graduate student
Moscow, Moscow, Russian Federation
graduate student
Moscow, Moscow, Russian Federation
employee
Moscow, Moscow, Russian Federation
UDK 621.892 Смазочные материалы
BBK 392 Железнодорожный транспорт
Application of machine learning to calculate the supply of motor oils to railway grounds is considered. The study objective is to use artificial intelligence and other machine learning methods to ensure the supply of motor oils and to provide stable operation of traction rolling stock. The possibility of using machine learning to improve the accuracy of planning the supply of motor oils to railway grounds, excluding the human factor from the calculation, is analyzed. The following research methods are used: the method of using a heat map, machine learning methods, intelligence analysis, and linear regression. As a result of the study, it is found that it is more expedient to use Lasso Regression when developing a program for calculating the supply of motor oils for its use in traction rolling stock.
training, motor oils, railway transport, innovations, lubricants, diesel locomotives, artificial intelligence
1. Russian Railways, Order No. 2718p. On Approval of the Holding's Energy Strategy for the Period up to 2015 and for the Future up to 2030; December 15, 2011.
2. Methodology for calculating engine oil consumption for the operation of traction rolling stock No. 717p; April 11, 2012.
3. Muller A. Introduction to machine learning using Python. A guide for data scientist. Moscow: Alpha-book; 2017.
4. Plas JV. Python Data Science Handbook. Moscow: Piter; 2017.
5. Vyugin VV. Mathematical grounds of machine learning and forecasting. Moscow: MCCME; 2014.
6. Raschka S, Mirjalili V. Python machine learning. Moscow: DMK Press; 2017.
7. Nikulin EA. Computer geometry and algorithms of machine graphics. Moscow: St. Petersburg: BHV; 2005.
8. Rogers D, Adams J. Mathematical elements for computer graphics. 2nd ed. Moscow: Mir; 2001.
