Forecast model for inner corrosion rate of oil pipeline based on GA-SVM

摘要：

　　In order to improve the prediction precision of inner corrosion rate of oil pipeline, this paper proposed a novel forecast model, which combined the global optimization ability of genetic algorithm and the superior regression performance of a support vector machine, for inner corrosion rate of oil pipeline.As the proposed model can reduce the dimensionality of data space and preserve features of inner corrosion rate of oil piepline, compared with BP neural network model, the proposed GA-SVM model had higher accuracy and speed, and the maximum error is 0.6%.Thus, it provided a new approach for the forecast of inner corrosion rate of oil piepline.

关键词： inner corrosion rate oil pipeline GA SVM forecast model

作者: Jingcheng LIU Hongtu WANG

作者单位: Key Laboratory for Exploitation of Southwestern Resources & Environmental Disaster Control Engineeri Key Laboratory for Exploitation of Southwestern Resources & Environmental Disaster Control Engineeri

会议类型: 国内会议

会议名称: 2011全国特殊气藏开发技术研讨会

会议地点: 重庆

会议语种:英文

页码: 264-270

在线出版日期: 2011-11-01（万方平台首次上网日期，不代表论文的发表时间）