data and the structural response of a conventional reinforced concrete panel under a TNT explosion were successfully validated by comparing with the experimental and empirical results. Secondly, the blast-resistant capacity of the proposed model was evaluated in comparison to two different conventional designs. Moreover, a parametric study was carried out to reveal the driving parameters of the newly proposed auxetic-shaped reinforcement design. It has been proved that the proposed auxetic reinforcement layout significantly reduces the spalling radius and increases the energy absorption capacity of panels. As a result of the parametric study, the increased reinforcement volume ratio was ineffective on the spalling radius, although the cell size of auxetic reinforcement was found to be quite effective for the blast-resistant design of concrete panels. Overall, the proposed re-entrant auxetic reinforced panel performed far better than conventional designs under blast load. With the recent developments in 3D printing technology, the proposed auxetic reinforcement layout is a strong candidate to deal with blast-resistant designs of concrete panels.