Saint-Petersburg State University of Aerospace Instrumentation, Saint-Petersburg, Russia

V. A. Kuznetsov, Programmer, Candidate of Engineering Sciences, Associate Professor, k.avk-c@mail.ru

Bauman State University, Moscow, Russia

A. S. Ermakov, Assistant

Optimalflow Group, LLC, Moscow, Russia

D. V. Zhuravov, Design Engineer

Operation quality and performance control of industrial machines is often associated with extreme operating conditions, unavailable communication channel and impossibility of a contact or manual control. For these reasons, one of the solutions for automated non-contact control is the development or adaptation of data processing algorithms for on-board devices limited in computing resources and dimensions. During operation of excavation machines, it is critical to control the presence of teeth on the working surface of buckets to prevent abnormalities of process flows, and to abate adverse consequences of unforeseen downtimes because of a tooth loss, accidental entry of teeth in crushing machines or conveyor belts, elevated cost of repair of excavator bucket parts, and reduced efficiency of excavation. Automated monitoring of the condition and length of bucket teeth is not a critical task in the technological process, therefore, the resources for its implementation are also limited. The existing missing tooth detection solutions offer stable results for a clean bucket only, and produce a high rate of false alarms due to other features of a setting. The algorithm for automated condition monitoring and length measurement of bucket teeth is developed and tested as a part of an on-board system, and an estimation of the accuracy and speed of the algorithm is presented. Additional features for the reliability estimation of the presence and length of teeth are defined to reduce the number of false alarms, but sensitivity to artifacts of the original data is not excluded. Stable performance can be guaranteed if there are at least three visible bucket teeth without dirt and obstructions. The results obtained can be used as a part of a hardware and software system for mining excavators of the most existing models for automated condition monitoring and length measurement of bucket teeth in real time. To obtain practical significance in a technological process, the result provided by the algorithm require generalization and analysis over a certain time interval.

1. Khedkar Y., Nagpure H., Dendage P., Shinde P., Naikavade S. et al. The evaluation of forces acting on excavator bucket and its capacity. Materials Today: Proceedings. 2022. Vol. 68, Iss. 1. DOI: 10.1016/j.matpr.2022.10.013
2. Rakhutin M., Simba N., Khoroshavin S. Analysis of the dependence of the stressed state of the tracked track of a career excavator from an angle slope. Ural Mining Decade : XVIII Scientific Forum. 2020. E3S Web of Conferences. 2020. Vol. 177. ID 03015.
3. Galiev S. Zh., Uteshov E. T., Galiev D. A., Farakhov K. A. Methods and techniques for energy efficiency assessment of geotechnological facilities at opencast mines based on the in-depth analysis. Eurasian Mining. 2021. No. 1. pp. 65–69.
4. Sembakutti D., Ardian A., Kumral M., Sasmito A. P. Optimizing replacement time for mining shovel teeth using reliability analysis and Markov chain Monte Carlo simulation. International Journal of Quality & Reliability Management. 2018. Vol. 35, Iss. 10. pp. 2388–2402.
5. Knights P. F. Optimal replacement intervals for shovel dipper teeth. International Journal of Mining, Reclamation and Environment. 2009. Vol. 23, Iss. 3. pp. 157–167.
6. Luo X., Zhang H. Missing Tooth Detection with Laser Range Sensing. Proceedings of the 5^th World Congress on Intelligent Control and Automation. Hangzhou, 2004. Vol. 4. pp. 3607–3610.
7. Lim S. N., Soares J., Zhou N. Tooth Guard: A Vision System for Detecting Missing Tooth in Rope Mine Shovel. 2016 IEEE Winter Conference on Applications of Computer Vision. New York, 2016. DOI: 10.1109/WACV.2016.7477594
8. Liu X., Qi X., Jiang Y. Electric Shovel Teeth Missing Detection Method Based on Deep Learning. Computational Intelligence and Neuroscience. 2021. Vol. 2021. ID 6503029.
9. Zhabin D. V., Makeev M. A., Klebanov D. A. Monitoring the loss and integrity of the excavator bucket teeth based on computer vision methods. Gornaya Promyshlennost. 2023. No. 3. pp. 48–49.
10. Ortiz L. E., Cabrera E. V., Gonçalves L. M. Depth Data Error Modeling of the ZED 3D Vision Sensor from Stereolabs. Electronic Letters on Computer Vision and Image Analysis. 2018. Vol. 17, No. 1. DOI: 10.5565/rev/elcvia.1084
11. Tadic V., Toth A., Vizvari Z., Klincsik M., Sari Z. et al. Perspectives of RealSense and ZED Depth Sensors for Robotic Vision Applications. Machines. 2022. Vol. 10, Iss. 3. ID 183.
12. Saadoun A., Fredj M., Boukarm R., Hadji R. Fragmentation analysis using digital image processing and empirical model (KuzRam): a comparative study. Journal of Mining Institute. 2022. Vol. 257. pp. 822–832.
13. Shakeri A., Moshiri B., Garakani H. G. Pedestrian detection using image fusion and stereo vision in autonomous vehicles. 2018 9th International Symposium on Telecommunication with Emphasis on Information & Communication Technology. Tehran, 2018. pp. 592–596.
14. Bajracharya M., Moghaddam B., Howard A., Matthies L. H. Detecting personnel around UGVs using stereo vision (Invited Paper). Unmanned Systems Technology X : Proceedings of SPIE—International Society for Optics and Photonics. Bellingham : SPIE, 2008. Vol. 6962. DOI: 10.1117/12.782210
15. Drygin M. Yu. Technical diagnostics of the main mining equipment.Gornoe oborudovanie i elektromekhanika. 2020. No. 2(148). pp. 44–50. 16. Ivanova P. V., Asonov S. A., Ivanov S. L., Kuvshinkin S. Yu. Analysis of structure and reliability of modern fleet of mine shovels. MIAB. 2017. No. 7. pp. 51–57.
17. Drygin M. Yu. Analysis of technical maintenance systems and repair of mining equipment. Gornoe oborudovanie i elektromekhanika. 2020. No. 2(148). pp. 35–43.
18. Fischler M. A., Bolles R. C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM. 1981. Vol. 24, No. 6. pp. 381–395.