摘要
油气管道腐蚀作用机理复杂,诸多因素存在模糊性与相互关联性,对管道腐蚀速率的有效预测存在一定困难。运用具有处理线性和非线性因素能力的灰色线性回归组合模型对油气管道腐蚀进行建模,并引入BP人工神经网络模型对组合模型的残差进行修正,以进一步提高预测精度。将所建模型应用于某油气管道腐蚀速率的预测中,结果表明:所建灰色线性回归组合模型在对油气管道进行腐蚀预测时,既充分考虑到了原始数据的线性因素,又考虑了其非线性因素,预测效果较好,同时适用于解决其他复杂腐蚀体系的预测问题。
The mechanism of oil and gas pipeline corrosion is complicated, and many factors are ambiguous and interconnected, bringing difficulty to effective prediction of pipeline corrosion rate. In this paper, the grey-linear regression combination model which is capable of dealing with linear and nonlinear factors is put forward for modeling of oil and gas pipeline corrosion. Besides, the BP artificial neural network model is used to correct the residual error of the combination model, in order to further improve the accuracy of prediction. The established model is applied to predict the corrosion rate of some oil and gas pipeline. The results show that in the prediction of oil and gas pipeline corrosion, the grey-linear regression combination model takes both linear factors and nonlinear factors of original data, which is well-performed and can also be applied to predict other complex corrosion systems. （4 Figures, 2 Tables, 14 References）
出处
《油气储运》
CAS
北大核心
2015年第12期1300-1304,共5页
Oil & Gas Storage and Transportation
基金
南宁市科学研究与技术开发项目"超临界二氧化硫罐装及在亚硫酸法(制糖)清净工艺中的应用"
20131078
关键词
油气管道
灰色线性回归组合模型
BP神经网络模型
腐蚀速率
oil and gas pipeline, grey-linear regression combination model, BP neural network model, corrosion rate
