IMPLEMENTATION OF INFORMATION MODELS OF DIAGNOSING AND PREDICTION OF CURRENT TRANSFORMER INSULATION STATE

Abstract

Listen

Translate article

The article deals with the problem of the development of the Unified Modeling Language-models such as use cases, classes, activities, conditions and sequences of interaction of components to diagnose the state of current transformers insulation. The purpose of the work is to improve the efficiency of diagnosing and prediction of current transformers primary insulation state using modern software. The object of research is the process of diagnosing of current transformers primary insulation state. The subject of research is the neural network models, by which the prediction of the insulation state is performed. The novelty lies in the fact that the developed information models allow realizing the neural network models of diagnosing and prediction of current transformer insulation state independently of the selected programming language. Experiments confirming the adequacy of the proposed model have been executed. The practical value of the work consists in the fact that by using the proposed UML-models the software that allows diagnosing and prediction of current transformer insulation state is developed.