Improvement of the Optical Sorting Process for Small-Seed Crops
DOI:
https://doi.org/10.32515/2664-262X.2026.14(45).245-256Keywords:
small-seed crops, photo separator, feeding system, drum feeder, pneumatic-mechanical method, sorting accuracyAbstract
The purpose of the study is to provide theoretical and practical justification for the use of a pneumatic seed feeding system in optical sorters to improve the accuracy of separating small-seed crops and increase the reliability of equipment in dusty conditions.
The study is devoted to solving the problem of low accuracy of photo-separation of small seeds caused by chaotic movement of particles under the action of air flows from ejectors. The shortcomings of existing gravitational and mechanical feeding systems in dusty conditions are analyzed. A design for a pneumatic-mechanical system is proposed, in which the use of a drum with calibrated holes ensures precise positioning of the seeds, and compressed air acts as a contactless ejector. It has been established that this approach combines high precision mechanical dosing with the reliability and low seed damage characteristic of pneumatic systems. For effective photo separation of small seeds, it is advisable to use a pneumatic-mechanical feeding system, which combines the accessibility of mechanical solutions, the reliability of pneumatics, and minimal risk of seed damage.
Adjusting the distance between the holes in the feeding system drum allows you to precisely control the interval between seeds as they move through the optical camera. This provides optimal conditions for photographing grains and accurately separating defective seeds with a jet of air from the ejector. The implementation of such a system improves the quality of small seed sorting, reduces the loss of full-fledged grains, and ensures stable operation of the photo separator when processing seeds of different crops.
References
References
1. Aliiev, E. B., & Lupko, K. O. (2020). Morphological characteristics and physical and mechanical properties of seeds of small-seeded crops. Design, Production and Exploitation of Agricultural Machines, 50, 27–35 [in Ukrainian]. https://doi.org/10.32515/2414-3820.2020.50.35-41.
2. Ovsiannykova, L. K. (2017). Physico-technological properties of modern varieties of small-seeded crops. Grain products and compound feeds, 17 (1), 9–15 [in Ukrainian].
3. Spirin, A. V., Tsurkan, O. V., Tverdokhlib, I. V., & Omelianov, O. M. (2021). Ways to intensify the production of grass seeds. Vibrations in engineering and technologies, 4(103), 110–120 [in Ukrainian]. https://doi.org/10.37128/2306-8744-2021-4-12.
4. Bakum, М., Krekot, М., Abduev, М., Mikhailov, А., Maiboroda, М., Chalaya, О., Bezpalko, В., et al. (2021). Study of the efficiency of a pneumatic separator with an inclined channel on the preparation of safflor seed material. Bulletin of Lviv National Environmental University. Series Agroengineering Research, 25, 28–35 [in Ukrainian]. https://doi.org/10.31734/agroengineering2021.25.028.
5. Stepanenko, S. P., & Nykyforov, A. O. Research on impact of alternating air flow on quality of vibro-frictional separation of fine-seed materials. (2024). Technical service of agriculture, forestry and transport, 24, 52–68 [in Ukrainian]. https://doi.org/10.37700/ts.2024.24.52-68.
6. Aliiev, E. (2019). Justification of constructive-mode parameters of a photo-electron separator of sunflower seeds. Scientific Horizons, 22(5), 23–30 [in Ukrainian]. https://doi.org/10.33249/2663-2144-2019-78-5-23-30.
7. Cujbescu, D., Nenciu, F., Persu, C., Găgeanu, I., Gabriel, G., Vlăduț, N.-V., Matache, M., et al. (2023). Evaluation of an Optical Sorter Effectiveness in Separating Maize Seeds Intended for Sowing. Applied Sciences, 13(15), 8892. https://doi.org/10.3390/app13158892.
8. Sabanci, K., Kayabasi, A. & Toktas, A. (2017). Computer vision-based method for classification of wheat grains using artificial neural network. Journal of the Science of Food and Agriculture, 97, 2588–2593. https://doi.org/10.1002/jsfa.8080
9. Stepanenko S., Kuzmych A., Kharchenko S., Borys A., Dnes V., Volyk D., & Kalinichenko R. (2025). A machine vision approach for grain quality control during separation. Journal of Engineering Sciences (Ukraine), 12(1), E9–E17. https://doi.org/10.21272/jes.2025.12(1).e2.
10. Stepanenko, S., Kuzmych, A., Borys, A., Dnes, V., Kharchenko, S., Rogovskii, I., Golub, G., et al. (2025). Substantiating the YOLO11 architecture for determining the fractional composition of winter wheat grain mixtures. Eastern-European Journal of Enterprise Technologies, 4(2 (136), 81–92. https://doi.org/10.15587/1729-4061.2025.338124.
11. Mensah, B., Prasifka, J., Hulke, B., Monono, E., & Sun, X. (2025). Detection of insect-damaged sunflower seeds using near-infrared hyperspectral imaging and machine learning. Smart Agricultural Technology, 12, 101110. https://doi.org/10.1016/j.atech.2025.101110.
12. Zade, N., Gupte, A., Gupta, P., Detalle, N., Mannion, A., & Voyle, R. (2025). Spectral Feature Extraction and Ensemble Learning for Multiclass Aircraft Damage Identification. MethodsX. 15. 103625. https://doi.org/10.1016/j.mex.2025.103625.
13. Yang, M., Shi, Y., Song, Q., Wei, Z., Dun, X., Wang, Z., Cheng, X., et al. (2025). Optical sorting: past, present and future. Light: Science & Applications, 14(1), 103. https://doi.org/10.1038/s41377-024-01734-5.
14. Su, C., Hong, J., Wang, J., & Yang, Y. (2023). Quick and Accurate Counting of Rapeseed Seedling with Improved YOLOv5s and Deep-Sort Method. Phyton-International Journal of Experimental Botany, 92(9), 2611–2632. https://doi.org/10.32604/phyton.2023.029457.
15. Hardwick, J., Morgan, Z. & Hirayama, R. (2025). Acoustophoretic system for seed separation on conveyor belts. Nature Communications, 16, 6975. https://doi.org/10.1038/s41467-025-62006-3.
16. Nadolski, S., Samuels, M., Klein, B., & Hart, C.J.R. (2018). Evaluation of bulk and particle sensor-based sorting systems for the New Afton block caving operation, Minerals Engineering, 121, 169–179. https://doi.org/10.1016/j.mineng.2018.02.004.
17. Fei, Y., Li, Z., Zhu, T., Chen, Z., & Ni, C. (2025). Nondestructive detection and classification of impurities-containing seed cotton based on hyperspectral imaging and one-dimensional convolutional neural network, Digital Communications and Networks, 11(2), 308–316. https://doi.org/10.1016/j.dcan.2024.05.008.
18. Hall, W., Seagar, A. & Palmer, S. (2012). Automatic grain texture analysis using integral transforms. Holzforschung, 66(2), 231–236. https://doi.org/10.1515/HF.2011.127.
19. Latif, G., Bouchard, K., Maitre, J., Back, A., & Bédard, L. P. (2022). Deep-Learning-Based Automatic Mineral Grain Segmentation and Recognition. Minerals, 12(4), 455. https://doi.org/10.3390/min12040455
20. Lin, F., Fang, H., Liu, H., Zhang, Y., Jensen, D. J., Hovad, E. (2025). Automatic detection of grains in partially recrystallized microstructures using deep learning, Materials Characterization, 219, 114576. https://doi.org/10.1016/j.matchar.2024.114576.
21. Cetin, G., Fadali, S. (2021). Optimal resource allocation in networked control systems using viterbi algorithm. Bulletin of Electrical Engineering and Informatics, 10(3), 1524–1535. https://doi.org/10.11591/eei.v10i3.3022.
22. Steeneck, D., Eng-Larsson, F. (2018). The Baum-Welch algorithm with limiting distribution constraints. Operations Research Letters, 46 (6), 563–567. https://doi.org/10.1016/j.orl.2018.08.008.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Serhii Stepanenko
This work is licensed under a Creative Commons Attribution 4.0 International License.
