Modern agriculture is becoming less dependent on traditional mechanical systems with the introduction of intelligent control systems. These systems utilize adaptive algorithms and neural networks to optimize the operation of engines, batteries, and hydraulic systems under variable loads and complex operating conditions. (Research purpose) To develop an electronic control system for a series hybrid tractor equipped with in-wheel motors. (Materials and methods) The study involved an analysis of the hybrid tractor components, including the diesel generator, traction battery, in-wheel motors, and electronic control units. The system architecture is based on microprocessor modules with feedback mechanisms (primarily using the CAN bus for data exchange). Control algorithm models were developed to ensure precise and adaptive system performance under dynamic operating conditions. (Results and discussion) The implementation of adaptive algorithms increases the efficiency of the diesel engine-generator by 42%, reduces fuel consumption by 12-15%, and decreases CO₂ emissions by 15%. The precision hydraulic and braking systems shorten the braking distance by 8–12%, while neural networks enable prediction of braking parameters with up to 95% accuracy. In addition, the upgraded battery systems maintain stable operation across a wide temperature range from 0 to 100°C, contributing to the durability and reliability of the equipment. These results confirm the potential of intelligent control systems to enhance both the efficiency and environmental sustainability of agricultural machinery. (Conclusions) The developed electronic control system optimizes the performance of the components in a series hybrid tractor with in-wheel motors, enabling adaptive and precise realtime regulation of operational parameters. It improves enhances the tractor's maneuverability and operational safety under varying field conditions. Ultimately, it leads to a longer component lifespan and improved overall productivity.

Previous studies have highlighted the potential of magnetic suspension technology for developing a levitating carousel-type milking platform based on permanent magnets and conducting its experimental evaluation. (Research purpose) This study aims to perform experimental investigations and magnetostatic calculations of a levitating “Carousel” milking platform using axially magnetized permanent magnets of rectangular shape, in accordance with the proposed technological schemes. (Materials and methods) Three configurations for placing axially magnetized neodymium permanent magnets with a cubic shape (0.01×0.01×0.01 meters) were examined for the rotating movable and stationary components of the carousel. A methodology was developed to determine the levitation and lateral air gaps between the movable and fixed magnets under both no-load and loaded conditions. (Results and discussion) An experimental scale model (1:33) of a levitating carousel-type milking platform with 24 positions was developed and tested. The most effective configuration was identified as the one in which magnets were placed directly opposite each other, with like poles facing each other and a tangential air gap of 0.004–0.002 meters, The magnets were positioned along concentric circles of equal radius on the movable and stationary parts of the platform. The levitation gap between the magnets was found to be inversely proportional to the applied load, which increased from 9 to 26.8 newtons as the radius of magnet placement decreased (from 0.1 to 0.06 meters) and the tangential gap narrowed (from 0.013-0.016 to 0.004-0.002 meters), while the levitation gap remained constant at 0.013 meters. (Conclusions) The maximum specific load-bearing capacity of the platform, taking into account the weight of the movable part (26.8 + 8 newtons), relative to the total mass of the 48 magnets (48 × 0.0074 = 0.355 kilograms), reached 98 newtons per kilogram. The value is close to the theoretical estimate of 84 newtons per kilogram, confirming the efficiency of the proposed magnetic suspension configuration.

The timely identification of diseased agricultural crops is essential for maintaining food security and reducing economic losses. The integration of machine vision with deep learning algorithms offers a more efficient and accurate method for monitoring potato crops and detecting disease symptoms than conventional visual assessment techniques. (Research purpose) This study aims to conduct a comparative analysis of one-stage and two-stage deep learning approaches for recognizing diseased and healthy potato plants. (Materials and methods) Two approaches were employed to train neural networks for the identification of diseased and healthy potato plants: a one-stage and a two-stage approach. In the one-stage approach, a single deep learning algorithm was used to simultaneously perform plant classification and localization. The two-stage approach utilized two separate algorithms: the first was responsible for detecting plant boundaries, while the second classified the identified regions as healthy or diseased. The models were trained on diverse datasets comprising images of individual potato leaves as well as entire plants. (Results and discussion) A comparative analysis was performed to evaluate the effectiveness of the one-stage and two-stage deep learning approaches in detecting diseased potato plants. For each training method, both the overall mean squared error and the coordinate-specific mean squared error were computed. Additionally, confusion matrices were generated to assess classification performance. The analysis revealed differences in accuracy and precision between the two approaches, highlighting their respective strengths and limitations. (Conclusions) The two-stage approach proved to be highly effective in distinguishing between diseased and healthy potato plants. Although it exhibited a slight reduction in coordinate-prediction accuracy – particularly when trained on both individual leaf images and whole-plant images – it offered superior classification performance. Both approaches demonstrate distinct advantages and hold significant potential for integration with modern technologies aimed at enhancing the early detection of phytopathologies in agricultural crops.

The preparation of flax retted straw is recognized as a critical stage in the flax production cycle. The performance of mechanized equipment used in this process significantly impacts the quality indicators of the resulting retted straw. (Research purpose) To analyze the dynamics of the ribbon pickup mechanism and examine the interaction between the pickup drum fingers and flax stems, taking into account the drum's design parameters and challenging harvesting conditions. (Materials and methods) Theoretical analysis of the pickup drum dynamics and the interaction between its fingers and the flax stems was conducted using Lagrange’s equations of the second kind. (Results and discussion) The study established the regularities governing the interaction between the drum fingers and a group of flax stems. A time-dependent function was derived to describe the polar radius of coupled stems, along with the conditions required for their stable transport without slipping off the fingers. It was determined that effective transport occur when the relative velocity is zero or negative and directed from the fingertip toward the center of rotation. Graphs were constructed to illustrate the effect of key parameters, such as the drum's angular velocity, deviation angle, drum radius, and the coefficient of sliding friction, on the polar radius of the stem group. (Conclusions) The analysis revealed that the polar radius is most sensitive to variations in the angular velocity of the pickup drum. The findings of this study were incorporated into the design of a pickup drum for an innovative pickup-and-turning device.

Approximately 25.5 million hectares of arable land in Russia are characterized by high acidity (pH below 5.5), which leads to up to a 30 percent reduction in the yield of major crops and a significant decline in the efficiency of mineral fertilizers. (Research purpose) To identify effective approaches for reducing soil acidity and to develop technical solutions for their practical implementation. (Materials and methods) The study analyzed the results of an experiment involving the application of coarsely ground dolomite flour to loamy chernozem soils, which demonstrated the effectiveness of this method in neutralizing soil acidity. The biochemical processes induced by liming materials and their influence on soil structure were also examined. (Results and discussion) Liming is a key method for reducing soil acidity, as it creates optimal conditions for microbial activity and enhances the efficiency of mineral fertilizer use. Moreover, it forms a geochemical barrier that prevents the leaching of mobile elements from the soil and helps reduce nutrient runoff into nearby water bodies. One of the most promising current approaches to applying lime-based soil ameliorants is the use of universal semi-trailers equipped with disc spreaders. (Conclusions) Liming increases the efficiency of mineral fertilizer use and creates favorable conditions for soil microbial activity. The efficiency of nitrogen fertilizer utilization increases by 1.4 to 2.7 times, while the uptake of phosphorus fertilizers improves by 10-15%. Coarsely ground dolomite flour has proven effective in reducing soil acidity. To deacidify the soil from moderately acidic to slightly acidic conditions (pHKCl 5.3-5.6), lime materials should be applied at a rate of 4 tons per hectare.

The advancement of seeding technologies aimed at improving sowing quality and reducing labor intensity has underscored the need to modernize selective seeders through the robotic integration. (Research purpose) To develop the design and operational algorithm of a robotic seeder for cereals, leguminous, and other crops for early-stage breeding trials, and to substantiate the seed feeding parameters during sowing. (Materials and methods) A seeder schematic was developed in accordance with current regulatory standards, and the structural and technological parameters of seed feeding using a robotic carousel-type cassette loading device were substantiated. (Results and discussion) The study identified key design features of selective seeders intended for early-stage breeding trials, specifically those incorporating a robotic carousel-type cassette loading device. An operational scheme and control algorithm for the seeder were developed, accompanied by formulas for calculating the cassette feed rate in multi-row sowing and the distributor gate opening speed during single-row sowing. A new distributor-type sowing mechanism equipped with a metering gate was proposed. A prototype seeder, SSSR 1, was constructed. Laboratory tests were conducted for six-row sowing of spring wheat, using a 15-centimeter row spacing and 20-centimeter intra-row seed spacing on a 1-meter-wide plot. (Conclusions) At a working speed of 1 kilometer per hour and intra-row seed spacing ranging from 0.1 to 0.3 meters, the cassette feed rate in multi-row sowing ranged from 0.056 to 0.168 meters per second. For single-row sowing, the distributor gate opening speed ranged from 0.028 to 0.084 meters per second. The sowing deviation was 1 percent, and the coefficient of variation for intra-row seed spacing did not exceed 5 percent. The robotic selective seeder ensures controlled sowing quality for cereals and other crops during early-stage breeding trials and seed production. The implementation of the developed seeder creates the prerequisites for increasing productivity and reducing the labor intensity of the core sowing operation.

Traditional crop monitoring methods are labor-intensive, time-consuming, and costly, while satellite imagery is constrained by dependence on weather conditions, low spatial resolution, and infrequent revisit times. In contrast, unmanned aerial vehicles (UAVs) off er rapid, high-resolution monitoring that enables the timely detection of anomalies and disruptions in crop development. (Research purpose) To develop an information model for real-time crop monitoring and decision support based on data collected by unmanned aerial vehicles (UAVs). (Materials and methods) Data obtained from UAVs support key crop management operations, including variable-rate spraying based on treatment zone maps, site-specific and zonal fertilization guided by the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Red Edge Index (NDRE), early detection of diseases and pests, and yield forecasting through statistical analysis of time series. A systematic content analysis of existing literature was conducted. Given the large volume and diversity of associated with UAV application in agriculture, particularly in cereal crop production, an appropriate information modeling approach was identified and substantiated. (Results and discussion) The advantages and limitations of UAV use were identified. It was shown that UAV-based agricultural monitoring generates vast and diverse datasets that require systematic collection, structuring, and efficient processing. The study substantiates and proposes an information model scheme for real-time crop monitoring and decision support in precision agriculture. The model includes modules for data collection and preprocessing, a computational module for mathematical analysis incorporating modeling and machine learning, and an expert system that generates recommendations for agro-technical interventions. (Conclusions) The study demonstrates that the effective integration of UAVs into crop management processes can reduce the consumption of fuel, water, fertilizers, and pesticides. Additionally, the use of UAVs increases yield potential and improves labor efficiency by enabling precise monitoring, automation, and optimization of agro-technical operations.

The paper highlights that in the context of intensifying climate change across various regions of the Russian Federation, marked by more frequent droughts, irregular precipitation, and rising temperatures, precision agriculture technologies are becoming a essential for enhancing the resilience of agricultural production. One of such technologies is fertigation, which combines irrigation with the application of fertilizers. (Research purpose) The study aims to assess the demand for fertigation technologies in the Russian agricultural sector and to analyze trends and regional characteristics of their adoption. (Materials and methods) The research draws on data from Rosstat and Roshydromet to evaluate the relationship between crop production indicators and both climatic and production conditions in the Southern, North Caucasian, and Volga Federal Districts. Trends in fertigation development in Russia were examined through patents reviews, expert evaluations, industry reports, and information from equipment manufacturers. (Results and discussion) Correlation analysis revealed a relationship between the yields of major crops and the volumes of mineral and organic fertilizers applied. However, fertilizer use efficiency varies significantly across regions due to differing local conditions. These findings were analyzed alongside the dynamics of climate risks prevalent in the selected regions. The increasing impact of adverse climatic factors in crop-specialized areas highlights the growing potential of fertigation. An analysis of the domestic fertigation technology market indicates that Russian-developed solutions are still insufficient to meet import substitution goals. A review of Russian and international patent databases also confirms a global trend toward the digitalization and automation of fertigation processes. (Conclusions) As a key component of precision agriculture, fertigation is crucial for promoting climate-resilient farming practices amid increasing aridity. Regional analysis confirms that crop yields depend on fertilizer input, while fertilizer use efficiency is influenced by both climatic and agronomic factors. To reduce import dependence and enable the development of smart fertigation systems, targeted government support is required, particularly in research and development, and in localizing technologies suited to the specific conditions of Russian agricultural regions.

Collaborative robotics in agriculture is designed to automate labor-intensive processes. In contrast to traditional autonomous systems, collaborative multi-agent robotic systems require active interaction between robots and human operators. This interaction creates the need for new methods for coordination, adaptation, and safety assurance in uncertain and dynamically changing environments. (Research purpose) The study aims to develop both theoretical and practical approaches to modeling the behavior and control of collaborative multi-agent robotic systems. The primary objective is to ensure efficient task allocation, coordinated agent behavior, and safe human-robot interaction during fruit harvesting operations. (Materials and methods) To achieve these objectives, the study employed methods from game theory, machine learning, and risk-aware control. A mathematical model was developed to describe the interactions among agents, incorporating the probabilistic nature of the environment and the involvement of a human operator. The proposed solutions were validated through a combination of numerical simulations and experimental data collected from a testbed replicating real-world agricultural scenarios. (Results and discussion) Algorithms were developed to enable coordination, adaptation, and dynamic task redistribution within the collaborative multi-agent robotic system. These algorithms demonstrated robustness against sensor inaccuracies, communication delays, and external disturbances typical of agricultural settings. Special attention was given to the system’s ability to adapt to human operator inputs, including task prioritization and context-sensitive interaction strategies. Simulation results showed enhanced system performance, characterized by more balanced task distribution among robots, reduced conflict during joint operations, and minimized idle time. Safety metrics also improved, including a reduction in collision risks and fewer incorrect responses to the presence of human operators in the work area. (Conclusions) The developed models and algorithms provide a foundation for the design of intelligent collaborative multi-agent robotic systems capable of adaptive and safe interaction in agricultural production. Their application can enhance the efficiency of automated harvesting processes while reducing reliance on manual labor.

Heat stress presents a significant challenge in livestock farming, leading to decreased productivity, impaired reproductive performance, and increased morbidity. In the context of global warming, the need for effective systems to monitor and regulate the microclimate in animal environments is becoming increasingly important. (Research purpose) The aim of this study is to develop a mathematical framework and control algorithms for a system that regulates heat stress levels based on ethological indicators. (Materials and methods) A systematic analysis was conducted on the ethological responses of cattle based on observation of 20 dairy cows. The study included the assessment of behavioral markers, physiological parameters, and microclimatic conditions. Heat stress levels were evaluated using the Temperature-Humidity Index (THI). (Results and discussion) The study identified 10 dominant behavioral markers of heat stress out of 16 possible, including elevated heart rate, reduced digestive activity, increased food selectivity, increased water intake, rapid breathing, seeking shaded areas, prolonged lying time, alterations in behavior patterns, and suppression of estrus. A mathematical framework was developed, incorporating equations for radiant energy, moisture exchange, relative humidity, air temperature, and carbon dioxide concentration. Additionally, algorithms were designed for the automated analysis of photo and video data to detect ethological indicators of stress. The proposed control system ensures accurate measurement of the Temperature-Humidity Index (±1) and achieves a 25 percent reduction in energy consumption compared to existing systems. (Conclusions) The developed system enables early detection of heat stress symptoms and contributes to mitigating their negative impact on animal productivity and welfare. By integrating microclimate data with behavioral responses, the system offers a comprehensive approach to climate control in livestock housing. The proposed mathematical framework and control algorithms can be incorporated into existing microclimate control systems, thereby improving the economic efficiency of dairy farming under changing climate conditions.

The production of drinking milk under alpine pasture conditions presents a number of specific features and challenges. The lack of specialized technical equipment for milk collection and primary processing can lead to economic losses, even in regions with ecologically clean environments and abundant natural forage resources. (Research purpose) To develop technical solutions and a closed-cycle technology for the production of drinking cow’s milk under alpine pasture conditions. (Materials and methods) The study examines the key aspects of organizing a closed-cycle milk production system that employs technical equipment for milking and primary milk processing, powered by a renewable energy source – mountain glacial rivers. The proposed technical solutions are patent-protected, and prototype units have been successfully tested on mountain farms in the Kabardino-Balkar Republic. (Results and discussion) The proposed milking equipment is specifically designed to ensure gentle handling of cows’ teats during the milking process. Freshly collected milk is transferred to a cooling unit that utilizes the natural cold of glacial mountain rivers. The initial quality of the milk met Group 1 sanitary standards, with an average fat content of 3.65% and a bacterial count of 280,700 microorganisms per milliliter. The average daily milk yield was 12.5 kilograms per cow in a herd of 100 cows. The milk is cooled within 25 minutes, and its temperature is maintained until further transportation or processing. This approach provides optimal storage conditions for milk production in mountainous regions. (Conclusions) The implementation of the proposed technical solutions significantly improves the profitability of cow milk production under alpine pasture conditions. In addition to milking and primary milk processing, the technological system also incorporates operations aimed at maintaining soil fertility and pasture sustainability through the utilization of livestock waste at the milking center.

The development of domestic technologies aimed at improving the durability of agricultural machinery, including assemblies, units, mechanisms, and individual parts, represents a key stage in agricultural production in the Russian Federation. To select wear-resistant materials for manufacturing working parts and to evaluate the effectiveness of surface strengthening technologies under specific operating conditions, it is essential to conduct accelerated service life tests using modern methods and tools. (Research purpose) To design a testing installation for accelerated corrosion-mechanical wear testing of working parts used in agricultural machinery and livestock equipment, particularly those involved in feed production and preprocessing. (Materials and methods) A methodology was developed for service life testing of cutting elements used in agricultural machinery for livestock and feed production. The study presents a kinematic diagram describing the testing installation, outlines possible mounting configurations for the working parts on the installation’s shaft, and assesses the levels of mechanical and corrosion wear experienced by the working parts under accelerated testing conditions. (Results and discussion) The control module of the installation includes an electrical schematic and a control panel which enables the regulation of shaft rotation frequency, selection of rotation direction (forward and reverse), and emergency braking. The electric motor was selected and the target shaft rotation frequency specified. Parameters of the V-belt transmission drive system, including belt type and quantity, diameters of the drive and driven pulleys, and transmission ratio, were calculated to ensure the required shaft speed. A strength calculation was performed to simulate a potential jamming scenario involving one of the middle-row knife holders and the results confirmed an adequate safety margin. (Conclusion) The proposed installation enables accelerated service life testing of working parts in machinery and equipment and allows evaluation of the effectiveness of surface hardening technologies. The testing methodology is based on determining corrosion-mechanical wear in a substrate that simulates the physicochemical properties of plant environments under specified cutting process conditions. The proposed installation complies with the required strength parameters and maintains its functionality even under potential overloads.