GRNTI 47.61 Приборы для радиотехнических измерений
GRNTI 47.63 Системы и устройства отображения информации
BBK 302 Проектирование
It was established that methods based on artificial neural networks (HC) find the most widespread in predicting thermal processes in power cable networks. Analysis of influence of various functions of HC activation on forecast error of thermoflux processes in power cable networks was carried out. It is established that the minimum error of thermal processes prediction in power cable networks is HC with function of logsig activation in hidden layer and pureline in output layer.
information systems, neural networks, mode-leasing, electric power industry, forecasting
1. Dubyago M.N., Poluyanovich N.K. Bur'kov D.V. Razrabotka metoda prognozirovaniya processa stareniya izolyacii na osnove termofluktuacionnoj teorii chastichnyh razryadov. Inzhenernyj vestnik Dona, №3 (2017).
2. Dubyago M.N., Poluyanovich N.K. Sovershenstvovanie metodov diagnostiki i prognozirovaniya elektroizolyacionnyh materialov sistem energosnabzheniya. Rostov-na-Donu-Taganrog, 2019.
3. Poluyanovich N.K. Energeticheskaya elektronika. Posobie po resheniyu zadach i metodicheskie ukazaniya / Taganrogskij radiotekhnicheskij universitet, Kafedra teoreticheskih osnov elektrotekhniki. Taganrog, 2001.
4. Dubyago M.N., Poluyanovich N.K. The method of nondestructive testing and prediction of evolving insulation defect of power line cable. V sbornike: Proceedings of XI International SAUM Conference on Systems, Automatic Control and Measurements SAUM 2012. 2012. S. 418-422.
5. Dubyago M.N., Poluyanovich N.K., Pshihopov V.H. Metod issledovaniya termofluktuacionnyh processov v zadachah diagnostiki i prognozirovaniya izolyacionnyh materialov. Vestnik Donskogo gosudarstvennogo tekhnicheskogo universiteta. 2017. T. 17. № 3 (90). S. 117-127.
