Problems with inaccurate prediction of electricity generation from photovoltaic (PV) farms cause severe operational, technical, and financial risks, which seriously affect both their owners and grid operators. Proper prediction results are required for optimal planning the spinning reserve as well as managing inertia and frequency response in the case of contingency events. In this work, the impact of a number of meteorological parameters on PV electricity generation in Poland was analyzed using the Pearson coefficient. Furthermore, seven machine learning models using Lasso Regression, K–Nearest Neighbours Regression, Support Vector Regression, AdaBoosted Regression Tree, Gradient Boosted Regression Tree, Random Forest Regression, and Artificial Neural Network were developed to predict electricity generation from a 0.7 MW solar PV power plant in Poland. The models were evaluated using determination coefficient ($R^2$), the mean absolute error ($MAE$), and root mean square error ($RMSE$). It was found out that horizontal global irradiation and water saturation deficit have a strong proportional relationship with the electricity generation from PV systems. All proposed machine learning models turned out to perform well in predicting electricity generation from the analyzed PV farm. Random Forest Regression was the most reliable and accurate model, as it received the highest $R^2$ (0.94) and the lowest $MAE$ (15.12 kWh) and $RMSE$ (34.59 kWh).

Far-reaching technological progress, manufacturing, and rapidly advancing globalization dictate new conditions for the development and changes in the construction industry. Valorization of by-products and the use of secondary materials in the production of building materials have attracted a lot of attention. Silicate materials were assessed on the basis of their compressive property. An orthogonal compositional plan type 3k (with k = 2), that is, a full two-factor experiment was applied in order to carry out the compressive strength and bulk density tests. Glass sand was added to the silicate mass as a modification. The results show that the compressive strength was higher than that of traditional bricks. Scanning electron microscopy coupled with energy dispersive spectrometry SEM/EDS was used to study the microstructure, whereas the XRD analysis was applied to examine the structures. Laboratory tests were performed on samples with dimensions of 50 × 50 × 50 mm. The results show the bulk density increase to the value of 1.75 kg/dm^3, which increases the acoustic performance of the new products. The results of the modifications also indicate changes in the structure of the new bricks. The reference sample contained α-quartz, zeolite, tobermorite 9A, and calcium aluminum silicate (Ca₂Al₄Si₁₂O₃₂), whereas the samples modified with glass sand, the presence of phases such as α-cristobalite, natrolite, tobermorite 11A, gyrolite, and analcite was recorded.

This study describes the relationship between the physio-mechanical and chemical properties of sand-lime materials which have undergone hydrothermal treatment, and which were modified through the introduction of glass components (90% glass sand, GS). Process parameters such as temperature, pressure and saturation vapor pressure were found to have a significant impact on the series of chemical reactions as well as on the formation and transformation of solid hydrates. During the stirring process of sand-lime mass, the temperature of the reaction between lime and water in the presence of quartz sand (QS) was determined to be 83 °C. In the presence of glass sand, measured temperature was only 42 °C. Thermodynamic equilibrium-based modelling was applied to predict stable phase assemblages in the studied systems. It was found that compositional modification along with the application of the autoclaving process resulted in the formation of two crystalline phases: natrolite and gyrolite. Compressive strength and density were also assessed. The strength of fresh laboratory samples was found to be greater than their traditional analogues by 15 MPa. In addition to experimental characterization, sand-lime materials were also modeled using neural networks (backpropagation neural network, BPNN) which serve as a universal approximation method capable of modelling complex functions.

This paper describes the use of glass sand in the production of autoclaved bricks. Traditional autoclaved materials consist of SiO₂, CaO, and H₂O. The purpose of the tests is to analyze the possibility of using glass sand in autoclaved materials and to determine their properties and durability. Depending on the structure, building materials can have porosities ranging from 0% (glass, metals) to over 90% (thermal insulation materials such as aerated concrete). Porosity of materials is directly related to the strength of materials and their density, and further to the thermal and acoustic insulation properties of products used especially for external wall construction, i.e., bricks, concrete, and aerated concrete. This type of silicate brick is formed at a temperature of 203 °C, therefore the dominant phase forming the microstructure is tobermorite, in contrast to the C-S-H phase, which dominates in concretes and which is characterized by a larger specific surface. The nature of pores, their number, appearance and arrangement in the material can be studied using computer techniques (SEM, XRD, computed tomography, porosimetry). Computed tomography (micro-CT analysis) showed that the number of voids in the material modified by glass sand is about 20% in relation to the weight of the product. The density of the product with glass sand was determined to be 2.2 kg/dm³.