Russian Federation
Russian Federation
UDK 004.896 Искусственный интеллект в промышленных системах. Интеллектуальные САПР и АСУ. Интеллектуальные роботы
A new hybrid approach has been proposed to automate the management of complex technological processes at railway stations of industrial transport using intelligent monitoring technologies. This approach is based on the concept of predictive modeling combined with methods of statistical analysis, including a modification of the principal components analysis method for multivariate statistical analysis and the identification of violations in technological processes using a combination of well-known methods such as contribution analysis and fuzzy dynamic analysis. The principal feature of the hybrid approach is mapping the initial space of numerical parameters of the technological process onto a new space formed by fuzzy rules of an evolving system model. Applying multivariate analysis to new system variables using the principal component method allows for the formation of a few intermediate variables with different degrees of granularity and interpretability, describing the behavior of the controlled process, which makes it possible to develop mathematical models and algorithms for solving various monitoring tasks An example of using this approach for post-processing monitoring data to identify performance discrepancies in a marshalling yard and anomalies in the controlled process is considered.
intelligent monitoring, evolving modeling, principal component method, fuzzy dynamic model, technological processes in railway transport
1. Stoyanova N. V. Osnovnye etapy strategicheskogo razvitiya zheleznodorozhnogo transporta // Transport: nauka, obrazovanie, proizvodstvo («TRANSPORT‑2022»). 2022. S. 268–272.
2. Rykov Yu. G. K voprosu razvitiya gibridnogo analiticheskogo podhoda k modelirovaniyu slozhnyh sistem, soderzhaschih kak slabo strukturirovannye, tak i horosho strukturirovannye podsistemy // Informacionnye i matematicheskie tehnologii v nauke i upravlenii. 2022. № 4(28). S. 234–247.
3. Kudryavcev E. GPSS World. Osnovy imitacionnogo modelirovaniya razlichnyh sistem. Litres, 2022.
4. Nikitin A. B., Groshev V. A. Avtomatizaciya kontrolya hoda tehnologicheskogo processa stancii v rezhime real'nogo vremeni // Izvestiya Peterburgskogo universiteta putey soobscheniya. 2016. № 2(47). S. 229–238.
5. A review of process fault detection and diagnosis: Part I: Quantitative model-based methods / V. Venkatasubramanian [et al.] // Computers & Chemical Engineering. 2003. T. 27. No. 3. P. 293–311.
6. A review of data mining technologies in building energy systems: Load prediction, pattern identification, fault detection and diagnosis / Y. Zhao [et al.] // Energy and Built Environment. 2020. T. 1. No. 2. P. 149–164.
7. Large language models for software engineering: A systematic literature review / X. Hou [et al.] // ACM Transactions on Software Engineering and Methodology. 2023.
8. Zheng S. A new unsupervised data mining method based on the stacked autoencoder for chemical process fault diagnostics // Computers & Chemical Engineering. 2020. Vol. 135. P. 106755. Russian.
9. An unsupervised data mining strategy for performance evaluation of ground source heat pump systemst X. Zhou [et al.] // Sustainable Energy Technologies and Assessments. 2021. Vol. 46. P. 01255.
10. Development of the intelligent monitoring system for water parameters / A. A. Bezgin [et al.] // 2020 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF). IEEE, 2020.
11. Kasabov N., Filev D. Evolving intelligent systems: methods, learning, & applications // International symposium on evolving fuzzy systems. IEEE, 2006. P. 8–18.
12. Lughofer E. On-line assurance of interpretability criteria in evolving fuzzy systems — Achievements, new concepts and open issues // Information Sciences. 2013. Vol. 251.
13. Angelov P., Filev D. An approach to online identification of Takagi–Sugeno fuzzy models // IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics. 2004. Vol. 34(1).
14. Leite D., Škrjanc I., Gomide F. An overview on evolving systems and learning from stream data. URL: https:// doi.org/10.1007/s12530-020-09334-5
15. Incremental Structure-Evolving Intelligent Systems with Advanced Interpretational Properties // Kuznetsov S. O., Panov A. I., Yakovlev K. S. (eds) Artificial Intelligence. RCAI 2020. Lecture Notes in Computer Science. Vol. 12412. Springer, Cham.
16. Temporal Prediction Models for Technological Processes Based on Predictive Analytics / Dolgiy A. [et al.] // Lecture Notes in Networks and Systems / eds. S. Kovalev [et al.]. T. 777. LNNS Springer Science and Business Media Deutschland GmbH, 2023. P. 179–194.
17. Abraham W. C., Robins A. Memory retention — the synaptic stability versus plasticity dilemma // Trends in Neurosciences. 2005. Vol. 28(2). P. 73–78.
18. Lazar N. Ockham’s razor // Wiley Interdisciplinary Reviews: Computational Statistics. 2010. T. 2. No. 2. P. 243–246.
19. Angelov P., Filev D. On-line design of Takagi-Sugeno models // International fuzzy systems association world congress. Berlin, Heidelberg: Springer Berlin Heidelberg, 2003. P. 576–584.
20. Chiu S. Fuzzy Model Identification Based on Cluster Estimation // Journal of Intelligent and Fuzzy Systems. 1994. Vol. 2(3). P. 267–278.
21. Pologov V. V. Kompleksirovanie metoda subtraktivnoy klasterizacii i metoda K-srednih dlya segmentacii izobrazheniy // Luchshiy issledovatel'skiy proekt. 2020. S. 180–187.
22. Dolgiy A. I., Kovalev S. M., Kolodenkova A. E. Nechetko-dinamicheskiy metod analiza glavnyh komponent v sistemah intellektual'nogo monitoringa // 21-ya Nacional'naya konferenciya po iskusstvennomu intellektu s mezhdunarodnym uchastiem (KII‑2023): trudy konferencii (Smolensk, 16–20 oktyabrya 2023 goda): v 2 t. Smolensk: Print-Ekspress, 2023. S. 66–76.
23. Dolgiy A. I., Kovalev S. M., Kolodenkova A. E. Interpretiruemost' i dizayn nechetkih interpretiruemyh sistem // Gibridnye i sinergeticheskie intellektual'nye sistemy. 2022. S. 359–364.
24. Dolgiy A. I., Kolodenkova A. E., Kovalev S. M. Interpretiruemaya model' klassifikatora na osnove nechetkoy logisticheskoy regressii // Integrirovannye modeli i myagkie vychisleniya v iskusstvennom intellekte: sbornik nauchnyh trudov XI Mezhdunarodnoy nauchno-prakticheskoy konferencii (IMMV‑2022, Kolomna, 16–19 maya 2022 g.): v 2 t. M.: RAII, 2022. T. 1. S. 53–60.
25. Angelov P., Zhou X. Evolving fuzzy systems from data streams in real-time // 2006 International Symposium on Evolving Fuzzy Systems. P. 29–35.
26. Hallgrímsson Á. D., Niemann H. H., Lind M. Improved process diagnosis using fault contribution plots from sparse autoencoders // IFAC-PapersOnLine. 2020. T. 53. No. 2. P. 730–737.
27. Formirovanie ob'ektivnyh pokazateley gruzovoy stancii na osnove dannyh «ot kolesa» / A. E. Hatlamadzhiyan [i dr.] // Avtomatika na transporte. 2024. T. 10, № 3. S. 254–268.
