Algorithm for Predicting the State of Equipment Based on Machine Learning
https://doi.org/10.17586/0021-3454-2022-65-9-648-655
Abstract
Analysis of production equipment sensors readings is carried out and a data aggregation technique is presented to assess the probability of equipment failure. The study relevance is due to the insufficient development of the scientific and methodological apparatus for assessing equipment condition based on big data. In order to form a data set intended for development of a predictive model of the equipment state, a number of features characterizing the state of machine with numerical program control are constructed. Practical significance of the study is related with the possibility of including the generated data set in the production process and using it to save the values of equipment parameters in time and within the established limits, which characterize its ability to perform the required functions in the specified modes and under the necessary conditions of use.
About the Authors
M. R. Salikhov
ITMO University
Russian Federation
Russian Federation
Maxim R. Salikhov - Student, Faculty of Control Systems and Robotics
St. Petersburg
R. A. Yurieva
ITMO University
Russian Federation
Russian Federation
Radda A. Yurieva - PhD, Associate Professor, Faculty of Control Systems and Robotics
St. Petersburg
References
1. Sedush V.Ya., Chentsov N.A., Chentsova N.S. Metallurgicheskaya i gornorudnaya promyshlennost', 1994, no. 3, pp. 75-77. (in Russ.)
2. Sokolov S.V., Antonov A.V., Chepurko V.A. Nuclear Physics and Engineering, 2011, no. 5(2), pp. 421-424, DOI: 10.1134/S2079562911050058
3. Antonov A.V., Chepurko V.A. Izvestiya vuzov. Yadernaya Energetika, 2016, no. 3, pp. 20-29. (in Russ.)
4. Perehvost V.S. Scientific Works of the Kuban State Technological University, 2014, no. 3, рр. 38-44. (in Russ.)
5. Javed K. Mechanical Systems and Signal Processing, 2017, no. 9(94), pp. 214-236.
6. Gorjian N. Australian Journal of Mechanical Engineering, 2017, no. 1(15), pp. 36-45.
7. Pitsyk V.V. Measurement Techniques, 2016, no. 3(59), pp. 216-221.
8. Chugreev V.L., Badanin D.А. Molodoy uchenyy (Young Scientist), 2016, no. 6, pp. 49-52. (in Russ.)
9. Borovikov S.M. Information Systems and Technologies: Management and Security, 2013, no. 2, pp. 140-144. (in Russ.)
10. Mangalova M.S. Molodezh'. Obshchestvo. Sovremennaya nauka, tekhnika i innovatsii, Krasnoyarsk, 2014, no. 13, pp. 198-199. (in Russ.)
11. Lipatov M. Exposition Oil & Gas Magazine, 2016, no. 3(49), pp. 82-83. (in Russ.)
12. Gavrilyuk Е.А. Fundamental Research, 2015, no. 7-2, pp. 309-313. (in Russ.)
13. https://toir.pro/mod/book/view.php?id=470&chapterid=370.
14. Zibert А.О. Universum, 2016, no. 2(24). (in Russ.)
15. Tsikora M. Physical and Technical Problems of Mineral Development, 2011, no. 4, pp. 95-107. (in Russ.)
16. Utkin N.N. Bulletin of the Saratov State Technical University, 2011, no. 2(2), pp. 271-275. (in Russ.)
17. Wang Z. Optics Express, 2017, no. 8(25), pp. 18553-18565.
18. Wu W. Journal of Systems Science and Systems Engineering, 2016, no. 2(25), pp. 210-228.
Review
For citations:
Salikhov M.R., Yurieva R.A. Algorithm for Predicting the State of Equipment Based on Machine Learning. Journal of Instrument Engineering. 2022;65(9):648-655. (In Russ.) https://doi.org/10.17586/0021-3454-2022-65-9-648-655
Views:
29
Email this article 