The processing of oil refining waste is essential from economic and environmental points of view. An important issue is the processing of soapstock to extract fatty acids, which are raw materials for various industries. The two-stage method of fatty acids obtaining from soapstock using saponification with sodium hydroxide solution and decomposition with sulfuric acid is investigated. The peculiarity of the work is the study of the influence of soapstock saponification conditions on the key efficiency indicators of fatty acid extraction: yield and neutralization number. A sample of soapstock was obtained as a result of alkaline neutralization of sunflower oil. Soapstock quality corresponds to DSTU 5033 (CAS 68952-95-4): mass fraction of total fat – 68.5 %, fatty acids – 62.6 %, neutral fat – 5.9 %. Rational saponification conditions were determined: duration (85 min.) and concentration of sodium hydroxide solution (45 %). After saponification, the soapstock was subjected to decomposition with sulfuric acid under the following conditions: temperature 90 °C, duration 40 min. Under the rational saponification conditions, the yield of fatty acids (91.8 %) and the neutralization number (187.1 mg KOH/g) were determined. The obtained fatty acids correspond to the first-grade fatty acids according to DSTU 4860 (CAS 61788-66-7). Acid indicators: mass fraction of moisture and volatile substances – 1.5 %, mass fraction of total fat – 98.0 %, cleavage depth – 69.2 % oleic acid. The use of the soapstock saponification stage before decomposition leads to an improvement in the quality indicators and an increase in the neutralization number of fatty acids by 4 %, yield – by 16.2 %. The results of the study make it possible to produce fatty acids from soapstock by two-stage technology with high yield and neutralization number

The process of sodium glyceroxide obtaining by the reaction of glycerol and sodium hydroxide in the form of an aqueous solution was investigated. Glycerol salts (metal glyceroxides) are important components in the synthesis of many compounds. Glyceroxides are used in the chemical industry, construction, medical practice, etc. Glyceroxides of alkali metals are used in the production of modified fats and biodiesel fuel. P.a.-grade glycerol (CAS Number 56-81-5) was used with a mass fraction of the main substance of 99.5 %. The parameters of sodium hydroxide (CAS Number 1310-73-2) were studied: the mass fraction of the main substance is 98.0 %, the mass fraction of sodium carbonate is 0.5%. Rational conditions for sodium glyceroxide obtaining were determined: temperature (145 °C) and concentration of sodium hydroxide solution (65 %). Under these conditions, the mass fraction of the main substance in the product was 80 %. The melting point (72 °C) and mass fraction of moisture (0.3 %) in sodium glyceroxide were determined. The catalytic activity of the product in the process of transesterification of palm olein was tested. The increase in the melting point of palm olein was 15 °C. Under similar conditions of using potassium glyceroxide with a mass fraction of the main substance of 75.77 %, the increase in the melting point is 12.1 °C. This indicates an increase in the efficiency of the transesterification process using sodium glyceroxide obtained by the developed technology. The research results make it possible to produce sodium glyceroxide under rational conditions with a high mass fraction of the main substance at enterprises that use metal glyceroxides as a production component or commercial product. The determined rational conditions will make it possible to effectively use the company's resources and predict the quality of the final product

The object of research is the process of chemical transesterification of palm olein with increased oxidation indicators in the presence of potassium glyceroxide catalyst. Transesterification is an important method of fat modification. The use of fats with increased oxidation indicators leads to the deactivation of common catalysts and a decrease in the efficiency of the process. There is a need to increase the dosage of catalysts, increase the process temperature, which negatively affects the product quality. An alternative transesterification catalyst (potassium glyceroxide) was used for the transesterification of palm olein with increased oxidation indicators. Palm olein (CAS Number 93334-39-5) with standard indicators was used: melting point 22.4 °C, peroxide value 0.8 ½ O mmol/kg, anisidine value 0.3 c. u. Olein was subjected to heating at a temperature of 90 °C in order to increase oxidation indicators, after which it underwent  transesterification. The difference in melting points of the initial and transesterified palm olein was used as a parameter of process efficiency. The maximum limit values of the oxidation indicators at which the process is effective are: peroxide value 12.7 ½ O mmol/kg, anisidine value 10.4 c. u. The difference in melting points is 12.1 °C, which indicates the efficiency of the process. The qualitative indicators of the obtained transesterified fat indicate compliance with DSTU 4336 (CAS Number 97593-46-9): melting point 34.5 °C, peroxide value 1.2 ½ O mmol/kg, anisidine value 1.0 c. u. The results of the research make it possible to use fat with increased oxidation indicators without pretreatment and predict the efficiency of transesterification depending on the fat indicators. This will increase profitability and reduce production waste.

This paper considers a model of the neural network for semantically segmenting the images of monitored objects on aerial photographs. Unmanned aerial vehicles monitor objects by analyzing (processing) aerial photographs and video streams. The results of aerial photography are processed by the operator in a manual mode; however, there are objective difficulties associated with the operator's handling a large number of aerial photographs, which is why it is advisable to automate this process. Analysis of the models showed that to perform the task of semantic segmentation of images of monitored objects on aerial photographs, the U-Net model (Germany), which is a convolutional neural network, is most suitable as a basic model. This model has been improved by using a wavelet layer and the optimal values of the model training parameters: speed (step) ‒ 0.001, the number of epochs ‒ 60, the optimization algorithm ‒ Adam. The training was conducted by a set of segmented images acquired from aerial photographs (with a resolution of 6,000×4,000 pixels) by the Image Labeler software in the mathematical programming environment MATLAB R2020b (USA). As a result, a new model for semantically segmenting the images of monitored objects on aerial photographs with the proposed name U-NetWavelet was built. The effectiveness of the improved model was investigated using an example of processing 80 aerial photographs. The accuracy, sensitivity, and segmentation error were selected as the main indicators of the model's efficiency. The use of a modified wavelet layer has made it possible to adapt the size of an aerial photograph to the parameters of the input layer of the neural network, to improve the efficiency of image segmentation in aerial photographs; the application of a convolutional neural network has allowed this process to be automatic.

The object of research is the process of fat glycerolysis in order to obtain fatty acid monoglycerides. Monoglycerides are an important component of chemical, pharmaceutical, cosmetic, and food industry products. These substances are used as emulsifiers, structure formers, complex formers, etc. The industrial production of monoglycerides involves the use of complex technologies, as well as dangerous and unstable catalysts. An urgent task is to develop new catalysts and improve technologies for monoglycerides obtaining. The technology for the synthesis of monoglycerides by the glycerolysis method, which involves the reaction of vegetable hydrogenated fat with glycerol, was studied. Potassium glyceroxide was used as a catalyst, which is effective and safe in terms of production and use. Hydrogenated unrefined fat according to DSTU 5040 (CAS Number 68334-28-1) was used. The fat has non-standard parameters: the melting point is 51 °C, the mass fraction of moisture and volatile substances is 0.3 %, the acid value is 3.2 mg KOH/g, the peroxide value is 7.6 ½ O mmol/kg. The process duration was 90 minutes, the glycerol concentration was 50 %. Rational conditions for glycerolysis were determined: catalyst concentration (1.5 %) and temperature (140 °C). Under these conditions, the product ensured the stability of the “water – sunflower oil” emulsion of 96.8 %, the concentration of monoglycerides in the system was 0.1 %. Product parameters: mass fraction of monoglycerides – 72.5 %, free glycerol – 1.5 %, acid value – 1.7 mg KOH/g. The research results make it possible to improve the glycerolysis process using a new catalyst and obtain monoglycerides with high emulsifying ability. This will increase the profitability of the enterprise and increase the volume of production of high-quality monoglycerides for various industries