Use of digital technologies in diagnosing engines of energy-saturated agricultural machinery
https://doi.org/10.26897/2687-1149-2023-4-52-59
Abstract
The development of digital technologies aimed at improving the diagnostic process, increasing the reliability of determining the functional characteristics of agricultural machinery in real time is important and relevant in the technical support of energy-saturated machines. To develop an intelligent system for remote diagnostics of the engines of energy-saturated agricultural machinery, the authors tested a neural network constructor with the ability to use up to ten input and output parameters. An algorithm for a digital system for remote diagnostics, a scheme for predicting failures in online monitoring, and a digital platform for diagnosing energy-saturated agricultural machinery have been developed. The developed platform makes it possible to obtain ICE diagnostic parameters (fuel consumption, engine temperature, and engine shaft speed), which are remotely transmitted in the form of encrypted data to the server using a GPS modem and digitized in the data bank. Then the received data are structured and analyzed using the developed artificial neural network models. The decrypted diagnostic parameters of the internal combustion engine are sent to the operator, who sees graphs of the parameters of the technical condition of agricultural machinery and reports on predicting possible failures of internal combustion engine parts. The article presents a method for collecting and storing diagnostic information obtained as a result of monitoring the technical condition of agricultural machinery. These data are processed using a mathematical model of a neural network. The use of digital technologies in diagnosing equipment with the help of artificial intelligence can significantly reduce the complexity of the operations performed, evaluate the efficiency of the machine as a whole and predict the onset of failures of its mechanisms, perform timely maintenance and repair of machines, and reduce unplanned downtime of energy-saturated agricultural machinery.
About the Authors
Yu. V. Kataev
Federal Scientific Agroengineering Center VIM
Russian Federation
Russian Federation
Yuri V. Kataev - CSc (Eng), Associate Professor, Lead Research Engineer
5, 1st Institutskiy Proezd Str., Moscow,109428
I. A. Tishaninov
Federal Scientific Agroengineering Center VIM
Russian Federation
Russian Federation
Igor A. Tishaninov - Junior Research Engineer
5, 1st Institutskiy Proezd Str., Moscow,109428
References
1. Kataev Yu.V., Zagoruiko M.G., Tishaninov I.A., Gradov E.A. Prediction of failures in agricultural machinery engines using digi- tal technologies. The Agrarian Scientifi c Journal. 2022;2:79-82. https://doi.org/10.28983/asj.y2022i2pp79-82 (In Rus.)
2. Petrishchev N.A., Kostomakhin M.N., Sayapin A.S., Iv- leva I.B. Improving the human-machine-environment monitoring system and operation rules for increasing operational tractor reliabil- ity. Machinery Technical Service. 2020;3(140):12-20. (In Rus.)
3. Dorokhov A.S., Kataev Yu.V., Kostomakhin M.N. Intelligent software package for diagnosing and predicting the technical condition of agricultural machinery: Certifi cate of state registration of the com- puter program RU2021681505; No. 2021668436;2021. (In Rus.)
4. Semeikin V.A., DorokhovA.S. Theoretical grounds for the organization of the process of input quality control of machine-building products. Vestnik of Moscow Goryachkin Agroengineering University. 2007;2(22):92-94. (In Rus.)
5. Pestryakov E.V. Software for diagnosing and predicting the technical condition of agricultural machines. Machinery and equipment for rural area. 2021;12(294):37-41. (In Rus.)
6. Kostomakhin M.N., VoronovA.N., Kovalev L.I., Kovalev I.L. Control of reliability parameters of agricultural machinery using GPS/GLONASS systems. Trudy GOSNITI. 2015;118:26-30. (In Rus.)
7. Manzhula V.G., Fedyashov D.S. Kohonen neural networks and fuzzy neural networks in data mining. Fundamental Research. 2011;4:108-114. (In Rus.)
8. Erokhin M.N. DorokhovA.S., Kataev Yu.V. Intelligent system for diagnosing the parameters of the technical condition of tractors. Agricultural Engineering. 2021;2(102):45-50. https://doi.org/10.26897/2687-1149-2021-2-45-50 (In Rus.)
9. Erokhin M.N., Leonov O.A., Shkaruba N.Z., Kataev Yu.V., Vergazova Yu.G. Assessing the relative interchangeability in joints with preload. Russian Engineering Research. 2020;40(6):469-472.
10. Sukhanova N.V., Sheptunov S.A. Fault-tolerant neural network, method for detecting neural network faults, method for ensuring fault tolerance of neural network: Patent RU2760636 C2, IPC G06F 11/20, G06N3/02. No. 2018145179, 2021. (In Rus.)
11. PosyaginA.I., YuzhakovA.A. Development of a two-layer neural network for a self-routing analog-to-digital converter based on a neural network. Elektrotekhnika. 2013;11:10-13. (In Rus.)
12. Pestryakov E.V., SayapinA.S., Kostomakhin M.N., Petrishchev N.A. Analysis of the Technical Condition of Agricultural Machinery Using Neural Networks. Lecture Notes on Data Engineering and Communications Technologies. 2022 Vol. 121. P. 92-101. https://doi.org/10.1007/978-3-030-97057-4_9 (In Rus.)
Review
For citations:
Kataev Yu.V., Tishaninov I.A. Use of digital technologies in diagnosing engines of energy-saturated agricultural machinery. Agricultural Engineering (Moscow). 2023;25(4):52-59. (In Russ.) https://doi.org/10.26897/2687-1149-2023-4-52-59
Views:
262
Email this article 