Analysis and classification of cleaning systems for visual sensors in agricultural machinery

Ihor Osadchyi
Received: 14.01.2026 Revised: 23.04.2026 Accepted: 27.05.2026 Published: 29.05.2026
Retrieved from Vol. 29, No. 2, 2026 Pages: 59-70
Download article Read article

Abstract

This study aimed to examine and categorise several different cleaning system options for sensor units on agricultural machinery in order to determine how their performance impacts the potential for application in field operations. The research considers the degree of impact of different types of impurities on the efficiency of cleaning system operation (dust, dirt, crop residues and others, associated with the use of machines and equipment). The authors used monographic and abstract‑logical research methods to consolidate information on scientific publications about the technical solutions that had already been tried out in experimental setups and practice. The classification includes 4 types of the air pattern and has determined the main characteristics of cleaning systems in this mode. Two design configurations were considered in the description of structural implementation: integrated and external systems. The review results demonstrated the advantages of the integrated configuration due to its protection from external influences and maximum compactness. The operation of cleaning systems was divided into modes with constant and variable pulse duration. The efficiency analysis has shown that all types of modes have different performance depending on the type of pollution. In general, pulsed cleaning modes show better results for dry contamination, and cleaning modes with continuous water supply show higher efficiency in the case of wet contamination. The article also considers combined air-liquid cleaning systems, describes their design and the principle of operation. The study showed that air-based cleaning systems are integrated into machinery more effectively and can utilise existing components already incorporated by engineers for other functions, thereby making such solutions more economically efficient. Depending on the type of contamination, the air-blowing system can readily adjust the operating mode of the airflow to ensure maximum cleaning efficiency. The obtained results may be applied in the development and modernisation of sensor cleaning systems for modern agricultural machinery equipped with automatic and autonomous control elements. Based on scientific findings and independent experimental observations, the study examined which types of cleaning systems may be relevant during the operation of radar sensors in the field and determined the influence of contamination on guidance quality and the overall stability of system performance

Keywords

precision agriculture; radars; contamination; pneumatic system; self-propelled machinery; auto-steering system

  1. Aarif, M.K.O., Alam, A., & Hotak, Y. (2025). Smart sensor technologies shaping the future of precision agriculture: Recent advances and future outlooks. Journal of Sensors, 1, article number 2460098. doi: 10.1155/js/2460098.
  2. Acuity Laser. (2025). Cleaning and maintaining laser sensors in dusty environments. Retrieved from https://www.acuitylaser.com.
  3. Adamchuk, V.V., Perepelytsia, N.M., & Hrytsyshyn, M.I. (2026). Intellectual agriculture – a determinant of innovative development of technical support of agricultural production. Bulletin of Agricultural Science, 2(875), 42-51. doi: 10.31073/agrovisnyk202602-05.
  4. Artyukh, O., Ruban, D., Tarasenko, O., Petriuk, Yu., & Ruban, H. (2025). Unmanned transport. Modern technologies, challenges, and prospects. Science and Technology Today, 5(46), 1159-1198. doi: 10.52058/2786-6025-2025-5(46)-1159-1198.
  5. Ascencione. (2024). 2025 vision sensor lens cleaning: Enabling undefeatable autonomous vehicles with essential lens maintenance. Retrieved from https://ascencione.com.
  6. Babiy, L., Yurkiv, M., Chetverikov, B., & Burshtynska, H. (2026). Accuracy of GPS and RTK navigation and their impact on reducing overlaps and losses during field work. Precision Farming, 1(2), 25-34. doi: 10.23939/pa2025.02.025.
  7. Debnath, S., Paul, M., & Debnath, T. (2023). Applications of LiDAR in agriculture and future research directions. Journal of Imaging, 9(3), article number 57. doi: 10.3390/jimaging9030057.
  8. Fan, X. (2020). Discuss and provide examples for the PWM Process. In Proceedings of the 5th international workshop on materials engineering and computer sciences (IWMECS). doi: 10.25236/iwmecs.2020.011. London: Francis Academic Press.
  9. Karim, R., Reza, N., Jin, H., Haque, A., Lee, K.-H., Sung, J., & Chung, S.-O. (2024). Application of LiDAR Sensors for crop and working environment recognition in agriculture: A review. Remote Sensing, 16(24), article number 4623. doi: 10.3390/rs16244623.
  10. Komesker, M., Meltebrink, C., Ebenhöch, S., Zahner, Y., Vlasic, M., & Stiene, S. (2024). Validation scores to evaluate the detection capability of sensor systems used for autonomous machines in outdoor environments. Electronics, 13(12), article number 2396. doi: 10.3390/electronics13122396.
  11. Lechler. (n.d.). Nozzle spray patterns and classification. Retrieved from https://www.lechlerusa.com.
  12. Liu, Q., Yu, R., Suo, H., Cai, Y., Chen, L., & Jiang, H. (2025). Autonomous driving in agricultural machinery: Advancing the frontier of precision agriculture. Actuators, 14(9), article number 464. doi: 10.3390/act14090464.
  13. Market Research Future. (2024). Automotive sensor cleaning system market. Retrieved from https://www.marketresearchfuture.com.
  14. Matos, F., Bernardino, J., Durães, J., & Cunha, J. (2024). A survey on sensor failures in autonomous vehicles: Challenges and solutions. Sensors, 24(16), article number 5108. doi: 10.3390/s24165108.
  15. Nikoliuk, O., Pyvovar, P., Nazarkina, R., Stolnikovych, G., & Bohonos, M. (2024). Dynamics of the land fund: How land resources of Ukraine have changed after February 24, 2022. Retrieved from https://kse.ua.
  16. Osadchyi, I. (2025). Investigation of pneumatic cleaning system effectiveness for radar navigation sensors on self-propelled sprayers in field conditions. Technology, Energy, Agriculture Transport AIC, 3(130), 89-98. doi: 10.37128/2520-6168-2025-3.
  17. PatentScope. (n.d.a). WO2016045828 – device for protection of an optical sensor. Retrieved from https://patentscope.wipo.int.
  18. PatentScope. (n.d.b). WO2018130610 – camera device for a motor vehicle with a cleaning device for providing the air stream, camera system as well as motor vehicle. Retrieved from https://patentscope.wipo.int.
  19. Qian, R., Tan, R.T., Yang, W., Su, J., & Liu, J. (2018). Attentive generative adversarial network for raindrop removal from a single image. arXiv. doi: 10.48550/arXiv.1711.10098.
  20. Raven Industries Manual. (n.d.). Radar row guidance and air knife kit for AGCO/ Fendt RoGator 900 with Factory VSN .Retrieved from https://files.coakleytech.com.
  21. Sanders, G., & Keeping, A.V. (2024). I can see clearly now: Keeping AV sensors clean in inclement conditions. Retrieved from https://www.wardsauto.com.
  22. Schafer Technologies. (n.d.). Retrieved from https://www.schaeffler.com.
  23. Shi, J., Bai, Y., Diao, Z., Zhou, J., Yao, X., & Zhang, B. (2023). Row detection-based navigation and guidance for agricultural robots and autonomous vehicles in row-crop fields: Methods and applications. Agronomy, 13(7), article number 1780. doi: 10.3390/agronomy13071780.
  24. Solero Technologies. (n.d.). Electromagnetic 3/2-way valve for ADAS sensor cleaning systems. Retrieved from https://solerotechnologies.com.
  25. Son, S., Lee, W., Jung, H., Lee, J., Kim, C., Lee, H., Cho, S., Jang, J., Lee, M., & Ryu, H.-C. (2023). Experimental analysis of various blockage performance for LiDAR sensor cleaning evaluation. Sensors, 23(5), article number 2752. doi: 10.3390/s23052752.
  26. Son, S., Lee, W., Lee, J., Lee, J., Lee, H., Jang, J., Cha, H., Bae, S., & Ryu, H.-C. (2024). Examining the optimization of spray cleaning performance for LiDAR sensor. Applied Sciences, 14(18), article number 8340. doi: 10.3390/app14188340.
  27. The Spray Nozzle People. (n.d.). Guide to spray properties: Fluid distribution. Retrieved from https://www.spray-nozzle.co.uk.
  28. Valeo. (2024). LiDAR cleaning: Sensor cleaning system. Retrieved from https://www.valeo.com.
  29. Vargas, J., Alsweiss, S., Toker, O., Razdan, R., & Santos, J. (2021). An overview of autonomous vehicles sensors and their vulnerability to weather conditions. Sensors, 21(16), article number 5397. doi: 10.3390/s21165397.
  30. Vitesco Technologies. (2024). Advanced sensor cleaning system. Retrieved from https://www.vitesco-technologies.com.
  31. XenomatiX. (2022). Sensor cleaning. Retrieved from https://xenomatix.com.
Osadchyi, I. (2026). Analysis and classification of cleaning systems for visual sensors in agricultural machinery. Scientific Horizons, 29(2), 59-70. https://doi.org/10.48077/scihor2.2026.59