The article is devoted to research of thermofluctuation processes of insulating materials of power cable lines (SCR) of electric power systems. It was established that an artificial neural network (ANN) can be used to compile a forecast of the temperature regime of a current-carrying core with an accuracy of 2.5% of the actual value of the core temperature. The comparison of the predicted values with the actual ones allows us to talk about the adequacy of the selected network model and its applicability in practice for reliable operation of the cable system of power supply to consumers. The development of an intelligent system for predicting the temperature of the core SCR contributes to the planning of the operating modes of the power grid in order to increase the reliability and energy efficiency of their interaction with the integrated power system.
Keywords: Neural networks, thermofluctuation processes, insulation materials, neural network architecture
The model of the occurrence of failures as a result of aging of insulation materials of power cable lines is considered. It is shown that the residual life depends on the ratio of the safety margin and the ultimate strength of the materials used. A simulation of the resource actuation processes was carried out using a mathematical model of the insulation state that relates the time and probability of its trouble-free operation with certain parameters of it. The model allows to predict the state of the insulation and the service life of the power cable lines.
Keywords: Reliability, life, insulation materials, heat aging