Development of elements of a digital system for identifying soil lumps and separating them from potato tubers in a potato harvester
https://doi.org/10.26897/2687-1149-2025-4-4-14
Abstract
Equipping mechanical cleaning devices with automation elements does not fully ensure the quality of cleaning commercial products from mechanical impurities. A possible solution is a system of digital identification of separated biological objects from mechanical impurities based on hyperspectral reflection. The authors carried out research to study approaches to processing hyperspectral reflection data of potato tubers and soil clods using the model of neural network YOLOv8 digital system of identification of soil clods mixed with potato tubers in a potato harvester. They have developed a structural scheme of a potato harvester with a digital system of identification of biological objects based on the hyperspectral reflection of potato tubers and recognition of soil clods in an automated mode. Potato tubers and soil clods in the images were recognized using trained models with the selection of lesion areas. The authors obtained curves of accuracy and completeness of soil clods recognition in the wavelength range between 500 and 700 nm. The optimal confidence level for neural network models was 0.28 for soil clods and 0.37 for potato tubers. The authors determined the calculation parameters of binary and multiclass classification metrics of the developed convolutional neural network models at different wavelength ranges for the classes “Potatoes”, “Soil on potatoes”, and “Soil clods”. The authors found that the highest average recognition accuracy for soil clods of mAP 0.329 and that for potato tubers of mAP 0.407 was recorded at a wavelength of 600 nm. The hyperspectral data obtained can significantly increase the accuracy of classification and recognition of diseases and lesions on tubers and can be used to identify minor changes in tuber condition. The accuracy of non-invasive recognition of soil clods and potato tubers using hyperspectral images is comparable to that of human experts (with a deviation of no more than 11.3%).
Keywords
About the Authors
A. S. DorokhovRussian Federation
Aleksei S. Dorokhov, Full Member of the Russian Academy of Sciences, DSc (Eng), Professor
109428, Moscow, 1st Institutskiy Proezd Str., 5
M. N. Erokhin
Russian Federation
Mikhail N. Erokhin, Full Member of the Russian Academy of Sciences, DSc (Eng), Professor
127434, Moscow, Timiryazevskaya Str., 49
A. V. Sibirev
Russian Federation
Aleksei V. Sibirev, DSc (Eng), Chief Research Engineer
109428, Moscow, 1st Institutskiy Proezd Str., 5
M. A. Mosyakov
Russian Federation
Maksim A. Mosyakov, CSc (Eng)
109428, Moscow, 1st Institutskiy Proezd Str., 5
D. N. Kynev
Russian Federation
Dmitriy N. Kynev, Junior Research Engineer, postgraduate student
109428, Moscow, 1st Institutskiy Proezd Str., 5
References
1. Cao T., Wang Y., Chen J. Analysis and simulation of potato combine harvesting machine. Сommunications, Signal Processing, and Systems. Lecture Notes in Electrical Engineering, 2022;879:556-563. https://doi.org/10.1007/978-981-19-0386-1_70
2. Dai F., Guo X.H., Zhao W. et al. Design and experiment of canvas belt combined operation machine for potato digging and plastic film collecting. Transactions of the Chinese Society for Agricultural Machinery. 2018;49(3):104-113. https://doi.org/10.6041/j.issn.1000-1298.2018.03.012
3. Wang L., Liu F., Wang Q. et al. Design of a spring-finger potato picker and an experimental study of its picking performance. Agriculture. 2023;13(5):945. https://doi.org/10.3390/agriculture13050945
4. Mu G., Wang W., Zhang T. et al. Design and experiment with a double-roller sweet potato vine harvester. Agriculture. 2022;12(10):1559. https://doi.org/10.3390/agriculture12101559
5. Pasaman B., Zakharchuk V. The determination of the parameters of a ploughshare-rotor potato digger. Econtechmod. An International Quarterly Journal. 2012;01(2):43-47.
6. Byshov N.V., Yakutin N.N., Koveshnikov R.Yu. et al. Modernization of digging machine KST-1.4. Bulletin of the Ryazan State Agrotechnological University named after P.A. Kostychev. 2016;2:75-78. (In Russ.)
7. Indraja D., Ajkhilesh J., Vishal P. et al. A review paper based on design and development of an onion harvesting machine. Journal of Information and Computational Science. 2020;9(12):333-337.
8. Khura T., Mani I., Srivastava A. Design and development of tractor-drawn onion (Allium cepa) harvester. Indian Journal of Agricultural Sciences. 2011;81(6):528-532.
9. El-Rahman A., Magda M. Development and performance evaluation of a simple grading machine suitable for onion sets. Journal of Soil Sciences and Agricultural Engineering. 2011;2(2):213-226. https://doi.org/10.21608/jssae.2011.55418
10. Lu K., Xie S., Gai X., Ji X. Design and experiment of toggle lever-type potato picker. Agriculture. 2024;14:826. https://doi.org/10.21608/jssae.2011.55418
11. Lü J.Q., Sun H., Dui H., Peng M.M., Yu J.Y. Design and experiment on conveyor separation device of potato digger under heavy soil condition. Transactions of the CSAM. 2017;48(11):146-155. https://doi.org/10.6041/j.issn.1000-1298.2017.11.018
12. Jia B., Sun W., Zhao Z. et al. Design and field test of a remotely controlled self-propelled potato harvester with manual sorting platform. American Journal of Potato Research. 2023;100:193-209. https://doi.org/10.1007/s12230-023-09909-3
13. Dorokhov A.S., Sibirev A.V., Aksenov A.G. The results of field tests of an onion set harvesting machine equipped with a shaker arrangement asymmetrical bar elevato. Engineering Technologies and Systems. 2020;30(1):133-148. https://doi.org/10.15507/2658-4123.030.202001.133-148
Review
For citations:
Dorokhov A.S., Erokhin M.N., Sibirev A.V., Mosyakov M.A., Kynev D.N. Development of elements of a digital system for identifying soil lumps and separating them from potato tubers in a potato harvester. Agricultural Engineering (Moscow). 2025;27(4):4-14. (In Russ.) https://doi.org/10.26897/2687-1149-2025-4-4-14