SMART ALGORITHM FOR INTERVAL ESTIMATION OF ARC-QUENCHING REACTOR PARAMETERS

Yuri A. Dementiy, Evgeny V. Shornikov, Kirill P. Nikolaev

DOI: 10.47026/1810-1909-2021-3-64-72

Key words

machine learning, interval estimation, parametric identification, Peterson coil, regularization, data informativity, generalization ability.

Abstract

The purpose of the arc suppression reactor is to reduce the capacitive current of the network to a safe level where the single-phase earth fault current at the fault location does not exceed five amperes. The current reduced to a permissible level prevents open arcing at the fault location. For proper operation of this device, the arc suppression reactor control automatics needs to adjust the zero-sequence circuit to resonance, which balances the capacitive current of the mains and the inductive current of the reactor. To perform this tuning, it is not necessary to have information about the absolute values of the parameters of the zero-sequence circuit, but by determining them, the automation device is able to solve a wider range of tasks related to network diagnostics and increasing the efficiency of the arc suppression reactor. In this article we consider an approach to solving the problem of parametric identification of arc suppression reactor using the method of interval estimation of object parameters. The information about the operation modes of the arc suppression reactor is obtained by means of a simulation model of the object. Using the observed values, the object parameters are obtained by use of the inverse function to the simulation model. The dependence of the object parameters on the observed parameters is approximated using upper and lower parameter estimation models. The quantile regression method was applied to tune the estimation models. The need to increase the generalization ability of the algorithm is revealed. The method of adjustment of parameters of regularization of learning process to increase generalization ability of algorithm without increase of informativity of data in a training sample is offered. The results of algorithm performance are presented on the example of magnetization branch parameters estimation of arc suppression reactor. The boundaries of the interval of equivalent magnetic core loss resistance and magnetizing inductance are obtained. The limitations of the methods are analyzed, and recommendations for improving the quality of the algorithms are given.

References

1. Vasilyeva S.N., Kahn Y.S. Metod linearizatsii dlya resheniya zadachi kvantil’noi optimizatsii s funktsiei poter’, zavisyashchei ot vektora malykh sluchainykh parametrov [Linearization method for solving the quantile optimization problem with the loss function depending on the vector of small random parameters]. Automation and telemechanics, 2017, no. 7, pp. 95–109.
2. Gorban I.I. Mnogoznachnye velichiny, posledovatel’nosti i funktsii [Multivalued values, sequences and functions]. Matematicheskie mashiny i sistemy, 2012, no. 3, pp. 147–161.
3. Dementiy Yu.A., Nikolaev K.P. Opredelenie induktivnosti DGR v bazise mgnovennykh velichin [Determination of inductance of DGR in the basis of instantaneous quantities]. In: Dinamika nelineinykh diskretnykh elektrotekhnicheskikh i elektronnykh sistem: materialy XIV Vserossiiskoi nauch.-tekhn. konf. [Proc. of 14^th All-Russian Sci. Conf. «Dynamics of nonlinear discrete electrical and electronic systems»]. Cheboksary, Chuvash University Publ., 2021, pp. 343–347.
4. Dementiy Yu.A., Shornikov E.V. Mashinnoe obuchenie dlya interval’noi otsenki parametrov ob”ekta [Machine learning for interval estimation of the object parameters]. In: Sovremennye tendentsii razvitiya tsifrovykh sistem releinoi zashchity i avtomatiki: materialy nauch. -tekhn. konf. molodykh spetsialistov foruma «RELAVEKSPO – 2021» [Proc. of Sci. Conf. «Modern tendencies in development of digital systems of relay protection and automatics (RELAVEXPO-2021)»]. Cheboksary, Chuvash University Publ., 2021, pp. 153–157.
5. Dementiy Yu.A., Shornikov E.V. Primenenie aktivnogo obucheniya dlya postroeniya modelei parametricheskoi identifikatsii [The Application of Active Learning for Parametric Identification Models Development]. In: Dinamika nelineinykh diskretnykh elektrotekhnicheskikh i elektronnykh sistem: materialy XIV Vserossiiskoi nauch.-tekhn. konf. [Proc. of 14^th Sci. Conf. «Dynamics of Nonlinear Discrete Electrical and Electronic Systems»]. Cheboksary, Chuvash University Publ., 2021, pp. 446–450.
6. Dementiy Yu.A., Shornikov E.V. Regulyarizatsiya v zadache obucheniya intellektual’nykh algoritmov parametricheskoi identifikatsii [Regularization in the task of training of intelligent algorithms of parametric identification] In: Dinamika nelineinykh diskretnykh elektrotekhnicheskikh i elektronnykh sistem: materialy XIV Vserossiiskoi nauch.-tekhn. konf. [Proc. of 14^th Sci. Conf. «Dynamics of Nonlinear Discrete Electrical and Electronic Systems»]. Cheboksary, Chuvash University Publ., 2021, pp. 450–454.
7. Kuzmin A.A., Medvedev V.G., Petrov M.I., Khadyev I.G. K voprosam otsenki para-metrov aktivnoi chasti reaktora dugogasheniya s raspredelennymi zazorami [To the evaluation of active part parameters of arc-quenching reactor with distributed gaps]. Vestnik Chuvashskogo Universiteta, 2019, no.3, pp. 119–126.
8. Leytes L.V. Elektromagnitnye raschety transformatorov i reaktorov [Electromagnetic calculations of transformers and reactors]. Moscow, Energy Publ., 1981, 392 p.
9. Lyamets Y.Y., Nudelman G.S., Podshivalin A.N., Zachek Y.V. Ob informatsionnoi teorii releinoi zashchity [About information theory of relay protection]. Izvestiya Akademii elektrotekhnicheskikh nauk RF, 2009, no. 1, pp. 32–44.
10. Faleichik, A. A., Kozhevnikov A.V., Stepanov M.V. Ispol’zovanie imitatsionnogo modelirovaniya v reshenii optimizatsionnykh zadach [Using simulation modeling in solving optimization problems]. In: Nauka i obrazovanie: aktual’nye is-sledovaniya i razrabotki: materialy II Vseros. nauch.-prakt. konf. (Chita, 25–26 aprelya 2019 g.) [Proc. of 2^nd Sci. Conf. «Science and Education: current research and development»]. Chita, 2019, pp. 75–79.
11. Chernikov A.A. Kompensatsiya emkostnykh tokov v setyakh s nezazemlennoi neitral’yu [Compensation of capacitive currents in networks with ungrounded neutral]. Moscow, Energy Publ., 1974, 96 p.
12. Benavides M., Telen D., Lauwers J, Logist F., Impe J. V., Vande Wouver A. Parameter identification of the Droop model using optimal experimental design. IFAC – PapersOnLine, 2015, no. 1(48), pp. 586–591.
13. Boyd S., Vandenberghe L. Convex Optimization. Cambridge, Cambridge University Press, 2007, 716 p.

Information about the authors

Yuri A. Dementiy – Candidate of Technical Sciences, Head of the Group, Relematika LLC, Russia, Cheboksary (dementiy.yu.a@gmail.com).

Evgeny V. Shornikov – Researcher-Engineer, Relematika LLC, Russia, Cheboksary (shornikov.ev.vl@gmail.com).

Kirill P. Nikolaev – Technician-Researcher, Relematika LLC, Russia, Cheboksary (nikolaev.kirill.p@mail.ru).

For citations

Dementiy Yu.A., Shornikov E.V., Nikolaev K.P. SMART ALGORITHM FOR INTERVAL ESTIMATION OF ARC-QUENCHING REACTOR PARAMETERS. Vestnik Chuvashskogo universiteta, 2021, no. 3, pp. 64–72. DOI: 10.47026/1810-1909-2021-3-64-72 (in Russian).

Download the full article