Development of a Methodology for Estimating the Heat Loss of Buildings based on Neural Networks

Abstract

The work describes a methodology for estimating the heat loss of a building, including the calculation of the heat loss of a building. In order to develop a methodology for estimating the heat loss of a building based on neural networks, the features of a wooden housing stock were studied. The stage of collecting images for training a neural network, the stage of training an optimal neural network for solving the problem of object detection are described. The technologies necessary to solve the problem are described.