This work reports a study into the possibility of using the GoogleNet neural network in the optoelectronic channel of the Data Fusion system. The search for the most accurate algorithms for detecting and recognizing unmanned aerial vehicles (UAVs) in Data Fusion systems has been carried out. The data processing scheme was selected (merging SVF state vectors and merging MF measurements), as well as the sensors and recognition models on each channel of the system. The Data Fusion model based on the Kalman Filter was chosen, integrating radar and optoelectronic channels. Mini-radars LPI-FMCW were used as a radar channel. Evaluation of the effectiveness of the selected Data Fusion channel model in UAV detection is based on the recognition accuracy. The main study is aimed at determining the possibility of using the GoogleNet neural network in the optoelectronic channel for UAV recognition under conditions of different range classes. The neural network for the recognition of drones was developed using transfer training technology. For training, validation, and testing of the GoogleNet neural network, a database has been built, and a special application has been developed in the MATLAB environment. The capabilities of the developed neural network were studied for 5 variants of the distance to the object. The detection objects were the Inspire 2, DJI Phantom 4 Pro, DJI F450, DU 1911 UAVs, not included in the training database. The UAV recognition accuracy by the neural network was 98.13 % at a distance of up to 5 m, 94.65 % at a distance of up to 20 m, 92.47 % at a distance of up to 20 m, 90.28 % at a distance of up to 100 m, and 88.76 % at a distance of up to 200 m. The average speed of UAV recognition by this method was 0.81 s.

The rapid spread of unmanned aerial vehicles (UAVs) has created new challenges for airspace security, as drones are increasingly used for surveillance, smuggling, and potentially for attacks near critical infrastructure. A key difficulty lies in reliably distinguishing UAVs from visually similar birds in electro-optical surveillance channels, where complex backgrounds and visual noise often increase false alarms. To address this, we investigated recent YOLO architectures and developed an enhanced model named YOLOv12-ADBC, incorporating an adaptive hierarchical feature integration mechanism to strengthen multi-scale spatial fusion. This architectural refinement improves sensitivity to subtle inter-class differences between drones and birds. A dedicated dataset of 7291 images was used to train and evaluate five YOLO versions (v8–v12), together with the proposed YOLOv12-ADBC. Comparative experiments demonstrated that YOLOv12-ADBC achieved the best overall performance, with precision = 0.892, recall = 0.864, mAP50 = 0.881, mAP50–95 = 0.633, and per-class accuracy reaching 96.4% for drones and 80% for birds. In inference tests on three video sequences simulating realistic monitoring conditions, YOLOv12-ADBC consistently outperformed baselines, achieving a detection accuracy of 92.1–95.5% and confidence levels up to 88.6%, while maintaining real-time processing at 118–135 frames per second (FPS). These results demonstrate that YOLOv12-ADBC not only surpasses previous YOLO models but also offers strong potential as the optical module in multi-sensor fusion frameworks. Its integration with radar, RF, and acoustic channels is expected to further enhance system-level robustness, providing a practical pathway toward reliable UAV detection in modern airspace protection systems.

This article explores the challenges of integrating two deep learning neural networks, YOLOv5 and RT-DETR, to enhance the recognition of unmanned aerial vehicles (UAVs) within the optical-electronic channels of Sensor Fusion systems. The authors conducted an experimental study to test YOLOv5 and Faster RT-DETR in order to identify the average accuracy of UAV recognition. A dataset in the form of images of two classes of objects, UAVs, and birds, was prepared in advance. The total number of images, including augmentation, amounted to 6337. The authors implemented training, verification, and testing of the neural networks exploiting PyCharm 2024 IDE. Inference testing was conducted using six videos with UAV flights. On all test videos, RT-DETR-R50 was more accurate by an average of 18.7% in terms of average classification accuracy (Pc). In terms of operating speed, YOLOv5 was 3.4 ms more efficient. It has been established that the use of RT-DETR as the only module for UAV classification in optical-electronic detection channels is not effective due to the large volumes of calculations, which is due to the relatively large number of parameters. Based on the obtained results, an algorithm for combining two neural networks is proposed, which allows for increasing the accuracy of UAV and bird classification without significant losses in speed.

In this research, by using the finite element method, the effect of five parameters (density of a liquid mineral fertilizer (ρ), its temperature (T), tank wall thickness (L), spacing of stiffeners (K) and stiffeners height (h)) on the strength of standard polyethylene rotomolded tanks used for storage of liquid mineral fertilizers (LMF) was studied. Using the Taguchi method, it was found that these parameters are ranked according to the degree of their influence (in decreasing order) on: maximum stresses (r>L>h>T>K), maximum stresses in the tank walls (r>L>K>T>h) and deformations of the tank (for DX/DY: r>L>h>T>K and for DZ: r>L>h>K>T). Validation of the FEM strength calculations was carried out, which showed satisfactory convergence of the calculated and experimental values. Generalized equations are derived that describe the effect of all five studied parameters on P, PW and tank deformations (along the X, Y and Z axes). On the basis of the derived equations, a nomogram has been constructed, which makes it possible to choose the optimal wall thickness that will correspond to the LMF density and storage temperature. Applying the optimal wall thickness ensures a guaranteed service life of at least 50 years, minimizing the risk of environmental accidents caused by tank failure and the release of LMF and associated toxic substances into groundwater. This research offers valuable insights for designing safer and more durable storage tanks for liquid mineral fertilizers. As an optimal design of the tank for storing the most common fertilizer UAN-32 (Urea Ammonium Nitrate, 32 % nitrogen), with a density of 1.32 g/cm3 and at storage temperatures up to 40 °C, the following values of structural parameters are recommended: L=10 mm, K=38 mm, and h=4 mm

In this study, using the method of probabilistic deterministic planning (PDP), the optimum design parameters of a standard polyethylene tank used worldwide for transporting liquid mineral fertilizers (LMF) were determined. By the finite element method, the effect of the density of liquid mineral fertilizer, tank wall thickness and four motion modes (braking, acceleration, jump and landing) on the strength of standard polyethylene tanks was studied. According to the results of the study, the five most informative areas in the tank design were identified, for which the values of maximum stresses (σmax) were obtained: filler neck, pockets, walls, tap-in points and wall transition to the tank roof. As the LMF density increases, σmax in the tank increases linearly. Increasing the tank wall thickness by 1.5 times reduces the maximum stresses by 30 to 50 %. It was found that motion mode has a significant effect on the stress-strain state of a standard tank. The “heaviest” mode for a standard tank is “braking”. The “acceleration” motion mode causes σmax of no more than 60 % of the “braking” mode values. The “lightest” mode is “landing”, in which σmax is no more than 28 % relative to “braking”. Based on the PDP method, equations were derived for calculating maximum stresses depending on LMF density, wall thickness and motion mode of the tank. Nomograms were built that make it possible to quickly determine the wall thickness of a standard tank without calculations, depending on external factors. The results of the study can be used in practice when designing safe and durable tanks for transporting liquid mineral fertilizers.

This work reports a study into the possibility of using the GoogleNet neural network in the optoelectronic channel of the Data Fusion system. The search for the most accurate algorithms for detecting and recognizing unmanned aerial vehicles (UAVs) in Data Fusion systems has been carried out. The data processing scheme was selected (merging SVF state vectors and merging MF measurements), as well as the sensors and recognition models on each channel of the system. The Data Fusion model based on the Kalman Filter was chosen, integrating radar and optoelectronic channels. Mini-radars LPI-FMCW were used as a radar channel. Evaluation of the effectiveness of the selected Data Fusion channel model in UAV detection is based on the recognition accuracy. The main study is aimed at determining the possibility of using the GoogleNet neural network in the optoelectronic channel for UAV recognition under conditions of different range classes. The neural network for the recognition of drones was developed using transfer training technology. For training, validation, and testing of the GoogleNet neural network, a database has been built, and a special application has been developed in the MATLAB environment. The capabilities of the developed neural network were studied for 5 variants of the distance to the object. The detection objects were the Inspire 2, DJI Phantom 4 Pro, DJI F450, DU 1911 UAVs, not included in the training database. The UAV recognition accuracy by the neural network was 98.13 % at a distance of up to 5 m, 94.65 % at a distance of up to 20 m, 92.47 % at a distance of up to 50 m, 90.28 % at a distance of up to 100 m, and 88.76 % at a distance of up to 200 m. The average speed of UAV recognition by this method was 0.81 s.