Ekaterina Alexandrova | 02/26/2021
Perm Polytechnic scientists have developed an intelligent module to control a local heating system.
Neural networks will help to accurately and quickly calculate the temperature of the coolant at the outlet of the boiler room. The technology allows you to maintain it in the norm among consumers, to avoid unnecessary overheating
coolant and save money on heating. The development has no analogues in Russia yet.
“Nowadays, control units are widely used, which automatically maintain the set temperature at the outlet from the boiler room. The required values are determined by the operator, mainly
focusing on the thermometer and available feedback. Our development involves control using such neural networks that use in calculations not only the current temperature value
environment, but also a reasonable forecast. This makes it possible to estimate the temperature of the medium in advance and avoid “lagging”, – says the associate professor of the Department of Computational Mathematics, Mechanics and
biomechanics of the Perm Polytechnic, candidate of technical sciences Vladimir Oniskiv.
To train the neural network, scientists used a large amount of statistical data. It includes synchronized coolant temperatures at various points of the heating network and ambient temperatures
Scientists have tested an intelligent module by integrating it into the hardware and software automated control system “Aurora. Heat balance in housing and communal services “, which was developed and used by one of the
companies of the Perm region. As a result, the complex makes it possible to automatically regulate the temperature of the coolant at the outlet of the boiler room, taking into account the forecast of changes in weather conditions.
“To ensure comfortable thermal conditions in consumers’ homes, heat supply organizations must constantly monitor the temperature state of the network. But this service is not yet available for
most heating companies, so they insure their risks by maintaining higher values of the coolant temperature. As a result, residents are often forced to overpay for utility bills.
services, ”explains the researcher.
According to scientists, the use of a neural network in the control processes of a heat network allows you to save fuel and prevent overspending. With sudden changes in the weather, this effect becomes
especially significant. Gas savings can reach 10-15%, depending on the outside air temperature and the general condition of heating networks.
Multilayer neural networks and deep learning networks are able to predict the required boiler temperature, taking into account the weather forecast and the characteristics of the movement of the coolant.
In the process of creating an intelligent module, scientists analyzed various types of neural networks. The resulting architecture consists of 224 neurons arranged in three layers. Calculated temperature
of the coolant at the outlet of the boiler room provides those temperatures at the entrance to the house, which are required by standards.