Open AccessInsulation failures prognosis in electric machines: preventive detection and time to failure forecast
Author(s) -
Guedes Armando S.,
Silva Sidelmo Magalhaes
Publication year - 2020
Publication title -
iet electric power applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.815
H-Index - 97
eISSN - 1751-8679
pISSN - 1751-8660
DOI - 10.1049/iet-epa.2019.0711
Subject(s) - artificial neural network , reliability engineering , autoregressive model , identification (biology) , work (physics) , engineering , line (geometry) , voltage , computer science , machine learning , electrical engineering , mechanical engineering , mathematics , statistics , botany , geometry , biology
This work presents a new approach to the on‐line evaluation of the insulation of electric machines. Through the proposed system, it is possible to identify the stress agents causing the degradation of the insulation of low‐ and medium‐voltage machines. In addition, the estimation of the time‐to‐failure (TF) of the insulation is developed based on linear stochastic models autoregressive moving average and artificial neural networks. The identification of the stress agent and the estimation of the TF give a complete prognosis for the predictive monitoring of the machine insulation.