Abstract:
This article explores the use of machine
learning algorithms to identify anomalies in the solar
heating system. A solar heating system that has been
developed consists of several parts to simplify the
description and modeling process. The authors propose a
new architecture for neural networks based on ordinary
differential equations. The idea is to apply the new
architecture for practical problems of accident
prediction (the problem of extrapolation of time series)
and classification (classification of accidents based on
historical data). The developed machine learning
algorithms, artificial intelligence techniques, the theory
of differential equations - these directions allow us to
build a model for predicting the system's accident rate.
The theory of database management (non-relational
databases) - these systems allow you to establish the
optimal storage of large time series.
