Russian Federation
Russian Federation
Russian Federation
Russian Federation
This research presents an accuracy analysis of the prediction of random signals using adaptive and non-adaptive extrapolators. Extrapolation is performed using Chebyshev polynomials orthogonal over a set of equally spaced points. Several algorithms for an automatic selection of an extrapolating polynomial in real time, based on estimates of the prediction error, are considered. A comparative study of these algorithms is carried out in order to identify the most effective one. The study includes an analysis of prediction errors when using fixed-order extrapolators, as well as adaptive extrapolators using different parameter selection rules. In particular, a selection rule based on the minimum of the error modulus at a given time and a rule based on the minimum of the root mean square error for previous cycles are considered. It is shown that the use of a neural network algorithm based on CatBoost provides the smallest prediction error compared to the alternative approaches considered. This demonstrates the potential of using neural networks to adapt extrapolator parameters to changing characteristics of the predicted random process.
adaptive extrapolator; Chebyshev polynomials; forecast errors; random process; neural networks
1. Baranov L. A. The object according state prediction to diagnostic data / L. A. Baranov, E. P. Balakina, A. I. Godyaev // Journal of Physics: Conference Series, Vladivostok, 7–8 October 2021. — Vladivostok, 2021. — P. 012121. — DOI:https://doi.org/10.1088/1742-6596/2096/1/012121.
2. Baranov L. A. Vliyanie prognoza rassoglasovaniya na kachestvo upravleniya v zamknutyh avtomaticheskih sistemah / L. A. Baranov, O. E. Pudovikov, E. P. Balakina // Elektrotehnika. — 2022. — № 9. — S. 8–15. — DOI:https://doi.org/10.53891/00135860_2022_9_8.
3. Petropoulos F. Forecasting: Theory and practice / F. Petropoulos, Ya. Kang, F. Li et al. // International Journal of Forecasting. — 2022. — Vol. 38. — Iss. 3, July — September. — Pp. 705–871. — DOI:https://doi.org/10.1016/j.ijforecast. 2021.11.001.
4. Asadi F. Adaptive Kalman Filter for Noise Estimation and Identification with Bayesian Approach / F. Asadi, S. H. Sadati // World Academy of Science, Engineering and Technology International Journal of Mathematical and Computational Sciences. — 2021. — Vol. 15. — Iss. 10.
5. Bulgakov A. Cyber-physical System for Diagnosing and Predicting Technical Condition of Servo-drives of Mechatronic Sliding Complex during Construction of Highrise Monolithic Buildings / A. Bulgakov, T. Bock, T. Kruglova // 2020 Proceedings of the 37th ISARC. — Kitakyushu, Japan. — Pp. 339–346.
6. Serradilla O. Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects / O. Serradilla, E. Zugasti, J. Rodriguez et al. // Applied Intelligence. — 2022. — DOI:https://doi.org/10.1007/s10489-021-03004-y.
7. Baranov L. A. Centralizovannoe upravlenie dvizheniem poezdov gorodskih zheleznyh dorog sovremennogo megapolisa / L. A. Baranov, E. P. Balakina, S. E. Ikonnikov, D. A. Antonov // Nauka i tehnika transporta. — 2020. — № 1. — S. 30–38.
8. Baranov L. A. Prognozirovanie sluchaynyh processov na baze mnogochlenov, ortogonal'nyh na mnozhestve ravnootstoyaschih tochek / L. A. Baranov, E. P. Balakina // Elektrotehnika. — 2020. — № 9. — S. 39–46.
9. Baranov L. A. Kvantovanie po urovnyu i vremennaya diskretizaciya v cifrovyh sistemah upravleniya / L. A. Baranov. — M.: Energoatomizdat, 1990. — 304 s.
10. Cypkin Ya. Z. Teoriya lineynyh impul'snyh sistem / Ya. Z. Cypkin. — M.: Fizmatizdat, 1963. — C. 968.
11. Miln V. E. Chislennyy analiz / V. E. Miln. — M.: IL, 1951. — 292 s.
12. Berezin I. S. Metody vychisleniy / I. S. Berezin, I. P. Zhidkov. — M.: Fizmatgiz, 1959. — T. 1. — C. 464.
13. Baranov L. A. Adaptivnyy ekstrapolyator nestacionarnyh sluchaynyh processov / L. A. Baranov // Elektrotehnika. — 2023. — № 9. — S. 22–25. — DOI:https://doi.org/10.53891/00135860_2023_9_22.
14. CatBoost. — URL: https://catboost.ai/ (data obrascheniya: 13.04.2025).
15. Prokhorenkova L. CatBoost: unbiased boosting with categorical features / L. Prokhorenkova. — URL: https://arxiv.org/pdf/1706.09516 (data obrascheniya: 13.04.2025).
16. Ajin R. S. Optimization of SVR and CatBoost models using metaheuristic algorithms to assess landslide susceptibility / R. S. Ajin, S. Segoni, R. Fanti // Scientific Reports. — 2024. — Vol. 14. — DOI:https://doi.org/10.1038/s41598-024-72663-x.
17. Liu X. Ultra Short Term Wind Power Prediction Model Based on WRF Wind Speed Prediction and CatBoost / X. Liu, L. Zhang, Zh. Zhang, T. Zhao et al. // IOP Conference Series: Earthand Environmental Science. — 2021. — Vol. 838. — 012001. — DOI:https://doi.org/10.1088/1755-1315/838/1/012001.
18. Balakina E. P. Analiz pogreshnostey prognoza dlya intellektual'nyh sistem upravleniya i prediktivnoy diagnostiki / E. P. Balakina, L. A. Baranov, Yu. Chzhan // Nadezhnost'. — 2023. — T. 23. — № 2. — S. 12–18. — DOI:https://doi.org/10.21683/1729-2646-2023-23-2-12-18.
19. Baranov L. A. Prognoz sluchaynyh processov, pri nalichii edinichnyh vozmuscheniy v intellektual'nyh transportnyh sistemah / L. A. Baranov, A. S. Anohin, I. A. Zherebyatin, Yu. Chzhan // Avtomatika na transporte. — 2023. — T. 9. — № 3. — S. 239–246. — DOI:https://doi.org/10.20295/2412-9186-2023-9- 03-239-246.
20. Baranov L. A. Imitacionnoe modelirovanie intellektual'nyh ekstrapolyatorov / L. A. Baranov, E. P. Balakina, Ch. Yuncyan i dr. // Nauka i tehnika transporta. — 2024. — № 3. — S. 62–67.
