Influencing Factors of Crude Oil Corrosion Based on Artificial Neural Network
摘 要
针对原油对储运设备腐蚀影响的复杂性, 本工作借助人工神经网络输入节点的筛选规则, 对影响原油腐蚀性的主要因素进行了筛选, 影响因素从最初的18个筛选到最后的9个; 然后分别以18个和9个因素作为输入节点构建神经网络模型, 通过对比两个模型的预测精度发现, 9个输入因素的神经网络模型预测精度更高。对单一影响因素进行敏感性分析, 研究了筛选得到的各个因素对腐蚀速率的影响规律。
Abstract
For the complexity of crude oil corrosion to transportation equipment, influencing factors of crude oil corrosion were cut down from 18 to 9 by means of a screening principle of input nodes in Artificial Neural Networks (ANN). It was found that the network model with 9 nodes in input layer had more prediction accuracy, than that with 18 nodes. The influence law of each selected factor on corrosion rate was obtained by sensitivity analysis.
中图分类号 TG174
所属栏目 试验研究
基金项目 中石油中青年创新基金(07E1021)
收稿日期 2010/6/12
修改稿日期 2010/6/28
网络出版日期
作者单位点击查看
备注任振甲, 硕士研究生,
引用该论文: REN Zhen-jia,ZHANG Jun,LUO Cheng-shuang,SHI Xin,HU Song-qing,ZHANG Yang. Influencing Factors of Crude Oil Corrosion Based on Artificial Neural Network[J]. Corrosion & Protection, 2011, 32(4): 293
被引情况:
【1】李启锐,陈晓龙, "炼厂常减压装置管线腐蚀速率的灰色预测",腐蚀与防护 35, 852-855(2014)
【2】伊帆,李德豪,郎春燕,朱越平,殷旭东, "基于BP神经网络的模拟冷却水中碳钢的腐蚀速率预测",腐蚀与防护 33, 947-951(2012)
共有人对该论文发表了看法,其中:
人认为该论文很差
人认为该论文较差
人认为该论文一般
人认为该论文较好
人认为该论文很好
参考文献
【1】王海涛, 韩恩厚, 柯伟. 基于人工神经网络模型的铝合金大气腐蚀的预测[J]. 中国腐蚀与防护学报, 2006, 26(5):272-274, 281.
【2】Srdjan Nesic, Magnus Nordsveen, Nigel Maxwell, et al. Probabilistic modeling of CO2 corrosion laboratory date using neural networks[J]. Corros Sci, 2001, 43(7):1373-1392.
【3】梅辉, 费敬银. 面向腐蚀工程的人工神经网络应用设想[J]. 腐蚀与防护, 2002, 23(1):34-38.
【4】高峰, 刘晖, 樊玉光, 等. 蒸汽管道剩余寿命评估方法评述[J]. 腐蚀与防护, 2008, 29(5):295-298.
【5】高大文, 王鹏, 孙丽欣, 等. 人工神经网络输入层节点筛选规则的确定[J]. 高技术通讯, 2002(6):65-68.
【6】黄鉴主编. 进口原油评价数据集[M]. 北京:中国石化出版社, 2001.
【7】Hernández S, Nesic S, Weckman G, et al. Use of artificial neural networks for predicting crude oil effect on CO2 corrosion of carbon steels[C]//Corrosion/2005, Paper No.05554.
【8】赵国仙, 吕祥鸿, 韩勇. 流速对P110钢腐蚀行为的影响[J]. 材料工程, 2008(8):5-8.
【9】Vera J R, Viloria A, CastillO M, et al. Flow velocity effect on CO2 corrosion of carbon steel using a dynamic field tester (A). A working party report on prediction CO2 corrosion in oil and gas industry[C]//London:The Institute of Materials, 1994:94-119.
【2】Srdjan Nesic, Magnus Nordsveen, Nigel Maxwell, et al. Probabilistic modeling of CO2 corrosion laboratory date using neural networks[J]. Corros Sci, 2001, 43(7):1373-1392.
【3】梅辉, 费敬银. 面向腐蚀工程的人工神经网络应用设想[J]. 腐蚀与防护, 2002, 23(1):34-38.
【4】高峰, 刘晖, 樊玉光, 等. 蒸汽管道剩余寿命评估方法评述[J]. 腐蚀与防护, 2008, 29(5):295-298.
【5】高大文, 王鹏, 孙丽欣, 等. 人工神经网络输入层节点筛选规则的确定[J]. 高技术通讯, 2002(6):65-68.
【6】黄鉴主编. 进口原油评价数据集[M]. 北京:中国石化出版社, 2001.
【7】Hernández S, Nesic S, Weckman G, et al. Use of artificial neural networks for predicting crude oil effect on CO2 corrosion of carbon steels[C]//Corrosion/2005, Paper No.05554.
【8】赵国仙, 吕祥鸿, 韩勇. 流速对P110钢腐蚀行为的影响[J]. 材料工程, 2008(8):5-8.
【9】Vera J R, Viloria A, CastillO M, et al. Flow velocity effect on CO2 corrosion of carbon steel using a dynamic field tester (A). A working party report on prediction CO2 corrosion in oil and gas industry[C]//London:The Institute of Materials, 1994:94-119.
相关信息