Hits:

Indexed by:会议论文

Date of Publication:2010-06-20

Included Journals:EI、Scopus

Volume:4

Page Number:206-210

Abstract: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).