Cercospora leaf spot (CLS) of sugar beet, caused by Cercospora beticola Sacc., is a highly destructive plant disease that can reduce yields by up to 40% and significantly impair root crop quality. This study aimed to develop and validate a quantitative disease assessment method utilizing UAV-based multispectral imaging and semantic segmentation. Field trials were conducted in 2023-2024 on commercial sugar beet crops (Agrofirma Start OOO, Buzdyak District, Republic of Bashkortostan). Plots, measuring 20 × 6 rows (≈21.6 m²), included both control and artificially inoculated treatments. UAV imagery was acquired using a Geoscan ChatGPT equipped with a Pollux multispectral camera (Blue, Green, Red, Red-edge, NIR) at an altitude of approximately 30 m. A U-Net model was trained on 420 annotated image tiles (512 × 512 px), using a 6:2:2 split for training, validation, and testing. The model incorporated spectral indices (NDVI, NDRE, MCARI, NSVDI) in addition to geometric features derived from the normal vectors of a Digital Surface Model (DSM). The developed integrative algorithm achieved an overall multiclass classification accuracy of 88.6%. Specifically, an F1-score of 46.0% was obtained for the ‘infected plants’ class, outperforming Partial Least Squares Discriminant Analysis (PLS-DA) by 18.6 percentage points. F1-scores reached 92.5% for ‘Healthy vegetation’ and 68.7% for ‘Soil/Background.’ This methodology confirms the strong applicability of U-Net for the diagnostic segmentation of Cercospora outbreaks, significantly enhancing the objectivity of crop monitoring. The integration of spectral and geometric features proved crucial in improving the detection of weakly expressed disease symptoms.

The implementation of intelligent digital control systems is essential for achieving high performance in agricultural enterprises. The study applies the biomachine systems theory to livestock farm management to analyze the functional links between complex system components. The research justifies the structure and functionality of an artificial intelligence (AI) framework for managing livestock biomachine systems. In this model, the farm is represented as an undirected multigraph, where vertices represent the «Human-Machine-Animal-Product-Environment» (H-M-A-P-E) elements and edges represent their functional interconnections. The study examines localized biotechnological systems – specifically milking and primary processing, feed preparation and distribution, microclimate control, and manure removal – analyzing their functional relationships through a directed multigraph. The authors categorize AI functions within these localized systems and provide a structural-functional diagram illustrating the interaction between milking and feeding systems within the Internet of Things (IoT) framework. The direct exchange of signals between these local systems, independent of a centralized «control center» (workstation), enables autonomous functioning and effective coordinated management. The systematization of AI functions presented here facilitates the development of intelligent telecommunication systems for monitoring operators’ performance, machine efficiency, physiological condition of animals, and the overall economic and environmental sustainability of the enterprise.

The digital transformation of the agro-industrial sector within the «Industry 4.0» paradigm is impossible without the widespread adoption of artificial intelligence (AI) technologies. Despite the emergence of the «smart farming» approach and the «Agriculture 5.0» concept, the adoption of AI in agriculture remains fragmented due to methodological, technical, and organizational barriers. The study aims to review existing approaches to the intellectualization of agricultural machinery and equipment, evaluating their advantages, practical implementation, and scalability limitations. The authors conducted a bibliometric analysis and preformed terminological mapping of key concepts («automation», «digitalization», «intellectualization») across Russian and English scientific literature. Using a convergent cognitive-semantic approach, they have examined current intellectualization strategies in the agro-industrial sector. The review identified the main barriers to technology scaling, including the lack of a unified formalized approach to the implementation of intelligent systems; high initial investments, key interest rates, and tax burdens; the lack of unified data standards; the proprietary nature of software solutions from equipment manufacturers; equipment compatibility issues; import dependency; the underdevelopment of domestic IT solutions for the agro-industrial sector; and a shortage of specialists with interdisciplinary competencies. Overcoming these identified barriers will facilitate the successful digital transformation of the sector. A Gartner Hype Cycle model was developed to visualize the development stages of intellectualization technologies in the agro-industrial sector over the next 10 years, highlighting their strategic role in global food security. The study concludes that there is a need for local intellectualization of technological system elements based on agent-based modeling, along with supra-systemic solutions to integrate disparate elements into a unified control loop.

The actual service life of tractor engines of traction class 1.4 in the Tomsk region falls significantly short of the warranty period and exhibits high dispersion. Statistical analysis reveals that the mean operating time until the first overhaul does not exceed 7,000 engine hours, with a standard deviation of 1,707 hours and a coefficient of variation of 0.24. The service life of new engines until the first overhaul varies by more than a factor of 2.8. To address the challenge of predicting failure modes based on cumulative operating time, this study employs artificial neural networks (ANNs). The research objective was to train an ANN to identify the most likely cause of engine failures using durability data collected under routine operating conditions of traction class 1.4 tractor engines. The authors developed an intelligent failure diagnostics system using Python and the PyTorch framework. The Matplotlib module was used for visualization, NumPy for matrix operations, and sklearn for input data normalization. The ANN uses a fully connected (dense) architecture consisting of an input layer (one neuron), a hidden layer (10 neurons), and an output layer (four neurons). The model was trained on a dataset from 25 Minsk Motor Plant engines (type 4Ch(N) 11/12.5). Based on the “operating time” input parameter, the model generates a probability distribution across four failure categories: the crank mechanism, the lubrication system, the fuel system, and the cooling system. Initial testing yielded a prediction accuracy of 60%. Future research will focus on fine-tuning the artificial neural network by expanding the training dataset to achieve a target accuracy of 80%.

The efficiency of agricultural machinery used in the cultivation of row crops – most notably sunflower and maize – depends significantly on how well the operating parameters match the physical and dimensional characteristics of the seeds. This study aims to analyze the dimensional properties of seeds from modern sunflower and maize hybrids (varieties). The research involved measuring the primary dimensions of twelve maize hybrids and seven sunflower varieties/hybrids recommended for the Central Black Earth and North Caucasus regions of the Russian Federation, followed by statistical analysis. The findings indicate that maize seeds have average dimensions of 11.0 mm (length), 8.4 mm (width), and 5.1 mm (thickness), with inter-hybrid variability ranging between 8.1% and 9.7%. Correlation analysis revealed no significant relationship between length and width or width and thickness; however, an inverse correlation was observed between seed length and thickness. Sunflower seeds exhibited average dimensions of 11.7 mm, 6.1 mm, and 3.8 mm for length, width, and thickness, respectively, showing a direct correlation across all primary dimensions. For process modeling purposes, maize seeds can be approximated as ellipsoids of revolution with the axis of rotation corresponding to thickness, while sunflower seeds are best represented as ellipsoids rotating about their longitudinal axis. These dimensional characteristics are applicable for selecting rational parameters of seed-cleaning screens, grading machinery, indent cylinders, and the diameters of metering elements in precision seeders.

Enhancing blade durability and determining optimal sharpening angles are critical for extending the service life and increasing the efficiency of feed choppers and industrial processing machinery. This study aims to determine the optimal sharpening angle for feed chopper blades subjected to through-hardening (volumetric quenching) followed by low-temperature tempering under abrasive wear conditions. Experimental samples were fabricated from U7 steel (GOST 1435-99) with sharpening angles of 10°, 20°, and 30°. Heat treatment produced a uniform fine-needle martensite structure across the entire cross-section. The resulting hardness was 740 HV, a 2.96-fold increase over the initial microhardness of 250 HV. Microstructural analysis revealed decarburizationinduced iron oxides at depths of up to 0.079 mm; consequently, suggesting that controlled-atmosphere furnaces should be used during quenching. Wear resistance was tested over a 100-hour period using a custom-made laboratory installation with quartz sand as the abrasive medium. The initial cutting-edge radius ranged from 20 to 35 μm. Under abrasive wear, the smallest increase in edge radius (blunting) was observed in the 10° blades (120 μm), while the 30° blades showed the greatest increase (185 μm). Conversely, the 30° sharpening angle exhibited the lowest overall width wear, while the 10° angle showed the highest. For cutting root crops without impact loads, the 10° sharpening angle is optimal. Furthermore, increasing the cutting speed from 5 to 7 m/s accelerated the dulling rate by 81.5%. These findings provide a technical basis for the design and maintenance of high-efficiency feed choppers and processing equipment

Existing occupational risk assessment methodologies often fail to sufficiently account for objective factors that influence risk realization. Consequently, there is a critical need to revise the conceptual approach to assessing risks for tractor and agricultural machinery operators. The study aims to identify overlooked occupational and environmental factors to enhance the accuracy and quality of risk assessments. The methodology is based on a comprehensive synthesis of research regarding the impact of workplace conditions and human factors on safety. The study demonstrates that risk levels are significantly influenced by investments in occupational health and safety (OHS) measures, as well as the presence of environmental stressors – such as excessive noise and extreme cabin temperatures – that accelerate fatigue and impair attention and reaction speeds. Findings show that an increase in workplace temperature to 26-28°C reduces operator performance by 20-25%. Conversely, poorly regulated air conditioning (temperatures below 20°C) also increases fatigue and accident risk by 15-20%. Similarly, every 10 dB increase in noise level leads to a proportional rise in fatigue and a decline in productivity. To address these «risk intensification factors,» the authors propose the use of correction factors in hazard coefficient calculations. These factors account for the impact of environmental stressors, operator age, and other variables on fatigue. The proposed framework provides a scientific basis for refining occupational risk assessment methods and improving the reliability of safety evaluations for tractor and machinery operators.

The accuracy and reliability of measurement results for controlled parameters are essential for ensuring the quality of engine repairs. However, current standards, such as GOST 10448-2014 («Piston Internal Combustion Engines») and GOST 14846-2020 («Automobile Engines: Bench Test Methods»), do not specify requirements for the permissible error in the indirect measurement of engine power. This study aims to develop metrological recommendations to achieve specified levels of reliability for measurement data obtained during the acceptance testing of repaired engines. Using probability theory, the authors derived a formula to calculate power measurement errors and established permissible error limits for various ZMZ engine models. A comparative analysis was performed to compare these calculated limits with the actual errors observed during running-in tests on GOSNITI test benches (models KI-5274, KI-5540М, KI-5541М, KI-542М, and KI-2118А). The results indicate that the actual measurement errors remain within the calculated permissible range (derived from the GOST-based methodology). To enhance the reliability of power control, the authors developed recommendations for calculating acceptance limits with an offset relative to the nominal power value. Permissible error margins and acceptance limits were determined for various ZMZ engine models based on the required reliability levels. The application of this methodology will improve measurement quality and the overall reliability of control results during the acceptance testing of repaired engines.

As compared to conventional analog (universal) measuring instruments, digital tools possess superior metrological characteristics, reduce the likelihood of reading errors, and enable automated data registration. The study aims to evaluate the feasibility of replacing analog instruments with digital ones, targeting a reduction in the limit error by a factor of 1.7-2.0 within the context of repair enterprises. The study examined 1,000 camshafts from YaMZ-236 engines and their corresponding bushings, totaling 4,000 connections. The camshaft bearing journals were of the first undersize (repair size) Ø 0.065 0.105 53.7− mm, while the mating bushings were Ø54+0.03 mm. For the inspection of the camshaft bearing journals, a Dasqua 4105 digital micrometer was selected to replace a lever snap gauge; for the internal diameter of the bushings, a Dasqua 4511 digital three-point internal micrometer (bore gauge) was used. The analysis revealed that replacing the lever snap gauge with a digital micrometer led to a 1.58-fold reduction in the total number of incorrectly accepted and incorrectly rejected parts. Over the entire service life of the tool, the savings exceeded 2,059,000 RUB. The implementation of the digital bore gauge ensured a 2.12-fold total reduction in incorrectly accepted and rejected bushings, with savings exceeding 3,830,000 rubles over the tool’s service life. Based on the economic feasibility analysis of the transition to digital instruments, the authors established that the highest efficiency is achieved when inspecting the internal diameters of bushings with a digital bore gauge. The results demonstrate that implementing these digital tools results in a 1.36-fold reduction in annual losses for camshaft journal inspection and a 1.96-fold reduction for the inspection of bushing internal diameters.

Optical spectral photoluminescent diagnostic methods, characterized by high speed and low implementation costs, can serve as an alternative to existing methods of varietal seed identification. The study aims to develop a methodology for identifying soybean seed varieties using a spectral luminescence method. The author used a diffraction spectrofluorimetric complex to measure the spectral excitation characteristics of photoluminescence in six soybean varieties: ultra-early maturing (Puma and Sayana), early maturing (Greya and Selena), and mid-maturing (Vilana and Vilana beta). Based on the obtained dependencies, he calculated integral and statistical parameters: integral absorptive capacity, mathematical expectation, variance, skewness, and kurtosis. The photoluminescence excitation characteristics of soybean seeds were found in the range between 330 and 475 nm, with primary peaks at 392 and 420 nm. For Gaussian decomposition, the spectra were converted to the frequency domain using the inverse Fourier transform. Based the research findings, the author selected the integral absorptive capacity in the range between 350 and 396 nm as the variety identification parameter. Skewness was recognized as the most effective statistical parameter for the unambiguous identification of three soybean varieties. Gaussian decomposition parameters – variance, skewness, and frequency-domain mathematical expectation – can be applied for the unique identification of all studied varieties. The methodology for identifying soybean seed varieties includes sample preparation, irradiation in the range between 330 and 475 nm, and registration of photoluminescent signals by a radiation receiver to obtain the U(λ) dependency and, based on it, calculate the varietal identification parameters: Gaussian amplitude and variance, frequency-domain mathematical expectation, integral absorptive capacity, and skewness. Narrow-spectrum LEDs and a broad-spectrum photodiode are used to implement the developed methodology. The characteristics of the U(λ) photo-signals help determine the varietal affiliation of the seeds. The results obtained can be used to develop a portable, high-speed variety control device for both laboratory and field conditions.

A bioenergy plant (BEP) at an agricultural enterprise generates thermal and electrical energy from biomass for production needs. The author proposes an investment project for the poultry farm Agrofirma Lipetsk OOO, involving the implementation of a BEP capable of processing biological poultry waste into energy and biofertilizer. The research aims to present a promising technology for poultry waste processing and calculate the projected technical and economic indicators of the BEP. The study considers the operating principle, feasibility, and economic expediency of using a BEP capable of annually processing 15,987 tons of chicken manure and 3,590 tons of poultry carcasses. It was established that the use of a RIELA bioenergy plant with a bioreactor volume of 4,000 m³ and a storage capacity of 550 m³ will enable the disposal of biological poultry waste and the annual generation of commercial thermal energy (887 Gcal) and electrical energy (12,116 MWh) for production needs, as well as solid biofertilizer (9,964.5 tons). According to the project, the required investment is 317.9 million roubles. The projected production effect, which includes the valuation of the generated electricity, heat, and biofertilizer, is 166.7 million roubles. Annual operating costs for the BEP will amount to 40.1 million roubles. Over the 10-year calculation period, the Net Present Value (NPV) will be approximately 550 million roubles, with a Profitability Index (PI) of 2.85 and a payback period of 4.1 years. Implementing a bioenergy plant at the poultry farm will improve the environmental situation through the zero-waste processing of production waste.

The evolving energy landscape, characterized by decarbonization, the integration of renewable energy sources (RES), and the growing demand for grid reliability and energy efficiency, necessitates a profound transformation of power grids, particularly in rural areas. Conventional methods of power grid management often prove insufficient for these challenges, driving the adoption of artificial intelligence (AI) solutions. This study provides a systematic analysis of key AI applications in power grids, examining the algorithms employed and practical implementation examples from both international and domestic contexts. Drawing on a comprehensive review of literature, the authors have identified four primary application areas: load forecasting, power system and grid optimization, fault detection and equipment monitoring, and optimal resource management within power grids. Within these domains, effective algorithms include deep learning techniques such as LSTM, GRU, and CNN, along with machine learning models like SVM and various metaheuristic methods. Practical examples highlight the diverse deployment of AI, adapting to national power system specificities. For instance, countries with a high share of renewable energy sources (RES) often prioritize AI for load forecasting, while in Russia, the focus is on automating the monitoring and diagnostics of extensive rural grids through computer vision and UAVs. AI is instrumental in the design of Smart Grids, enabling the digital transformation of power infrastructure to enhance efficiency, resilience, and adaptability. However, successful AI integration requires addressing challenges related to reliability, cybersecurity, and the explainability of automation-driven decision-making.

Achieving technological leadership in the agro-industrial sector is hampered by a severe shortage of highly qualified specialists. The authors argue that a critical aspect of preparing in-demand specialists in higher education is the personal and professional development of the students achieving their personal and professional maturity. However, this aspect is not fully addressed in the current scientific literature. This study aims to justify personalized strategies for developing the personal and professional maturity of future specialists in the agroindustrial sector. To achieve this goal, the authors employed qualitative content analysis and cognitive methods. The multidimensional nature of the categories «maturity,» «personal maturity,» and «professional maturity,» along with their diverse semantic meanings, necessitated the introduction of the concept of «personal and professional maturity,» the content of which is presented from the perspective of a setting-incremental approach. Taking into account the industry-specific characteristics of the agricultural sector and the results of the qualitative analysis, the study identifies and justifies five personalized strategies for developing the personal and professional maturity of future agro-industrial specialists: the integration strategy, the flexibility strategy, the career strategy, the cooperation strategy, and the mentorship strategy. These strategies contribute both to the development of personal and professional maturity of future specialists and to the development of human resources in the agro-industrial sector – those capable of effectively responding to modern challenges and achieving technological excellence.