Residual Life Prediction of Mine Cable Based on RBF Neural Network

Wen-ling FAN, Xian-min MA, Lei LI

Abstract


In this paper, the RBF (Radial basis Function) neural network forecasting model is constructed for the mine cable life prediction problem. As the mine cable is in line with the characteristics of accelerated life test, the temperature and the dielectric dissipation factor are chosen as the model input. In order to obtain the enough sample data and to construct the detecting sample possibly, using the linear interpolation generates a large amount of simulation data as the training target vector, RBF neural network is established accessibly for life prediction. Then life prediction value and design life was verified and the result confirms that the RBF neural network model can reflect the relationship between the dielectric dissipation factor and residual life under a certain humidity and different levels of temperature. The residual life prediction of cable insulation can protect the safety of underground power supply.

Keywords


Cable life prediction, RBF neural network, Temperature, Dielectric dissipation factor


DOI
10.12783/dtcse/aiie2017/18222

Full Text:

PDF

Refbacks

  • There are currently no refbacks.