Application of neural network technologies in power engineering

Abstract

In this work, key areas of artificial neural networks using in the energy sector are highlighted. The application of neural network technologies to assess the current technical condition of energy equipment, systems and tools for various purposes is implemented on classification algorithms, allowing to establish the degree of closeness of the current technical state to the “normal” state through the use of key technological (diagnostic) parameters. The prediction of operating modes (normal, emergency, etc.), the occurrence of defects, failures and accidents is carried out by establishing functional dependencies using historical data on the operation of power equipment. The data accumulated for different periods are used to predict the consumption of various types of energy and loads during these periods. On the basis of neural network algorithms, operational intelligent control of the operating modes of energy facilities is implemented, and systems for dispatch control, decision support, repair management, etc. are developed.

Power Equipment Defects Prediction Based on the Joint Solution of Classification and Regression Problems Using Machine Learning Methods

“…The training of a recurrent neural network can be carried out by the error backpropagation method [53], the schematic digram of which in relation to RNN is shown in Figure 2. Thus, during training, after calculating the output signal (the initial stage), the error functional ( 6) is determined (in regression problems, the root of the standard deviation between the answers RNN output t and the values from the response space y t is used).…”

“…The weights are updated using the backpropagation method. In contrast to the standard model of a recurrent neural network, the values of the gradients during gradient descent operations remain stable due to the structure of the LSTM of recurrent neural networks [53].…”