Prediction of Corrosion Rate Based on Recurrent Neural Network
摘 要
采用循环神经网络(RNN) 对腐蚀探针的监测数据(90%)进行训练,建立了管道腐蚀速率预测模型,并利用剩余的10%监测数据对模型的有效性进行了验证。结果表明:基于RNN建立的腐蚀速率预测模型能准确地预测出管道的腐蚀速率,预测值与监测数据的均方误差为0.008%,该方法可以为管道的腐蚀监测提供预警信息。
Abstract
A prediction model of pipeline corrosion rate was established through training the monitoring data (90%) from corrosion probe using recurrent neural network (RNN), and the validity of the model was verified by the remaining 10% monitoring data. The results showed that the model based on RNN could predict the corrosion rates of pipelines accurately. The mean square error between the predicted values and the monitoring data was 0.008%. The method can provide early warning information for pipeline corrosion monitoring.
中图分类号 TG179 TE988 DOI 10.11973/fsyfh-202311014
所属栏目 数值模拟
基金项目
收稿日期 2021/11/29
修改稿日期
网络出版日期
作者单位点击查看
引用该论文: JIANG Haisheng,NUERXIATI Nuerdong,LIU Junheng. Prediction of Corrosion Rate Based on Recurrent Neural Network[J]. Corrosion & Protection, 2023, 44(11): 78
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】马飞, 熊江东, 冯元元. 浅谈化工厂工艺管道安装过程质量控制[J]. 城市建设理论研究(电子版), 2011(24):1-3.
【2】肖斌, 张恒宾,刘宏伟.改进PSO-BPNN算法在管道腐蚀预测中的应用[J].郑州大学学报(工学版),2022,43(1):27-33.
【3】史云涛. 油水井油管的腐蚀与防护措施探讨[J]. 科学与财富, 2019(21):168.
【4】田源, 肖杰,李珊,等.含硫气田集输管道腐蚀预测软件应用[J].石油与天然气化工,2021,50(1):83-86.
【5】王逍, 梁永图.美国水源地旁油气运输管道事故分析及启示[J].油气田地面工程,2019,38(7):1-7.
【6】张新生, 蔡宝泉.基于改进随机森林模型的海底管道腐蚀预测[J].中国安全科学学报,2021,31(8):69-74.
【7】SIDDHARTH D, SAINI D K J, SINGH P. An efficient approach for edge detection technique using Kalman filter with artificial neural network[J].International Journal of Engineering, 2021, 34(12):2604-2610.
【8】SZOPLIK J,CIUKSZA M.Mixing time prediction with artificial neural network model[J].Chemical Engineering Science,2021,246:116949.
【9】SHEN M L,LEE C F,LIU H H,et al.Effective multinational trade forecasting using LSTM recurrent neural network[J].Expert Systems With Applications, 2021,182:115199.
【2】肖斌, 张恒宾,刘宏伟.改进PSO-BPNN算法在管道腐蚀预测中的应用[J].郑州大学学报(工学版),2022,43(1):27-33.
【3】史云涛. 油水井油管的腐蚀与防护措施探讨[J]. 科学与财富, 2019(21):168.
【4】田源, 肖杰,李珊,等.含硫气田集输管道腐蚀预测软件应用[J].石油与天然气化工,2021,50(1):83-86.
【5】王逍, 梁永图.美国水源地旁油气运输管道事故分析及启示[J].油气田地面工程,2019,38(7):1-7.
【6】张新生, 蔡宝泉.基于改进随机森林模型的海底管道腐蚀预测[J].中国安全科学学报,2021,31(8):69-74.
【7】SIDDHARTH D, SAINI D K J, SINGH P. An efficient approach for edge detection technique using Kalman filter with artificial neural network[J].International Journal of Engineering, 2021, 34(12):2604-2610.
【8】SZOPLIK J,CIUKSZA M.Mixing time prediction with artificial neural network model[J].Chemical Engineering Science,2021,246:116949.
【9】SHEN M L,LEE C F,LIU H H,et al.Effective multinational trade forecasting using LSTM recurrent neural network[J].Expert Systems With Applications, 2021,182:115199.
相关信息
标题 | 相关频次 | |
基于KPCA和SVM的工艺管道腐蚀速率预测 | 2 | |
接地网腐蚀性评价方法与腐蚀速率预测 | 2 | |
三次指数平滑法预测管道腐蚀速率的应用 | 1 |