点击次数：

论文类型：会议论文

发表时间：2010-06-20

收录刊物：EI、Scopus

卷号：4

页面范围：206-210

摘要：Bayesian Regularization Neural Network is used in the estimating system for corrosion protection status survey of submarine pipeline. Firstly it discusses about the theory and approach to mend back-propagation (BP) neural network using Bayesian Regularization training algorithm, then using this algorithm to train and validate an actual Neural Network based on a particular simulation calculated model for the submarine pipeline cathodic protection system, and it was proved that this algorithm effectively improved the precision and generalization capability of BP Neural Network. This approach is used in the estimating software system and need further extension. ? 2010 by The International Society of Offshore and Polar Engineers (ISOPE).