Moscow, Moscow, Russian Federation
Moscow, Moscow, Russian Federation
Moscow, Moscow, Russian Federation
Moscow, Moscow, Russian Federation
Moscow, Moscow, Russian Federation
The paper discusses the use of machine learning to analyze and predict the resource of components and parts of railway rolling stock. Special attention is paid to the procedure of checking the hypothesis that data samples collected from different sources belong to the same general population. This is critically important for correct data aggregation and improving the quality of training samples used in predictive models. The developed approach helps to increase the accuracy of assessing the condition of components and parts, which, in turn, increases the safety of railway transportation.
training, analysis, rolling stock, forecasting, resource, checking, hypotheses, data, reliability, transportation
1. Beysolow T. Applied reinforcement learning with Python: with OpenAI Gym, Tensorflow, and Keras. Apress;2019.
2. Sharden B, Massaron L, Basketti A. Large-scale machine learning with Python: a textbook [Internet]. Moscow: DMK Press; 2018. onic library system. Available from: https://e.lanbook.com/book/105836
3. Plas, Vander J. Python for complex tasks. Data science and machine learning: manual. / Moscow: Piter; 2018.
4. Solntseva OG. Aspects of applying artificial intelligence technologies. E-Management [Internet]. 2018;1. Available from: https://cyberleninka.ru/article/n/aspekty-primeneniya-tehnologiy-iskusstvennogo-intellekta
5. Kolesnikova GI. Artificial intelligence: problems and prospects. Videonauka [Internet]. 2018;2(10). Available from: https://videonauka.ru/stati/44-novye-tekhnologii/190-iskusstvennyj-intellekt-problemy-i-perspektivy.
