Open AccessResidual life prediction of mining cables based on RBF neural network
Author(s) -
Weili Wu,
Jing Yang,
Lei Li,
Weijun Fan
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1754/1/012194
Subject(s) - artificial neural network , residual , radial basis function , loss factor , predictive modelling , computer science , engineering , reliability engineering , artificial intelligence , machine learning , dielectric , algorithm , electrical engineering
The RBF (Radial basis Function) neural network forecasting model is constructed for the mine cable life prediction problem. According to the mine cable in line with the characteristics of accelerated life test, the temperature and the dielectric loss factor are chosen as the model input. In order to solve the problem that the number of training samples is too small and detection samples cannot be constructed, the dielectric loss factor and aging time in each temperature segment collected are linearly interpolated to generate a large number of simulation data as training target vectors, and the RBF neural network is established for life prediction. Then the predicted life value is compared with the design life of the cable for verification. The result confirms that the RBF neural network model can reflect the relationship between the dielectric loss factor and residual life under a certain humidity and the different levels of temperature, which has certain practical significance for the prediction of cable insulation life.