APPLIED RESEARCH

Intelligent system for automatic selection of front loader operating modes depending on material characteristics

Authors

  • Mikhail V. Mityakin Gubkin Russian State University of Oil and Gas (National Research University), 65 Leninsky Prospekt, bldg. 1, Moscow, 119991, Russia

How to cite

GOST Mityakin M. V. Intelligent system for automatic selection of front loader operating modes depending on material characteristics // STROITEL'NYE I DOROZHNYE MASHINY. 2026. Vol. 70. No. 8. P. 378-391. DOI: 10.25726/e9726-6778-4289-h
APA Mityakin, M. V. (2026). Intelligent system for automatic selection of front loader operating modes depending on material characteristics. STROITEL'NYE I DOROZHNYE MASHINY, 70(8), 378-391. https://doi.org/10.25726/e9726-6778-4289-h

Abstract

Power train tuning of a front loader operating at a site with several stockpiles remains manual, so the same machine handles sand and blasted rock with identical feed and traction settings. Current standards describe the outcome of the digging phase geometrically: bucket capacity is computed under GOST 29290-92 from the struck volume plus the material above the cutting edges at a 2:1 slope, rated operating load follows GOST ISO 14397-1-2015, and the bucket fill factor is not covered by either document. The purpose of the study was to construct and compute a model of a system that recognises the material class from force and kinematic signals of the initial penetration phase and assigns the power train mode without operator involvement. The computation rests on the author's model of the digging process for a modelled 5 t class loader with a 3.0 м³ bucket; the numerical experiment covered a series of 1,240 cycles. Materials are grouped into five classes by the author's digging difficulty index ranging from 1,00 to 2,35. The limiting penetration depth under the traction condition falls from 1,35 to 0,88 m and the fill factor from 1,06 to 0,76, while the mass carried in the bucket varies by only 8,7% between dry sand and coarse crushed stone. The material class is recognised from four features of a 0,4 s window with a correct assignment share of 0,914, the heaviest confusion falling on the pair of adjacent granulometric classes. Adaptive mode assignment raises operational output by 1,4-10,7% and lowers specific fuel consumption by 12,9-17,4% depending on the class. The gain grows with digging difficulty and splits unevenly between output and fuel economy: on cohesive soil the output gain peaks while the specific consumption gain is smallest. This relation shows that the bucket fill factor behaves as a controlled variable rather than a reference constant of the machine and belongs in the control loop alongside pressure and engine speed.

Keywords

front loader power train operating mode material characteristics bucket fill factor penetration resistance material class recognition adaptive control specific fuel consumption

References

Buryi G.G. Mathematical model of soil digging with a spherical excavator bucket // Russian Automobile and Highway Industry Journal. 2021. № 6. pp. 688-698.

Velikanov V.S. Forecasting the load on the working equipment of a quarry excavator using a fuzzy logic model // Journal of Mining Institute. 2020. Vol. 241. pp. 29-36.

Velikanov V.S., Dremin A.V., Chernukhin S.A., Lomovtseva N.V. Neural network technologies in intelligent analysis of data on the particle size distribution of blasted rocks // Russian Mining Industry. 2024. № 4. pp. 90-94.

Gartfelder V.A., Stadukhin A.A., Mokretsov N.A. Control laws for the individual traction electric drive of a front loader // Tractors and Agricultural Machinery. 2023. № 6. pp. 531-541.

Gorbenko I.D., Shagniev O.B. Intellectualization of the drilling process control system under uncertainty of the workpiece material // Mechanics, Automation, Management. 2025. № 3. pp. 119-127.

Gorelov V.A., Kositsyn B.B., Stadukhin A.A., Chudakov O.I. Method for determining the parameters of the electromechanical transmission of a front loader // Tractors and Agricultural Machinery. 2021. № 5. pp. 38-45.

Dremin A.V., Sitdikova S.V., Velikanov V.S., Stozhkov D.S., Grishin I.A. Real-time analysis of rock fragmentation using domestic hardware and software // Russian Mining Industry. 2025. № 3. pp. 118-123.

Osipov P.A. Review of technical solutions for measuring the mass of rock in the bucket of electric single-bucket excavators // Mining Informational and Analytical Bulletin. 2021. № 11-1. pp. 229-238.

Salikhov R.F., Permyakov V.B. Study of the influence of the dynamics of technical parameters on the operational performance of hydraulic single-bucket excavators // Russian Automobile and Highway Industry Journal. 2024. Vol. 21. № 4. pp. 540-560.

Khoreshok A.A., Dubinkin D.M., Litvin Ya.O., Markov S.O., Tyulenev M.A. On the change in the productivity of hydraulic backhoes under different schemes of loading overburden into mining dump trucks // Minerals and Mining Engineering. 2024. № 4. pp. 26-34.

Shemyakin S.A., Shishkin E.A. Determination of the maximum bucket turning force of a hydraulic backhoe excavator // Minerals and Mining Engineering. 2023. № 3. pp. 17-24.

Shprekher D.M., Babokin G.I., Zelenkov A.V. Neural network algorithm for tuning a PI controller in the control system of a shearer // Mechanics, Automation, Management. 2022. № 1. pp. 13-22.

Azulay O., Shapiro A. Wheel loader scooping controller using deep reinforcement learning // IEEE Access. 2021. Vol. 9. pp. 24145-24154.

Dadhich S., Sandin F., Bodin U., Andersson U., Martinsson T. Field test of neural-network based automatic bucket-filling algorithm for wheel-loaders // Automation in Construction. 2019. Vol. 97. pp. 1-12.

Wang S., Yu S., Hou L., Wu B., Wu Y. Prediction of bucket fill factor of loader based on three-dimensional information of material surface // Electronics. 2022. Vol. 11. № 18. Article 2841.

Metrics

77 views
0 downloads
Want to publish with us?
Submit an article

Machine-readable metadata

Similar Articles

1 2 3 4 5 6 7 > >> 

You may also start an advanced similarity search for this article.