Advanced machine learning algorithms have the potential to be successfully applied to many areas of system modelling. In the present study, the capability of ten machine learning algorithms to predict the structural damage of an 8-storey reinforced concrete frame building subjected to single and successive ground motions is examined. From this point of view, the initial damage state of the structural system, as well as 16 well-known ground motion intensity measures, are adopted as the features of the machine-learning algorithms that aim to predict the structural damage after each seismic event. The structural analyses are performed considering both real and artificial ground motion sequences, while the structural damage is expressed in terms of two overall damage indices. The comparative study results in the most efficient damage index, as well as the most promising machine learning algorithm in predicting the structural response of a reinforced concrete building under single or multiple seismic events. Finally, the configured methodology is deployed in a user-friendly web application.

For the first time, the thermoelectric properties of cement/single-walled carbon nanotube (SWCNT) nanocomposites with over 3, 7, 14 and 28 days of hydration are reported, while a thermoelectric generator device (TEG) is fabricated utilising the material with the highest achieved power factor (PF). SWCNTs with inherent p-type semiconductor characteristics were introduced into the cementitious matrix at a water to cement (w/c) ratio of 0.5, while the Seebeck coefficient (S), electrical conductivity (σ) and PF for different SWCNT loadings were determined at different ages. The 28 day cement/SWCNT sample with 0.5 wt% loading exhibited the highest performance in terms of σ (1.59 × 10³ S m⁻¹), S (+ 1348.8 μV K⁻¹) and PF (2.89 × 10³ μW m⁻¹ K⁻²), with the PF being the highest among other carbon nanoadditive-based cement thermoelectric nanocomposites to date. The cement/SWCNT(0.5) was used for the fabrication of a thermoelectric generator (TEG) device exhibiting a maximum power output (P_max) of 5.02 μW and a power density of 5.02 mW m⁻², upon being exposed to a temperature difference (ΔT) of 50 K. Finite element (FE) simulations validated the TEG thermoelectric performance corroborating the experimental findings. The highly efficient cement/SWCNT thermoelectric nanocomposites, as well as the cement-based structural TEG device, demonstrated herein could open new avenues towards future energy efficient buildings and green construction.

Advanced machine learning algorithms, have the potential to be successfully applied to many areas of system modelling. In the present study the capability of ten machine learning algorithms in predicting the structural damage of an 8-storey reinforced concrete frame building subjected to single and successive ground motions is examined. From this point of view, the initial damage state of the structural system, as well as 16 well known ground motion intensity measures are adopted as the features of the machine-learning algorithms that aim to predict the structural damage after each seismic event. The structural analyses are performed considering both real and artificial mainshock–aftershock sequences, while the structural damage is expressed in terms of two overall damage indices. The comparative study results in the most efficient damage index, as well as the most promising machine learning algorithm in predicting the structural response of a reinforced concrete building under single or multiple seismic events. Finally, the configured methodology deployed in a user-friendly web-application.

Recently developed Machine Learning (ML) interpretability techniques have the potential to explain how predictors influence the dependent variable in high-dimensional and non-linear problems. This study investigates the application of the above methods to damage prediction during a sequence of earthquakes, emphasizing the use of techniques such as SHapley Additive exPlanations (SHAP), Partial Dependence Plots (PDPs), Local Interpretable Model-agnostic Explanations (LIME), Accumulated Local Effects (ALE), permutation and impurity-based techniques. Following previous investigations that examine the interdependence between predictors and the cumulative damage caused by a seismic sequence using classic statistical methods, the present study deploy ML interpretation techniques to deal with this multi-parametric and complex problem. The research explores the cumulative damage during seismic sequences, aiming to identify critical predictors and assess their influence on the cumulative damage. Moreover, the predictors contribution with respect to the range of final damage is evaluated. Non-linear time history analyses are applied to extract the seismic response of an eight-story Reinforced Concrete (RC) frame. The regression problem’s input variables are divided into two distinct physical classes: pre-existing damage from the initial seismic event and seismic parameters representing the intensity of the subsequent earthquake, expressed by the Park and Ang damage index ($\mathrm{D}{\mathrm{I}}_{\mathrm{P}\mathrm{A}}$) and Intensity Measures (IMs), respectively. In addition to the interpretability analysis, the study offers also a comprehensive review of ML methods, hyperparameter tuning, and ML method comparisons. A LightGBM model emerges as the most efficient, among 15 different ML methods examined. Among the 17 examined predictors, the initial damage, caused by the first shock, and the IMs of the subsequent shock—${\mathrm{I}}_{\mathrm{F}\mathrm{V}\mathrm{F}}$ and $\mathrm{S}{\mathrm{I}}_{\mathrm{H}}$—emerged as the most important ones. The novel results of this study provide useful insights in seismic design and assessment taking into account the structural performance under multiple moderate to strong earthquake events.

This study examines the seismic response of free-standing, monolithic rocking columns, taking into account different ground motion intensity measures (IMs). The primary scope of this article is to investigate the effect of the IMs, among 23 considered, on the rocking response of the examined structural system. The seismic vulnerability of the examined structural systems is based on the probabilistic seismic demand model (PSDM), in which the degree of uncertainty depends on the used IM. Thus, concluding to the most efficient one is of major importance. A performance-based analysis has been performed, using three limit states, and fragility curves are generated in terms of the most efficient univariate and bivariate IMs, considering the maximum rocking rotation normalized to the critical overturning rotation, as engineering demand parameter. Time domain analyses are numerically performed, by solving the equation of rocking motion, given a set of 35 natural seismic records. The results indicate that the velocity based as well as the frequency content IMs exhibit a strong correlation with the seismic behavior of free-standing rocking columns. Moreover, the acceleration based IMs can describe with great efficiency the rocking response only as a bivariate IM combined with the frequency content of the ground motions.