Modern capabilities of intelligent control systems are increasingly being used in areas previously considered the exclusive work of people — experts with relevant experience in a particular field. Machine learning capabilities in the field of electric power industry, obtaining forecasts based on the data of intelligent sensors of various purposes are not an exception. At present the Russian Government has adopted a program for the development of the manufacturing industry until the end of 2035: during this time manufacturing output should grow by 192 %. It is obvious that this program should also meet the requirements of the modern scientific concept of industrial revolution "Industry 4.0", when manufacturing enterprises and corporations begin to develop and apply subsystems and elements of "smart manufacturing", which help to build intelligent communications between individual tasks and operations during the entire life cycle of production, in accordance with the principles and methods of systems engineering. It is important to note that the issues of intelligent management in the subject-oriented area of electric power industry (in our case — energy saving), as the basis of any industrial production in modern conditions, require the development and implementation, first of all, of new solutions based on modern IT-technologies. It is known that energy intensity in Russia, according to the World Bank, is 3-4 times lower than in European countries. It is also known that in connection with the new provisions in the field of housing and communal services, aimed at improving economic efficiency in terms of electricity consumption, it becomes very important to ensure its accurate and operational accounting with the possibility of further forecasting of electricity consumption and the state of power grid facilities, which will allow specialized organizations and services, as well as the managing bodies in the shortest time to make a balanced specialized decisions This paper proposes the concept of intelligent control system to manage the process of condition monitoring based on data from intelligent sensors. The novelty of the concept is to consider a variant of solving the problem of integration of information systems associated with weakly structured subject-oriented information flows in the electric power industry enterprise by using methods of set theory and category theory.

The concept of "Digital Transformation 2030", which defines the national goals and strategic objectives of the development of the Russian Federation for the period up to 2030, specifies specialized goals and objectives that are an important message for the introduction of intelligent information management technologies in the electric power industry. The main challenges for the transition to digital transformation are the increase in the rate of growth of tariffs for the end consumer, the increasing wear and tear of the network infrastructure, the presence of excessive network construction and the increase in requirements for the quality of energy consumption. The determining factor in the possibility of developing an effective energy policy is the forecasting of electricity consumption using artificial intelligence methods. One of the methods for implementing the above is the development of an artificial neural network (ANN) to obtain an early forecast of the amount of required (consumed) electricity. The obtained predictive values open up the possibility not only to build a competent energy policy by increasing the energy efficiency of an energy company, but also to carry out specialized energy-saving measures in order to optimize the organization’s budget. The solution to this problem is presented in the form of an artificial neural network (ANN) of the second generation. The main advantages of this ANN are its versatility, fast and accurate learning, as well as the absence of the need for a large amount of initial da-ta for a qualitative forecast. The ANN itself is based on the classical neuron and the error back-propagation method with their further modification. The coefficients of learning rate and sensitivity have been added to the error backpropagation method, and the coefficient of response to anomalies in the time series has been introduced into the neuron. This made it possible to significantly improve the learning rate of the artificial neural network and improve the accuracy of predictive results. The results presented by this study can be taken as a guideline for energy companies when making decisions within the framework of energy policy, including when carrying out energy saving measures, which will be especially useful in the current economic realities.