点击次数：

论文类型：期刊论文

发表时间：2012-04-01

发表刊物：Journal of Computational Information Systems

收录刊物：EI、Scopus

卷号：8

期号：7

页面范围：2999-3006

ISSN号：15539105

摘要：Thermal lifetime estimation of low voltage ethylene propylene rubber (EPR) shipboard power cables using artificial neural network (ANN) is discussed in this paper. In order to provide enough data for the artificial neural network and to investigate the correlation among elongation-at-break, temperature and lifetime of the insulation, thermal accelerated aging studies were conducted. The assessment method using a three-layer feed forward neural network with back propagation error was proposed. Predicted and experimental results are comparatively analyzed to prove that ANN is a suitable alternative to traditional, expensive and time consuming experiments. The method discussed in this paper can be extended to other different types of power cables. ? 2012 Binary Information Press.