Improving the methods of reserving spare parts for agricultural machinery based on genetic algorithms

The uninterrupted use of agricultural machinery performing field operations is ensured by maintaining their working condition through timely maintenance and prompt elimination of operational failures. The period of inoperative state of machines can be reduced if there is a certain inventory stock of spare parts in the warehouse of the operating company. When determining the stock, taking into account the feasibility of the reservation and the calculation of the required number of the reserved parts, the methods of artificial intelligence are to be sufficiently studied. To justify the method of reserving spare parts for agricultural machinery and determine the effect of its industrial implementation, the authors developed a genetic algorithm and software. The developed reservation method was tested at an agricultural enterprise to determine seasonal reserves of spare parts for Don-1500B and TORUM combine harvesters. The designers of the information data model took into account the cost and quantity of consumed spare parts by year, the number of machines consuming spare parts in a particular work season, the time values for installing spare parts on a machine, etc. The use of the genetic algorithm made it possible to identify sixty-six of the most significant items out of 2,500 spare parts that need to be reserved for the harvesting season. It has been established that the method of reserving spare parts for agricultural machinery based on the use of the genetic algorithm in combination with a database containing information on the actual consumption of spare parts by machines for at least three previous years, can reduce the idle time of combines waiting for the delivery of spare parts by 37%, increase the daily productivity of combines by 11.4%, and increase the coefficient of the operational availability of combines by 4.38%.

1. Tsarev Yu.A., Simon D.V. Algorithm of inventory management as a control method of operational reliability of combine harvesters. Politematicheskiy setevoy elektronniy nauchniy zhurnal Kubanskogo gosudarstvenno-go agrarnogo universiteta. 2016; 115: 263-283. (In Rus.)

2. Nikitchenko S.L., Grinchenkov D.V. Mathematical support of an information system for reserving spare parts of agricultural machinery. Fundamental’no-prikladnye problemy bezopasnosti, zhivuchesti, nadozhnosti, ustoychivosti i effektivnosti sistem: Materialy IV mezhdunarodnoy nauchno-prakticheskoy konferentsii. Yelets, 2020: 374-379. (In Rus.)

3. Filatov M.I., Yusupova O.V. Formirovanie rezerva zapasnykh chastey dlya remonta transportno-tekhnologicheskikh mashin [Forming a reserve of spare parts for the repair of transport and technological machines]. Vestnik Orenburgskogo gosudarstvennogo universiteta. 2014; 10 (171): 213-218. (In Rus.)

4. Ryazanova E.S., Korchagina E.V. Economic efficiency of WMS systems in warehousing. Nedelya nauki SPbPU: Materialy nauchnoy konferentsii s mezhdunarodnym uchastiem. Sankt-Peterburg, 2017: 106-108. (In Rus.)

5. Schreibfeder G. Efficient inventory management. Translated from English. 2nd ed. Moscow, Alpina Business Books, 2006. 304 р.

6. Zhukov O.V., Sazonov S.P., Onoprienko Yu.G., Mershieva G.A. Methods of applying ABC/XYZ-analysis for the inventory management purposes within the ERP-system. Vestnik Voronezhskogo gosudarstvennogo universiteta inzhenernykh tekhnologiy. 2017; 74(1): 477-484. https://doi.org/10.20914/2310-1202-2017-1-477-484 (In Rus.)

7. Rakhutin M.G. Prospects of using neural networks for forecasting the consumption of spare parts for downhole hydraulic equipment. Gorniy informatsionno-analiticheskiy byulleten’. 2002; 2: 147-148. (In Rus.)

8. Rutkovskaya D., Pilin’skiy M., Rutkovskiy L. Neural networks, genetic algorithms and fuzzy systems. Translated from Polish by I.D. Rudinskiy. 2nd ed. Moscow, Goryachaya liniya – Telekom, 2013. 384 p. (In Rus.)

9. Babina O.I. Developing a simulation optimization model for supporting the planning of warehouse systems. Komp’yuternye issledovaniya i modelirovanie. 2014; 6(2): 295-307. (In Rus.)

10. Protalinskiy O.M., Shcherbatov I.A., Protalinskaya Yu.O. Intelligent management of production assets in the energy sector. Shag v budushchee: iskusstvenniy intellekt i tsifrovaya ekonomika: Materialy 1-y Mezhdunarodnoy nauchno-prakticheskoy konferentsii. Moscow, GUU, 2017: 5-10. (In Rus.)

11. Serdyukov V.I., Serdyukova N.A., Shishkina S.I. Increase in product uptime by using elements of artificial intelligence. Vestnik MGTU im. N.E. Baumana. Ser. Mashinostroenie. 2017; 1(112): 62-72. https://doi.org/10.18698/0236-3941-2017-1-62-72 (In Rus.)

12. Volochkov I.V. Evolutionary modeling in decision making. Ekonomika i predprinimatel’stvo. 2020; 2 (115): 897-901. (In Rus.)

13. Holland J.H. Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence. The MIT Press, Cambridge, 1992. 211 p. ISBN0262581116.

14. Doronin V.A. Application of a genetic algorithm for inventory optimization. Novye informatsionnye tekhnologii v avtomatizirovannykh sistemakh: Materialy konferentsii. 2006; 9: 117-123. (In Rus.)

15. Periaux J., Chen H.Q., Mantel B., Sefrioui M., Sui H.T. Combining game theory and genetic algorithms with application to DDM-nozzle optimization problems. Finite Elements in Analysis and Design. 2001; 37(5): 417-429. https://doi.org/10.1016/S0168-874X(00)00055-X