Assessment of the current technical condition of electrical equipment based on an artificial neural network

• Published in: Journal of physics. Conference series 2021-12, Vol.2131 (5), p.52049
• Main Authors: Manusov, V Z, Otuzbaev, M R, Scherbinina, M A, Ivanov, G V
• Format: Article
• Language: English
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/2131/5/052049

Assessment of the current technical condition is an important task, so the state of electrical equipment depends on its further operability. Thanks to modern computing devices, it is possible to implement actively artificial intelligence and computer-assisted learning methods that allow achieving high efficiency in data processing. A study was conducted and an algorithm for diagnosing the technical condition based on an artificial neural network was developed. A model based on a multilayer perceptron is proposed, which allows evaluating the technical condition of a high-voltage power transformer. The result of the technical diagnostics of the model is the assignment of the condition to one of the five classes, proposed by the guidelines presented by the International Council on Large Electrical Systems. The methodology is presented on the example of a 250 MVA transformer with a certain defect history, which allowed us to show the reliability and validity of the obtained results. It is shown that the use of the proposed model makes it possible to achieve accuracy in determining the technical condition of 0.95. The introduction of this model into an automated monitoring and diagnostics system will allow assessing the technical condition of electrical equipment in real time with sufficient accuracy.