MULTI-STAGE METHOD FOR SHORT-TERM FORECASTING OF TEMPERATURE CHANGES MODES IN THE POWER CABLE
Abstract
The article is devoted to research on the creation of diagnostics and prediction of thermofluctuation processes of insulating materials of power cable lines (PCL) of electric power systems based on such methods of artificial intelligence as neural networks and fuzzy logic. The necessity of developing a better methodology for the analysis of thermal conditions in PCL is shown. The urgency of the task of creating neural networks (NS) for assessing the throughput, calculating and predicting the temperature of PCL conductors in real time based on the data of the temperature monitoring system, taking into account changes in the current load of the line and the external conditions of the heat sink, is substantiated. Based on the main criteria, traditional and neural network algorithms for forecasting are compared, and the advantage of NS methods is shown. The classification of NS methods and models for predicting the temperature conditions of cosmic rays has been carried out. The proposed neural network algorithm for predicting the characteristics of electrical isolation was tested on a control sample of experimental data on which training of an artificial neural network was not carried out. The forecast results showed the effectiveness of the selected model. To solve the problem of PCL resource prediction, a network was selected with direct data distribution and back propagation of the error, because Networks of thistype, together with the activation function in the form of a hyperbolic tangent, are to some extent a universal structure for many problems of approximation, approximation, and forecasting. A neural network was developed to determine the temperature regime of a current-carrying core of a power cable. A comparative analysis of the experimental and calculated characteristics of the temperature distributions was carried out, while various load modes and the functions of changing the cable current were investigated. When analyzing the data, it was determined that the maximum deviation of the data received from the neural network from the data of the training sample was less than 2.2 %, which is an acceptable result. The model can be used in devices and systems for continuous diagnosis of power cables by temperature conditions.
References
[Regulation of JSC "Rosseti" on the unified technical policy in the electric grid complex].
Moscow: OAO «Rosseti», 2013, 196 p.
2. Anishchenko V.A., Kolosova I.V. Osnovy nadezhnosti sistem elektrosnabzheniya [Fundamentals
of reliability of power supply systems]. Minsk: BNTU, 2007.
3. Dubyago M.N., Poluyanovich N.K. Sovershenstvovanie metodov diagnostiki i
prognozirovaniya elektroizolyatsionnykh materialov sistem energosnabzheniya [Improving
methods of diagnostics and forecasting of electrical insulation materials of power supply systems].
Rostov-on-Don; Taganrog: Izd-vo YuFU, 2019, 192 p.
4. Katalog oborudovaniya kompanii LIOS Technology GmbH – 2010 [Directory of equipment of
the company lios Technology GmbH – 2010].
5. GOST R MEK 60287-1-1. Kabeli elektricheskie. Raschet nominal'noy tokovoy nagruzki.
Ch. 1-1. Uravneniya dlya rascheta nominal'noy tokovoy nagruzki i raschet poter'. Obshchie
polozheniya [GOST R IEC 60287-1-1. Electrical cables. Calculation of the rated current load.
Part 1-1. Equations for calculating the rated current load and calculating losses. Generalities].
Moscow: Standartinform, 2009, 28 p.
6. GOST R MEK 60287-1-2. Kabeli elektricheskie. Raschet nominal'noy tokovoy nagruzki.
Ch. 1-2. Uravneniya dlya rascheta nominal'noy tokovoy nagruzki i raschet poter'. Koeffitsienty
poter', obuslovlennykh vikhrevymi tokami v obolochke, dlya dvukh tsepey, raspolozhennykh v
odnoy ploskosti [GOST R IEC 60287-1-2. Electrical cables. Calculation of the rated current
load. Part 1-2. Equations for calculating the rated current load and calculating losses. Coefficients
of losses due to eddy currents in the shell for two circuits located in the same plane].
Moscow: Standartinform, 2009, 23 p.
7. GOST R MEK 60287-2-2. Kabeli elektricheskie. Raschet nominal'noy tokovoy nagruzki.
Ch. 2-2. Teplovoe soprotivlenie. Metod rascheta koeffitsientov snizheniya maksimal'no
dopustimoy tokovoy nagruzki dlya grupp kabeley, prolozhennykh na vozdukhe i
zashchishchennykh ot pryamogo solnechnogo izlucheniya [GOST R IEC 60287-2-2. Electrical
cables. Calculation of the rated current load. Part 2-2. Thermal resistance. Method for calculating
the reduction coefficients of the maximum permissible current load for groups of cables
laid in the air and protected from direct solar radiation]. Moscow: Standartinform, 2009, 12 p.
8. Larina E.T. [i dr.]. Raschet perekhodnykh teplovykh rezhimov odnozhil'nogo silovogo kabelya
s plastmassovoy izolyatsiey, prolozhennogo v vozdukhe [Calculation of transient thermal
modes of a single-core power cable with plastic insulation laid in the air], Elektrotekhnika
[Electrical Engineering], 1991, No. 10, pp. 39-42.
9. Titkov, V.V. K otsenke teplovogo rezhima trekhfaznoy linii iz SPE-kabelya [On the estimation
of the thermal regime of a three-phase line from a SPE cable], Kabel'news [Cable-news], 2009,
No. 10, pp. 47-51.
10. Neher J.M., McGrath M.H. The calculation of the temperature rise and load capability of cable
systems, Philadelphia electric company, October 1957, pp. 752-763.
11. Leon F. Calculation of underground cable ampacity, CYME international T&D Inc., 2005.
12. Melamed M.A. Sovremennye metody analiza i prognozirovaniya rezhimov elektropotrebleniya
v elektroenergeticheskikh sistemakh [Modern methods of analysis and forecasting of power
consumption in electric power systems], Itogi nauki i tekhniki. Seriya «Energeticheskie sistemy
i ikh avtomatizatsiya» [Itogi Nauki i Tekhniki. Series Energy systems and their automation],
1988, Vol. 4, pp. 4-111.
13. Gross G. and Galiana F.D. Short term load forecasting, Proc. IEEE, 1987, Vol. 75, No. 12,
pp. 1558-1573.
14. Chen S.T., David C.Y., Moghaddamjo A.R. Weather sensitive short-term load forecasting using
non fully connected artificial neural network, IEEE Trans. on Power Systems, 1992, Vol. 7,
No. 3, pp. 1098-1105.
15. Hsy Y., Ho K. Fuzzy expert systems: An application to short term load forecasting, IEE Proceedings
– C, 1992, Vol. 139, No. 6, pp. 471-477.
16. Lee K.Y., Park J.H. Short-term load forecasting using an artificial neural network, IEEE Trans.
on Power Systems, 1992, Vol. 7, No. 1, pp. 124-130.
17. Meldorf M., Kilter J., Pajo R. Comprehensive Modelling of Load, CIGRE Regonal Meeting,
June 18-20, 2007, Tallinn, Estonia, pp. 145-150.
18. Shumilova G.P., Gotman N.E., Startseva T.B. Prognozirovanie elektricheskikh nagruzok EES s
ispol'zovaniem metodov iskusstvennogo intellekta [Prediction of electric loads of EPS using
artificial intelligence methods], Sb. trudov Rossiyskogo natsional'nogo simpoziuma po
energetike. Kazan' 10–14 sent. 2001 g. [Proceedings of the Russian National Symposium on
Energy, Kazan, September 10-14. 2001]. Moscow: KGEU, 2001, pp. 103-106.
19. Khaykin S. Neyronnye seti: polnyy kurs [Neural networks: full course]. 2nd ed. Moscow: Izd.
dom «Vil'yams», 2006, 1104 p.
20. Rutkovskaya D., Pilin'skiy M., Rutkovskiy L. Neyronnye seti, geneticheskie algoritmy i
nechetkie sistemy [Neural networks, genetic algorithms and fuzzy systems]: trans. from polish
I.D. Rudinskogo. Moscow: Goryachaya liniya – Telekom, 2008, 452 p.
21. Krichevskiy M.L. Intellektual'nyy analiz v menedzhmente [Intelligent analysis in management].
Saint Petersburg: SPbGUAP, 2005, 48 p.
22. Sidorov S.G. i dr. Mnogoprotsessornaya realizatsiya neyrosetevogo algoritma
prognozirovaniya izmeneniya kharakteristik elektricheskoy izolyatsii [Multiprocessor implementation
of a neural network algorithm for predicting changes in the characteristics of electrical
insulation], Vestnik IGEU [Bulletin of the ISEU], 2011, Issue 1.
23. Poluyanovich N.K., Dubyago M.N. Prognozirovanie resursa kabel'nykh liniy s ispol'zovaniem
metoda iskusstvennykh neyronnykh setey [Prediction of the resource of cable lines using the
method of artificial neural networks], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU.
Engineering Sciences], 2019, No. 3 (205), pp. 51-62.
24. Galushka V.V., Fathi V.A. Formation of the training sample by using artificial neural networks
in search problems database errors, Inženernyj vestnik Dona (Rus.), 2013, No. 2. Available at:
ivdon.ru/ru/magazine/archive/n2y2013/1597/.
25. Dubyago M.N., Poluyanovich N.K. Metod otsenki i prognozirovaniya ostatochnogo resursa
izolyatsii kabel'nykh liniy [A method for assessing and predicting the residual life of insulation
of cable lines], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences],
2019, No. 3, pp. 132-143.
