基于模糊神经网络的海洋管线腐蚀速率预测新方法

doi:10.11902/1005.4537.2014.221

中国腐蚀与防护学报

2015, Vol. 35

Issue (6): 571-576 DOI: 10.11902/1005.4537.2014.221

研究报告

本期目录 | 过刊浏览

基于模糊神经网络的海洋管线腐蚀速率预测新方法

邓志安(

),李姝仪,李晓坤,王珊,王晓军

西安石油大学石油工程学院西安 710065

A Prediction Method Based on Fuzzy Neural Network for Corrosion Rate of Marine Pipelines

Zhian DENG(

),Shuyi LI,Xiaokun LI,Shan WANG,Xiaojun WANG

College of Petroleum Engineering, Xi'an Shiyou University, Xi'an 710065, China

全文: PDF(669 KB) HTML

摘要:

针对海洋环境中油气管线腐蚀速率预测的复杂问题,提出了灰色关联分析与模糊神经网络结合的新方法对管线腐蚀速率进行预测。首先使用灰色关联分析对管线腐蚀速率与环境因素进行关联度计算,优选关联度较高的若干参数,然后应用模糊神经网络寻找管线腐蚀速率与优选环境因素之间的映射关系,使得影响管线腐蚀的主要因素数量明显减少,降低了预测难度。还根据管线已有腐蚀速率统计数据对该方法进行了测试,结果表明,管线腐蚀速率预测的平均相对误差为5.96%,方法在减少环境因素数量的情况下仍具有良好的预测精度。因此,基于灰色关联分析与模糊神经网络的新方法能够根据环境因素快速准确地预测管线的腐蚀速率,对保障管线的安全运营具有指导意义。

关键词 ：模糊神经网络, 管线腐蚀, 预测, 灰色关联分析

Abstract：

An intelligent method based on fuzzy neural network and grey correlation analysis was proposed to predict the corrosion rate of oil and gas pipelines in marine environment. Through correlation analysis, the correlation between the corrosion rate of pipelines and environmental factors was built, and from which then the appropriate factors with high correlation could be picked out. Finally, the mapping relationship between the corrosion rate of pipelines and environmental factors could be figured out through fuzzy neural network. The validity and reliability of the results predicted by the proposed method were tested with statistic data which involved different environmental factors, it follows that the average relative error of the predicted corrosion rate was 5.96%, in other words, the present method exhibited a good accuracy in prediction even that less environmental factors were involved during the analysis process. Therefore, the method based on fuzzy neural network and grey correlation analysis, can predict the corrosion rate of pipelines rapidly and accurately with the known environmental factors.

Key words： fuzzy neural network pipeline corrosion prediction grey correlation analysis

基金资助:国家自然科学基金项目 (51274166) 资助

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	邓志安
	李姝仪
	李晓坤
	王珊
	王晓军
44.8K

引用本文:

邓志安,李姝仪,李晓坤,王珊,王晓军. 基于模糊神经网络的海洋管线腐蚀速率预测新方法[J]. 中国腐蚀与防护学报, 2015, 35(6): 571-576.
Zhian DENG, Shuyi LI, Xiaokun LI, Shan WANG, Xiaojun WANG. A Prediction Method Based on Fuzzy Neural Network for Corrosion Rate of Marine Pipelines. Journal of Chinese Society for Corrosion and protection, 2015, 35(6): 571-576.

链接本文:

https://www.jcscp.org/CN/10.11902/1005.4537.2014.221 或 https://www.jcscp.org/CN/Y2015/V35/I6/571

图1 T-S模糊神经网络的拓扑结构

图2 实验步骤

Serial number	Oceantemperature / ℃	Dissolved oxygen / mg·L^-1	Salinity10³ mg·L^-1	pH	Redox potential / mV	Corrosion rateμA·cm^-2
1	25.90	6.71	30.10	5.10	378	16.40
2	29.35	6.09	29.00	6.30	400	16.90
3	27.90	6.18	31.50	7.00	363	15.57
4	24.00	7.95	30.20	8.10	324	13.65
5	28.00	5.05	31.40	9.20	240	13.24
6	27.32	3.21	29.31	8.20	281	12.91
7	27.87	6.55	31.68	7.20	356	14.06
8	28.27	6.98	28.20	6.60	384	15.47
9	30.70	7.15	31.74	6.50	401	16.28
10	29.37	6.82	30.12	6.20	414	17.11
11	24.27	0.80	32.56	8.10	717	3.61
12	27.45	2.60	35.37	7.96	287	7.94
13	27.23	4.20	31.94	7.89	289	9.63
14	27.48	5.90	32.39	7.83	331	10.58
15	28.75	6.80	32.22	8.00	340	11.43
16	28.52	8.40	32.10	8.01	345	12.52
17	28.45	9.90	31.95	7.93	309	22.64
18	23.95	7.61	9.17	8.04	231	10.94
19	24.73	6.06	17.33	7.88	321	11.45
20	24.60	7.52	24.42	7.57	210	11.83
21	24.51	7.02	32.00	8.16	308	12.55
22	23.65	6.51	41.34	7.67	245	8.40
23	16.74	7.11	33.55	8.25	178	10.85
24	21.11	6.03	33.44	8.03	295	11.45
25	25.57	6.70	32.19	8.09	325	11.87
26	31.16	4.38	33.21	7.94	242	8.92
27	24.27	0.80	32.56	8.10	171	2.55
28	27.45	2.60	35.37	7.96	287	10.96
29	27.23	4.20	31.94	7.89	289	12.00
30	28.72	6.80	32.21	8.00	325	13.33
31	28.52	8.40	32.10	8.01	345	17.31
32	28.45	9.90	31.95	7.93	309	22.48
33	23.95	7.61	9.17	8.04	231	8.13
34	24.95	6.80	16.29	7.82	341	9.07
35	24.60	7.52	24.42	7.57	210	10.74
36	27.32	3.12	29.31	8.20	281	13.59
37	24.00	7.95	30.20	8.10	324	12.89
38	27.78	6.35	31.38	7.20	356	13.61
39	27.97	6.05	31.94	6.60	384	14.60
40	30.70	7.15	31.74	6.50	401	15.00
41	29.37	6.82	30.12	6.20	414	15.39
42	29.35	6.09	29.00	6.30	400	16.45
43	27.00	6.70	30.70	7.00	350	12.60
44	27.90	5.15	31.50	9.20	264	9.08
45	25.55	6.67	31.00	8.09	320	12.49
46	24.31	6.42	40.67	7.88	250	8.75
47	24.11	6.38	41.00	7.98	228	8.99
48	17.45	7.48	34.08	8.10	135	17.05
49	21.95	8.28	34.64	7.95	113	17.34
50	27.19	4.91	33.50	7.99	275	15.48

表1 实海挂片腐蚀实验数据[1]

图3 各影响因素的关联度

表2 FNN预测结果与文献[1]中BP人工神经网络预测结果的对比

图4 腐蚀速率预测结果与实验数据的对比

表3 不同参数的测试对比

图5 测试结果的误差对比

[1]	Hu G.Study on submarine pipeline corrosion detection and corrosion prediction [D]. Chongqing: Chongqing University, 2007
[1]	(胡舸. 海底管线腐蚀检测与腐蚀预测的研究 [D]. 重庆: 重庆大学, 2007)
[2]	Piao Z D.The research of the corrosion forecast and control of FCC device and system [D]. Xi'an: Xi'an Shiyou University, 2012
[2]	(朴在栋. 催化裂化装置及系统腐蚀预测与控制的研究 [D]. 西安: 西安石油大学, 2012)
[3]	Hu S Q, Shi X, Hu J C, et al.BP neural network-based prediction model for internal corrosion rate of oil pipelines[J]. Oil Gas Storage Transp., 2010, 29(6): 448
[3]	(胡松青, 石鑫, 胡建春等. 基于BP神经网络的输油管线内腐蚀速率预测模型[J]. 油气储运, 2010, 29(6): 448)
[4]	Yang L, Bu W H, Gao L Q, et al.Prediction of corrosion rate of carbon steel in oilfield water using BP neuralnetwork[J]. Corros. Prot., 2008, 29(10): 631
[4]	(杨凌, 卜文海, 高立群等. BP神经网络预测碳钢在油田水介质中的腐蚀速率[J]. 腐蚀与防护, 2008, 29(10): 631)
[5]	Ren Z J.Research the corrosion factors of oil in pipeline and exploitation the residual life prediction software for oil pipeline [D]. Dongying: China University of Petroleum (East China), 2011
[5]	(任振甲. 管输原油腐蚀特性研究及管线剩余寿命预测软件开发[D]. 东营: 中国石油大学, 2011)
[6]	Ren Z J, Zhang J, Luo C S, et al.Influencing factors of crude oil corrosion based on artificial neural network[J]. Corros. Prot., 2011, 32(4): 293
[6]	(任振甲, 张军, 骆成双等. 基于人工神经网络研究原油腐蚀的影响因素[J]. 腐蚀与防护, 2011, 32(4): 293)
[7]	Yao Q K.Study of gas pipeline internal corrosion prediction in Moxi gas field [D]. Chengdu: Southwest Petroleum University, 2012
[7]	(姚权珂. 磨溪气田集气管线内腐蚀预测方法研究 [D]. 成都: 西南石油大学, 2012)
[8]	Wang C, Wang Z Y, Wei W, et al.Statistical analysis and predictive model in corrosion research[J]. J. Chin. Soc. Corros. Prot., 2010, 30(4): 306
[8]	(汪川, 王振尧, 魏伟等. 腐蚀研究中的统计分析方法和预测模型[J]. 中国腐蚀与防护学报, 2010, 30(4): 306)
[9]	Liu W, Zhao X M, Deng C L, et al.Grey neural network and its application to forecasting ocean-water corrosion[J]. J. Chin. Soc. Corros. Prot., 2008, 28(4): 201
[9]	(刘威, 赵选民, 邓春龙等. 灰色神经网络模型在海水腐蚀预测中的应用[J]. 中国腐蚀与防护学报, 2008, 28(4): 201)
[10]	Haque M E, Sudhakar K V.Prediction of corrosion fatigue behavior of DP steel through artificial neural network[J]. Int. J. Fatigue, 2001, 23(1): 1
[11]	Kamrunnahar M, Urquidi-Macdonald M.Prediction of corrosion behavior using neural network as a data mining tool[J]. Corros. Sci., 2010, 52(3): 669
[12]	Li H W.Research status review of fuzzy neural networks[J]. J. Liaoning Inst. Sci. Technol., 2010, 12(2): 15
[12]	(李恒嵬. 模糊神经网络研究现状综述[J]. 辽宁科学院学报, 2010, 12(2): 15)
[13]	Shi F, Wang X C, Yu L, et al.MATLAB Neural Network Analysis of 30 Cases [M]. Beijing: Beijing University of Aeronautics and Astronautics Press, 2010
[13]	(史峰, 王小川, 郁磊等. MATLAB神经网络30个案例分析 [M]. 北京: 北京航空航天大学出版社, 2010)

[1]	郭宝会, 邱友绪, 李海龙. 人工神经网络在钛合金表面Ni-SiC复合电镀工艺中的应用[J]. 中国腐蚀与防护学报, 2017, 37(4): 389-394.
[2]	林晓冬,彭群家,韩恩厚,柯伟. 核级不锈钢的热老化研究进展[J]. 中国腐蚀与防护学报, 2017, 37(2): 81-92.
[3]	聂亚楠,沈浩,谷坤鹏,王成启. 玻璃钢复合材料耐海水腐蚀性能及抗Cl^-渗透寿命预测[J]. 中国腐蚀与防护学报, 2016, 36(4): 357-362.
[4]	刘海霞,程学群,李晓刚,肖葵,董超芳. A1060纯Al的海洋大气环境腐蚀寿命预测模型研究[J]. 中国腐蚀与防护学报, 2016, 36(4): 349-356.
[5]	张新生,曹乃宁,李亚云. 基于Gumbel极值I型分布埋地油气管道的剩余寿命预测[J]. 中国腐蚀与防护学报, 2016, 36(4): 370-374.
[6]	刘静,李晓禄,朱崇伟,张涛,曾冠鑫,孟国哲,邵亚薇. 利用人工神经网络技术预测气田环境下316L不锈钢临界点蚀温度[J]. 中国腐蚀与防护学报, 2016, 36(3): 205-211.
[7]	朱志平,银朝晖,柳森,肖剑峰. 紫铜T2在高浓度H₂S模拟环境中的腐蚀行为及预测模型[J]. 中国腐蚀与防护学报, 2015, 35(4): 333-338.
[8]	韩夏冰高志明党丽华王迎毕慧超. Q235钢在模拟大气环境中早期腐蚀图像小波包分析[J]. 中国腐蚀与防护学报, 2013, 33(3): 211-215.
[9]	陆晓峰,朱晓磊,凌祥. 一种预测异径管流动加速腐蚀速率的新模型[J]. 中国腐蚀与防护学报, 2011, 31(6): 431-435.
[10]	翁永基. 腐蚀预测和计量学基础[J]. 中国腐蚀与防护学报, 2011, 31(4): 245-249.
[11]	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 .
[12]	梁彩凤; 侯文泰 . 钢的大气腐蚀预测[J]. 中国腐蚀与防护学报, 2006, 26(3): 129-135 .
[13]	张国安; 陈长风; 路民旭; 吴荫顺 . 油气田中CO2腐蚀的预测模型[J]. 中国腐蚀与防护学报, 2005, 25(2): 119-123 .
[14]	侯建国; 路民旭; 常炜 . 原油对CO2腐蚀过程的影响及相应腐蚀速率预测研究进展[J]. 中国腐蚀与防护学报, 2005, 25(2): 124-128 .
[15]	谭晓明 . 基于人工神经网络的铝合金腐蚀预测及其精度分析[J]. 中国腐蚀与防护学报, 2004, 24(4): 218-221 .

Viewed

Full text

Abstract

Cited

Shared

Discussed