Heat Exchange Equipment Technical Condition Assessment Using Machine Learning on the Example of Condenser Tubes Contamination

The article considers the issue of creating a system for assessing the technical condition of heat exchange equipment using machine learning using the example of condenser tube contamination. An approach based on training machine learning models using a data set generated based on a computer model of a digital twin of an object is proposed. The paper describes the development of a simplified dynamic model of a thermal power plant condenser, the creation of a machine learning model for determining the average thickness of contamination. An assessment of the accuracy of the resulting model is given. Methods for increasing the accuracy of determining the current technical condition and, as a result, the accuracy of the forecast are proposed.