This study investigates the viability of industrial hempseed oil as a sustainable extender oil in rubber compounding, addressing the urgent demand for alternatives to petroleum-based oils due to regulatory pressures on polycyclic aromatic hydrocarbons (PAH). We employed automated neural networks to analyze the physical and mechanical properties of rubber composites containing industrial hempseed oil, comparing them with six vegetable oils and three petroleum-based oils at extender oil concentrations from 0 to 30 phr. The results revealed that compounds with 20 phr of industrial hempseed oil and raw soybean oil exhibited the highest cure rate index values of 64.32 1/min. Rubber samples with industrial hempseed oil showed a significant 18% reduction in hardness compared to conventional oils, with the softest rubber measuring 40.5 Shore A hardness at 30 phr. Additionally, energy consumption during mixing was decreased by up to 12% for vegetable oil samples compared to mineral oils, enhancing processing efficiency. The neural network approach yielded more accurate predictions of the cure rate index, Shore A hardness, and power consumption during rubber mixing, with a validation performance exceeding 99.2%. Sensitivity analysis identified key factors, including oil content and surface tension, influencing rubber hardness. Overall, this study underscores the potential of industrial hempseed oil as an effective, eco-friendly substitute for conventional mineral oils, contributing to more sustainable practices in the rubber industry.

Undesirable water-in-crude oil emulsions in the oil and gas industry can lead to several issues, including equipment corrosion, high-pressure drops in pipelines, high pumping costs, and increased total production costs. These emulsions are commonly treated with surface-active chemicals called demulsifiers, which can break an oil–water interface and enhance phase separation. This study introduces a novel approach based on neural networks to estimate demulsification efficiency and to aid in the selection of demulsifiers under field conditions. The influence of various types of demulsifiers, demulsifier concentration, time required for demulsification, temperature and asphaltene content on the demulsification efficiency is analyzed. To improve model accuracy, a modified full-scale factorial design of experiments and the comparison of response surface method with multilayer perception neural networks were conducted. The results demonstrated the advantages of using neural networks over the response surface methodology such as a reduced settling time in separators, an improved crude oil dehydration and processing capacity, and a lower consumption of energy and utilities. The findings may enhance processing conditions and identify regions of higher demulsification efficiency. The neural network approach provided a more accurate prediction of maximum of demulsification efficiency compared to the response surface methodology. The automated multilayer perceptron neural network, with an architecture consisting of 3 input layers, 14 hidden layers, and 1 output layer, demonstrated the highest validation performance R² of 0.991932 by utilizing a logistic output activation function and a hyperbolic tangent activation function for the hidden layers. The identification of shifted optimal values of time required from demulsification, demulsifier concentration, and asphaltene content along with sensitivity analysis confirmed advantages of automated neural networks over conventional methods.

Zeolites, known for their unique structural and catalytic properties, are added to the natural rubber matrix to investigate their influence on the vulcanization process and the resultant properties of composites. The natural rubber-based composites were masticated with 4A synthetic zeolite (0, 5, 10, 15, 20, and 30 phr). The curing of the rubber compounds was monitored on a moving die rheometer at 150 °C. The isothermal DSC method was also used to study the curing process at 150 °C, 160 °C, and 170 °C. Based on the obtained results, it is assumed that there is an interaction between the components of the curing system and the surface of the zeolite particle, and that is why the vulcanization reaction starts earlier with an increase in zeolite in the rubber mixture. This underscores the significant role of zeolite in accelerating the curing reaction of natural rubber-based compounds. The composites were vulcanized in a press at 150 °C for 15 min. The chemical structure was analyzed using FTIR, and the sample morphology was examined using SEM. The degree of swelling in toluene and distilled water was determined. The tensile strength values, modulus of elasticity at 100% and 300% elongation, and elongation at break were measured using a universal testing machine. Hardness was assessed according to the Shore A scale. With a small addition of zeolite (up to 10 phr), there is no significant change in the tensile strength values. However, adding a considerable amount of zeolite to a natural rubber matrix results in a deterioration of the tested mechanical properties. It can be assumed that with large proportions of zeolite 4A MS in the composites, the mechanical properties deteriorated due to increased porosity. The amount of added zeolite affects the initial stages of thermal decomposition of the examined samples and the rest after the analysis at a temperature of 500 °C.

Good selection of natural rubber compounds is substantial in rubber industry. Behavior of products based on natural rubber is determined by rubber blending components, especially nature of process oil and concentration of reinforcing fillers. Rubber process oil main purpose is to improve dispersibility of fillers and reduce the viscosity of the rubber compound, therefore enable better processing. Mineral oils are mostly used process oils in natural rubber compounding, but, due to their toxicity and new requirements for preservation of the environment, more and more well-known manufacturers have turned to the use of environmentally friendly process oils. In this study, influence of the hempseed oil as process oil on the products properties in natural rubber compounding was investigated. Properties of hempseed oil as process oil were experimentally determined or calculated. Blending of natural rubber was performed in a laboratory by internal batch mixer, at the constant temperature of 90°C and a rotor speed of 60 rpm. Main rubber properties such as hardness, tensile strength, elongation at break, modulus at 100 and 300% elongation, and rheological properties were determined. Also, voltage and amperage were experimentally measured for calculating power consumption during effective mixing phase in rubber blending.

The northern province of Vojvodina in the Republic of Serbia has significant but underutilized geothermal resources. This study compiles a dataset of 78 hydrothermal boreholes, utilizing geospatial interpolation, principal component analysis (PCA) and robust principal component analysis to characterize multivariate patterns among geothermal resources and support preliminary site prioritization. Six borehole attributes—depth, temperature, flow rate, thermal power, mineralization, and salinity—were analyzed using collected data. The first two principal components account for 80% of the total variance: PC1 is influenced by temperature, depth, and thermal power, while PC2 reflects flow rate, mineralization, and salinity. Robust PCA based on minimum covariance determinant (MCD) helps reduce the effects of outliers, allowing for a more accurate classification of boreholes. Summary statistics indicate a mean depth of about 897 m, a mean temperature of approximately 44 °C, a mean flow rate of 8.8 dm³/s, and a mean thermal power of 1.0 MWt, with only 11 boreholes currently operational. Several boreholes exhibit elevated temperatures, flow rates, or thermal power, making them potential candidates for further evaluation for direct-use geothermal applications. These applications could include district heating, greenhouse heating, agriculture, and balneology. However, detailed geological, engineering, and economic assessments are necessary to determine the suitability for development. This framework serves as a reproducible tool for prioritizing sustainable geothermal resource exploitation in Serbia.