-
摘要:
针对京津冀地区碳钢土壤腐蚀问题,应用误差反向传播(BP)神经网络,以主影响因素为输入参数,分别构建了针对京津冀地区碳钢土壤腐蚀速率模型。根据各主要土壤腐蚀影响因素数值,对碳钢土壤腐蚀速率实现了预测。并基于地理信息系统(GIS)绘制了中国年均碳钢土壤腐蚀速率地图。研究表明:京津冀地区单年均碳钢土壤腐蚀速率西北高东南低,多年均碳钢土壤腐蚀速率基本均匀分布;pH、含盐总量、土壤温度、全氮量和有机质对碳钢土壤腐蚀较为显著;1、3、5和8年均碳钢土壤腐蚀速率分布最大为6.159、2.322、2.614和3.467 g/(dm2·a)。
-
关键词:
- 碳钢 /
- 反向传播(BP)神经网络 /
- 地理信息系统(GIS) /
- 京津冀 /
- 土壤腐蚀速率地图
Abstract:In view of the corrosion of carbon steel soil in Beijing-Tianjin-Hebei region, the prediction model for corrosion and pore corrosion in soil were developed using Back Propagation (BP) neural network. The main influencing factors were used as input parameters. According to the values of main soil corrosion influencing factors, the carbon steel soil corrosion rate was predicted. Average annual carbon steel soil corrosion rate in China was mapped based on Geographic Information System (GIS). The research shows that the average annual corrosion rate of carbon steel in Beijing-Tianjin-Hebei region is higher in the northwest and lower in the southeast in one year, and the average annual corrosion rate is basically uniformly distributed in many years. The carbon steel soil corrosion caused by pH value, total salt content, soil temperature, total nitrogen content and organic matter is more significant. The maximum average annual corrosion rate of carbon steel in 1, 3, 5 and 8 years is 6.159, 2.322, 2.614 and 3.467 g/(dm2·a).
-
表 1 BP神经网络参数设置
Table 1. Parameter setting of BP neural network
参数 数值 输入节点数 9 隐含节点数 6 输出节点数 1 样品组数 64 训练样本组数 48 验证样本组数 16 权重调节系数 0.1 阈值调节系数 0.1 误差控制率 0.001 最大学习次数 8000 表 2 碳钢土壤腐蚀影响因素与年均碳钢土壤腐蚀速率相关性
Table 2. Correlation between factors affecting carbon steel soil corrosion and average annual corrosion rate of carbon steel soil
因素 埋藏时间/年 1 3 5 8 有机质 0.603 0.528 0.236 0.217 含水量 0.101 0.103 0.101 0.031 全氮量 0.637 0.466 0.129 0.158 土壤温度 0.533 0.198 0.203 0.135 容重 -0.009 -0.013 -0.017 -0.01 总孔隙率 0.131 0.011 0.216 0.267 含盐总量 0.714 0.440 0.312 0.130 pH -0.369 -0.117 -0.414 -0.501 -
[1] 侯保荣, 路东柱.我国腐蚀成本及其防控策略[J].中国科学院院刊, 2018, 33(6):601-609. http://d.old.wanfangdata.com.cn/Periodical/zgkxyyk201806008HOU B R, LU D Z. Corrosion cost and preventive strategies in China[J].Strategy & Policy Decision Research, 2018, 33(6):601-609(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/zgkxyyk201806008 [2] 潘雪新, 姜海昌, 付鸿, 等.区域性气候条件下低合金高强耐候钢的初期腐蚀行为研究[J].腐蚀科学与防护技术, 2017, 29(4):356-362. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fskxyfhjs201704004PAN X X, JIANG H C, FU H, et al.Investigation on initial-stage corrosion behavior of low-alloy high-strength weathering resistant steel in regional climates[J].Corrosion Science and Protection Technology, 2017, 29(4):356-362(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fskxyfhjs201704004 [3] SORIANO C, ALFANTAZI A.Corrosion behavior of galvanized steel due to typical soil organics[J].Construction & Building Materials, 2016, 102(2):904-912. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=7feb2d3a318069b3f9e67c0f57335e75 [4] 曲良山, 李晓刚, 杜翠薇, 等.运用BP人工神经网络方法构建碳钢区域土壤腐蚀预测模型[J].北京科技大学学报, 2009, 31(12):1569-1575. doi: 10.3321/j.issn:1001-053X.2009.12.015QU L S, LI X G, DU C W, et al.Corrosion rate prediction model of carbon steel in regional soil based on BP artificial neural network.[J] Journal of University of Science and Technology Beijing, 2009, 31(12):1569-1575(in Chinese). doi: 10.3321/j.issn:1001-053X.2009.12.015 [5] 李丽, 李晓刚, 邢士波, 等.BP人工神经网络对国内典型地区碳钢土壤腐蚀的预测研究[J].腐蚀科学与防护技术, 2013, 25(5):372-376. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fskxyfhjs201305004LI L, LI X G, XING S B, et al.Research on soil corrosion rate prediction of carbon steel in typical Chinese cities based on BP artificial neural network[J].Corrosion Science and Protection Technology, 2013, 25(5):372-376(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fskxyfhjs201305004 [6] 郭阳阳.基于神经网络的海南变电站土壤对Q235钢的腐蚀预测研究[D].北京: 华北电力大学, 2016. http://cdmd.cnki.com.cn/Article/CDMD-10079-1016276173.htmGUO Y Y.Study on corrosion prediction of Q235 steel from soil in Hainan substation based on artificial neural network[D].Beijing: North China Electric Power University, 2016(in Chinese). http://cdmd.cnki.com.cn/Article/CDMD-10079-1016276173.htm [7] BRAGA G E, JUNQUEIRA R M R.Methodology for planning tower leg foundations corrosion maintenance of overhead transmission lines based on GIS[J].IEEE Transactions on Power Delivery, 2016, 31(4):1601-1608. doi: 10.1109/TPWRD.2016.2524003 [8] SHABARCHIN O, TESFAMARIAM S.Internal corrosion hazard assessment of oil & gas pipelines using Bayesian belief network model[J].Journal of Loss Prevention in the Process Industries, 2016, 40:479-495. doi: 10.1016/j.jlp.2016.02.001 [9] KARACA F.Mapping the corrosion impact of air pollution on the historical peninsula of Istanbul[J].Journal of Cultural Heritage, 2013, 14(2):129-137. doi: 10.1016/j.culher.2012.04.011 [10] NEOCLEOUS K, CHRISTOFE A, AGAPIOU A, et al.Digital mapping of corrosion risk in coastal urban areas using remote sensing and structural condition assessment:Case study in cyprus[J].Open Geosciences, 2016, 8(1):662-674. https://ui.adsabs.harvard.edu/abs/2016OGeo....8...63N/abstract [11] 鲁娟娟, 陈红.BP神经网络的研究进展[J].控制工程, 2006, 13(5):449-451. doi: 10.3969/j.issn.1671-7848.2006.05.016LU J J, CHEN H.Researching development on BP neural networks[J].Control Engineering of China, 2006, 13(5):449-451(in Chinese). doi: 10.3969/j.issn.1671-7848.2006.05.016 [12] 许宏良, 殷苏民.基于改进BP神经网络优化的管道腐蚀速率预测模型研究[J].表面技术, 2018, 47(2):177-181. http://d.old.wanfangdata.com.cn/Periodical/bmjs201802028XU H L, YIN S M.Prediction model of pipeline corrosion rate based on improved BP neural network[J].Surface Technology, 2018, 47(2):177-181(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/bmjs201802028 [13] 李可, 王全鑫, 宋世民, 等.基于改进人工神经网络的航天器电信号分类方法[J].北京航空航天大学学报, 2016, 42(3):596-601. doi: 10.13700/j.bh.1001-5965.2015.0186LI K, WANG Q X, SONG S M, et al.Spacecraft electrical signal classification method based on improved artificial neural network[J].Journal of Beijing University of Aeronautics and Astronautics, 2016, 42(3):596-601(in Chinese). doi: 10.13700/j.bh.1001-5965.2015.0186 [14] 孙文彬, 刘希亮, 王洪斌, 等.基于MIV的抛掷爆破影响因子权重分析[J].中国矿业大学学报, 2012, 41(6):993-998. http://d.old.wanfangdata.com.cn/Periodical/zgkydxxb201206022SUN W B, LIU X L, WANG H B, et al.Weight analysis of cast blasting effective factors based on MIV method[J].Journal of China University of Mining & Technology, 2012, 41(6):993-998(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/zgkydxxb201206022 [15] 杨斌, 李敬洋, 文磊.基于MIV的碳钢大气腐蚀速率影响因子权重分析[J].北京航空航天大学学报, 2018, 44(8):1620-1628. doi: 10.13700/j.bh.1001-5965.2017.0638YANG B, LI J Y, WEN L.Impact factor weight analysis of atmospheric corrosion rate of carbon steel based on MIV[J].Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(8):1620-1628(in Chinese). doi: 10.13700/j.bh.1001-5965.2017.0638 [16] 聂铭, 周冀衡, 杨荣生, 等.基于MIV-SVM的烤烟评吸质量预测模型[J].中国烟草学报, 2014, 20(6):56-62. http://d.old.wanfangdata.com.cn/Periodical/zgycxb201406010NIE M, ZHOU J H, YANG R S, at al.MIV-SVM-based prediction model for smoking quality of flue-cured tobacco[J].Acta Tabacaria Sinica, 2014, 20(6):56-62(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/zgycxb201406010 [17] REDDY R L, APOORVA B, SNIGDHA S, et al.GIS applications in land use and land development of a city[J].International Journal of Emerging Technology and Advanced Engineering, 2013, 3(5):303-308. http://d.old.wanfangdata.com.cn/OAPaper/oai_doaj-articles_5875a5fa26943614bc4c8c6f033c2f87 [18] ACHARYA S S, PANIGRAHI M K.Evaluation of factors controlling the distribution of organic matter and phosphorus in the Eastern Arabian shelf:A geostatistical reappraisal[J].Continental Shelf Research, 2016, 126:79-88. doi: 10.1016/j.csr.2016.08.001 [19] GUPTA A, KAMBLE T, MACHIWAL D.Comparison of ordinary and Bayesian Kriging techniques in depicting rainfall variability in arid and semi-arid regions of north-west India[J].Environmental Earth Sciences, 2017, 76(15):512. doi: 10.1007/s12665-017-6814-3 [20] SAĞIR Ç, KURTULUŞ B.Hydraulic head and groundwater 111cd content interpolations using empirical Bayesian Kriging(EBK)and geo-adaptive neuro-fuzzy inference system (geo-ANFIS)[J].Water SA, 2017, 43(3):509-519. http://www.scielo.org.za/scielo.php?script=sci_abstract&pid=S1816-79502017000300016&lng=pt&nrm=iso&tlng=en