The current trend in modern research revolves around novel techniques that can predict the characteristics of materials without consuming time, effort, and experimental costs. The adaptation of machine learning techniques to compute the various properties of materials is gaining more attention. This study aims to use both standalone and ensemble machine learning techniques to forecast the 28-day compressive strength of high-performance concrete. One standalone technique (support vector regression (SVR)) and two ensemble techniques (AdaBoost and random forest) were applied for this purpose. To validate the performance of each technique, coefficient of determination (R²), statistical, and k-fold cross-validation checks were used. Additionally, the contribution of input parameters towards the prediction of results was determined by applying sensitivity analysis. It was proven that all the techniques employed showed improved performance in predicting the outcomes. The random forest model was the most accurate, with an R² value of 0.93, compared to the support vector regression and AdaBoost models, with R² values of 0.83 and 0.90, respectively. In addition, statistical and k-fold cross-validation checks validated the random forest model as the best performer based on lower error values. However, the prediction performance of the support vector regression and AdaBoost models was also within an acceptable range. This shows that novel machine learning techniques can be used to predict the mechanical properties of high-performance concrete.

In a fast-growing population of the world and regarding meeting consumer’s requirements, solid waste landfills will continue receiving a substantial amount of waste. The utilization of solid waste materials in concrete has gained the attention of the researchers. Ceramic waste powder (CWP) is considered to be one of the most harmful wastes for the environment, which may cause water, soil, and air pollution. The aim of this study was comprised of two phases. Phase one was based on the characterization of CWP with respect to its composition, material testing (coarse aggregate, fine aggregate, cement,) and evaluation of concrete properties both in fresh and hardened states (slump, 28 days compressive strength, and dry density). Concrete mixes were prepared in order to evaluate the compressive strength (CS) of the control mix, with partial replacement of the cement with CWP of 10 and 20% by mass of cement and 60 prepared mixes. However, phase two was based on the application of the artificial neural network (ANN) and decision tree (DT) approaches, which were used to predict the CS of concrete. The linear coefficient correlation (R²) value from the ANN model indicates better performance of the model. Moreover, the statistical check and k-fold cross validation methods were also applied for the performance confirmation of the model. The mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) were evaluated to confirm the model’s precision.

Development and commercialization of self-healing concrete is hampered due to a lack of standardized test methods. Six inter-laboratory testing programs are being executed by the EU COST action SARCOS, each focusing on test methods for a specific self-healing technique. This paper reports on the comparison of tests for mortar and concrete specimens with polyurethane encapsulated in glass macrocapsules. First, the pre-cracking method was analysed: mortar specimens were cracked in a three-point bending test followed by an active crack width control technique to restrain the crack width up to a predefined value, while the concrete specimens were cracked in a three-point bending setup with a displacement-controlled loading system. Microscopic measurements showed that with the application of the active control technique almost all crack widths were within a narrow predefined range. Conversely, for the concrete specimens the variation on the crack width was higher. After pre-cracking, the self-healing effect was characterized via durability tests: the mortar specimens were tested in a water permeability test and the spread of the healing agent on the crack surfaces was determined, while the concrete specimens were subjected to two capillary water absorption tests, executed with a different type of waterproofing applied on the zone around the crack. The quality of the waterproofing was found to be important, as different results were obtained in each absorption test. For the permeability test, 4 out of 6 labs obtained a comparable flow rate for the reference specimens, yet all 6 labs obtained comparable sealing efficiencies, highlighting the potential for further standardization.

Self-healing concrete has the potential to optimise traditional design approaches; however, commercial uptake requires the ability to harmonize against standardized frameworks. Within EU SARCOS COST Action, different interlaboratory tests were executed on different self-healing techniques. This paper reports on the evaluation of the effectiveness of proposed experimental methodologies suited for self-healing concrete with expansive mineral additions. Concrete prisms and discs with MgO-based healing agents were produced and precracked. Water absorption and water flow tests were executed over a healing period spanning 6 months to assess the sealing efficiency, and the crack width reduction with time was monitored. High variability was reported for both reference (REF) and healing-addition (ADD) series affecting the reproducibility of cracking. However, within each lab, the crack width creation was repeatable. ADD reported larger crack widths. The latter influenced the observed healing making direct comparisons across labs prone to errors. Water absorption tests highlighted were susceptible to application errors. Concurrently, the potential of water flow tests as a facile method for assessment of healing performance was shown across all labs. Overall, the importance of repeatability and reproducibility of testing methods is highlighted in providing a sound basis for incorporation of self-healing concepts in practical applications.

The inorganic structure formed at the stage of setting of the geopolymer binder ensures high durability of the material under high-temperature conditions. However, changes in the microstructure of the material are observed. The purpose of the study was to analyze changes in the structure of geopolymer mortar after exposure to high temperatures T = 200, 400, 600, 800, and 1000 °C. Mortars with a binder based solely on fly ash (FA) and mixed in the 1:1 ratio with a binder containing fly ash and ground granulated blast-furnace slag (GGBFS) were tested. The descriptions of their microstructures were prepared based on digital microscope observations, scanning electron microscope (SEM) observations, EDS (energy dispersive spectroscopy) analysis, and mercury intrusion porosimetry (MIP) porosity test results. Changes in the material due to high temperature were observed. The differences in the microstructure of the samples are also visible in the materials that were not exposed to temperature, which was influenced by the composition of the materials. Porosity increases with increasing annealing temperature. The distribution of individual pores also changes. In both materials, the proportion of pores larger than 1000 nm increases with the temperature increase. Moreover, the number of cracks and their width also increases, reaching 20 µm in the case of GGBFS. Furthermore, the color of geopolymers has changed. The obtained results extend the current state of knowledge in the field of changes in the microstructure of geopolymers subjected to high temperature.

Polyurethane flexible joints (PUFJ) and fiber reinforced polyurethanes (FRPU) have shown great potential in the repair and protection of masonry and concrete structures. However, some questions have been raised about the durability of such solutions. The accelerated weathering and thermal stability tests carried out so far have shown the mechanical stability of PS-polyurethane in temperatures up to 100 °C and some UV-induced surface degradation. The paper reports the results from tensile tests of PS-polyurethane, used in the technologies mentioned above after being subjected to aging in different corrosive factors, a thermal analysis of unaged polymer which consists of DSC-TGA and dilatometry studies, and SEM-microscopy observation of the specimens with the indication of the elemental composition (EDS). PS-polyurethane showed low sensitivity to weathering with exposition to UV-radiation, some reactiveness to aqueous environments of a different chemical nature, and resistivity to soil and freezing in both air and water. SEM observations indicated changes in the composition of mineral fillers as the main effect of immersion in different water solutions. DSC-TGA studies showed the thermal stability of PS-polyurethane up to 200 °C and degradation proceeding in five stages. Dilatometry studies revealed that the first-degree thermal degradation over 200 °C causes a serious loss of mechanical properties.