首页 | 本学科首页   官方微博 | 高级检索  
     检索      

海洋环境中平台钢腐蚀速率的三层BP 神经网络预测
引用本文:兰志刚,侯保荣,白 刚,宋积文,陈胜利,谭 震,张 杰.海洋环境中平台钢腐蚀速率的三层BP 神经网络预测[J].海洋科学,2010,34(12):75-77.
作者姓名:兰志刚  侯保荣  白 刚  宋积文  陈胜利  谭 震  张 杰
作者单位:1. 中国科学院,海洋研究所,山东,青岛,266071;中海油能源发展股份有限公司北京分公司,北京,100027;中国科学院,研究生院,北京,100039
2. 中国科学院,海洋研究所,山东,青岛,266071
3. 中海油有限公司工程建设部,北京,100010
4. 中海油能源发展股份有限公司北京分公司,北京,100027
基金项目:海洋石油总公司综合科研项目
摘    要:利用三层BP神经网络预测海洋环境因素对材料的腐蚀速率的影响。结合实测的pH值、温度、溶解氧、盐度、生物附着等影响因素,分析了上述环境因素对平台钢腐蚀的影响,建立环境因素与腐蚀速率之间的映射关系,预测了平台钢在海洋环境中的腐蚀速率。结果表明,全浸区腐蚀速率预测误差为6.95%,潮差带腐蚀速率预测误差为4.2%,预测精度较高。说明利用三层BP神经网络预测钢在海水中腐蚀速率技术可行,具有较高的预测精度和应用价值。

关 键 词:腐蚀因素    腐蚀速率预测    BP  神经网络    海洋环境腐蚀预测
收稿时间:5/4/2010 12:00:00 AM
修稿时间:2010/10/18 0:00:00

Prediction of effects of marine environmental factors on steel corrosion rates with three-layer BP neural network
LAN Zhi-gang,HOU Bao-rong,BAI Gang,SONG Ji-wen,CHEN Sheng-li,TAN Zhen,ZHANG Jie.Prediction of effects of marine environmental factors on steel corrosion rates with three-layer BP neural network[J].Marine Sciences,2010,34(12):75-77.
Authors:LAN Zhi-gang  HOU Bao-rong  BAI Gang  SONG Ji-wen  CHEN Sheng-li  TAN Zhen  ZHANG Jie
Abstract:We introduced the methodology to study relationship between steel corrosion and marine environmental factors and to predict of steel corrosion rates with three-layer BP neural network. With the in situ measurements of pHs, water temperatures, dissolved oxygen, salinities and bio-fouling, the effects of marine environmental factors on steel corrosion were analyzed and sorted in a descending sequence. With a three-layer BP neural network, the corrosion rates of steel in seawater were predicted with an error of 6.95% in submerged zones and 4.2% in tidal zones. The results show that prediction with the neural network was feasible, producing good prediction accuracy and value.
Keywords:corrosion factors  prediction of corrosion rate  three-layer BP neural network  prediction of corrosion on marine environmental
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《海洋科学》浏览原始摘要信息
点击此处可从《海洋科学》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号