STUDY OF ABNORMAL INDICATORS OF COAL COKING PROCESS ON THE BASIS OF MACHINE LEARNING

On the basis of computer modeling and machine learning methods, an algorithm for preparing and training data taken from technological databases and journals for the preparation of raw materials for coke production was compiled. After statistical analysis, conclusions were drawn, which were accepted in production for implementation. In a continuous production process, the ability to timely detect defects in equipment and logistics directly affects the economic effect. Any field in the modern world tends to develop artificial intelligence and machine learning technologies. Novokuznetsk enterprises, including metallurgical ones, are also actively developing robots - prompters and systems for predicting product quality. Artificial intelligence is concerned with the task of using computers to understand human intelligence. This is an important direction in the construction of human-like systems. At this stage in the development of machine learning, a number of algorithms and software systems began to be attributed to it, the distinguishing feature of which is that they can solve some problems in the same way as a person thinking about their solution would do. But with respect to actively developing information technology systems, metallurgical processes live much longer, so finding solutions to combine the knowledge and experience of technologists and artificial intelligence is a difficult but interesting task for finding possible problems in production. Identification of abnormal deviations helps to avoid unplanned downtime, and, accordingly, avoid economic losses. This article is a demonstration of the path that has been taken to combine information technologies in the field of artificial intelligence and metallurgy, namely the production of coking coal, based on the technological indicators of coke production.

1. Vegman E.F., Zherebin B.N., Pokhvisnev A.N. et al.; Yusfin Yu.S. ed. Metallurgy of pig iron. 3rd ed., reprint. and add. Moscow: IKTs «Akademkniga», 2004, 774 p. (In Russ.).

2. Korotich V.I. ed. The beginnings of metallurgy. Ekaterinburg: UGTU, 2000, 392 p. (In Russ.).

3. Vasant Dhar. Data Science and Prediction. Communications of the ACM. 2013, vol. 56, no. 12, pp. 64–73.

4. Cox David R. Some procedures connected with the logistic qualitative response curve. Research Papers in Probability and Statistics (Festschrift for J. Neyman). London: Wiley, 1966, pp. 55–71.

5. Babarykin N.N. Theory and technology of the domain process. Magnitogorsk: ITs MGTU, 2009, 257 p. (In Russ.).

6. Sklyar M.G. Intensification of coking and coke quality. Moscow: Metallurgiya, 1976, 256 p. (In Russ.).

7. Zhuravlev Yu.I., Ryazanov V.V., Sen'ko O.V. Recognition. Mathematical methods. Software system. Practical applications. Moscow: Fazis, 2006. (In Russ.).

8. Zagoruiko N.G. Applied methods of data and knowledge analysis. Novosibirsk: IM SO RAN, 1999. (In Russ.).

9. Barsegyan A.A., Kupriyanov S., Kholod I.I., Tess M.D., Elizarov S.I. Analysis of data and processes. St. Petersburg: BKhV-Peterburg, 2009, 512 p. (In Russ.).

10. Katsko I.A., Paklin N.B. A workshop on data analysis on a computer. Moscow: KolosS, 2009. 278 s. (In Russ.).

11. Brink Kh., Richards D., Feverolf M. Machine learning. St. Petersburg: Piter, 2017, 336 p. (In Russ.).

12. Sharden B., Massaron L., Bosketti A. Large-scale machine learning with Python. St. Petersburg: Piter, 2018, 180 p. (In Russ.).

13. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer-Verlag, 2009. 746 p.

14. Mitchell T. Machine Learning. McGraw-Hill Science/Engineering/Math, 1997.

15. Vapnik V.N. Statistical learning theory. N.Y.: John Wiley & Sons, Inc., 1998.

16. Bernhard Schölkopf, Alexander J. Smola Learning with Kernels. Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge, MA, 2002.

17. Witten I.H., Frank E. Data Mining: Practical Machine Learning Tools and Techniques (Second Edition). Morgan Kaufmann, 2005.

18. Liang Wang, Li Cheng, Guoying Zhao. Machine Learning for Human Motion Analysis. IGI Global, 2009. 318 p.

19. Witten I.H., Frank E., Hall M.A. Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, 2011.

20. Smith F.J. Data Science as An Academic Discipline. Data Science Journal. 2006, vol. 5, no. 19, pp. 163–164.