Use BP Neural Network set up the Corrosion Prediction Model of Low Temperature Parts of Atmospheric Pressure Device

被引：4

作者：

Fan, Yu Guang ^{[1
]}

Piao, Zai Dong ^{[1
]}

Chen, Bing ^{[1
]}

Lin, Hong Xian ^{[1
]}

Yang, Yang ^{[1
]}

机构：

[1] Xian Shiyou Univ, Coll Mech Engn, Xian 710065, Shaanxi, Peoples R China

来源：

MECHANICAL ENGINEERING AND MATERIALS, PTS 1-3 | 2012年 / 152-154卷

关键词：

Atmospheric pressure device; Neural network; Corrosion; Predict;

D O I：

10.4028/www.scientific.net/AMM.152-154.1138

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

In research of the low temperature parts of atmospheric pressure device, by using BP neural network, the connection of PH value, Cl-, H2S and Fe+2 was setup which can predict Fe+2 content accurately, and obtain the requirement accuracy, hence more accurate corrosion can be predicted and providing more suggests for corrosion protection. This paragraph includes the DUSHANZI petrochemical atmospheric pressure equipment files, pipeline and the archives of each equipment material content data, and then analysis the corrosion situation, concludes the corrosion types mainly about(I)Low temperature HCl-H2S-H2O corrosion. (2) High temperature naphthenic acid corrosion. (3) High temperature S and H2S corrosion. Among them, the corrosion of the low temperature parts of atmospheric pressure device is seriously affected the safety of the oil production, also it is the main corrosion of atmospheric device. The low temperature parts of DUSHANZI petrochemical atmospheric pressure device will be a training sample of neural network, to build a corrosion prediction model.

引用

页码：1138 / 1142

页数：5