[1]李 明,闻 伟,李秉军,等.基于ICS-GRNN的油气管道剩余强度预测技术[J].焊管,2022,45(1):32-36.[doi:10.19291/j.cnki.1001-3938.2022.01.006]
　LI Ming,WEN Wei,LI Bingjun,et al.Residual Strength Prediction Technology of Oil and Gas Pipeline Based on ICS-GRNN[J].,2022,45(1):32-36.[doi:10.19291/j.cnki.1001-3938.2022.01.006]
点击复制

基于ICS-GRNN的油气管道剩余强度预测技术()
分享到：

《焊管》[ISSN:1001-3938/CN:61-1160/TE]

卷:
45
期数:
2022年第1期
页码:
32-36
栏目:
应用与开发
出版日期:
2022-01-28

文章信息/Info

Title:
Residual Strength Prediction Technology of Oil and Gas Pipeline Based on ICS-GRNN
文章编号:
10.19291/j.cnki.1001-3938.2022.01.006
作者:
李 明; 闻 伟; 李秉军; 牛志勇; 陈学敏; 梁昌晶
1. 中国石油华北油田分公司第五采油厂，河北 辛集 052360；2. 中国石油华北油田分公司第二采油厂，河北 霸州 065700；3. 中国石油管道局工程有限公司第四分公司，河北 廊坊 065000；4. 河北华北石油港华勘察规划设计有限公司，河北 任丘 062552
Author(s):
LI Ming;  WEN Wei;  LI Bingjun;  NIU Zhiyong;  CHEN Xuemin;  LIANG Changjing
1. No.5 Oil Production Plant of Huabei Oilfield Company CNPC，Xinji 052360, Hebei, China;2. No.2 Oil Production Plant of Huabei Oilfield Company CNPC，Bazhou 065700, Hebei, China;3. No.4 Branch Company of China Petroleum Pipeline Engineering Co., Ltd., Langfang 065000, Hebei, China;4. Hebei Huabei Petroleum GangHua Survey Planning&Design Co., Ltd., Renqiu 062552, Hebei, China
关键词:
布谷鸟搜索算法; 广义回归神经网络; 剩余强度; 腐蚀; 油气管道
Keywords:
ICS;  GRNN;  residual strength; corrosion; oil and gas pipeline
分类号:
TE973
DOI:
10.19291/j.cnki.1001-3938.2022.01.006
文献标志码:
B
摘要:
为提高腐蚀管道剩余强度的预测精度，深入分析影响管道剩余强度的主要因素，通过广义回归神经网络（GRNN）对剩余强度进行有效预测，采用改进的布谷鸟搜索算法（ICS）对光滑因子进行寻优，建立了基于ICS-GRNN的管道剩余强度预测模型，并与其他模型进行了对比。结果表明，ICS算法较CS算法提前88次迭代达到收敛条件，具有更快的迭代速度；ICS-GRNN模型的平均相对误差和希尔不等系数均最小，分别为1.92%和0.43，与其他模型相比，预测精度和鲁棒性最好，预测时间最短。研究结果可为进一步确定腐蚀管道的后续承载力和服役状态提供参考。
Abstract:
In order to improve the prediction accuracy of residual strength of corrosion pipeline and analyze the main factors affecting the residual strength of pipeline, the residual strength is effectively predicted by generalized regression neural network (GRNN), the smoothing factor is optimized by improved cuckoo search algorithm (ICS), and the prediction model of pipeline residual strength based on ICS-GRNN is established, and comparison has been made with the other models. The results show that ICS algorithm achieves the convergence condition 88 times earlier than CS algorithm, and has faster iteration speed. The average relative error and hill inequality coefficient of ICS-GRNN model are the smallest, which are 1.92% and 0.43 respectively. Compared with other models, the prediction accuracy and robustness are the best and the prediction time is the shortest. The research results can provide reference for further determining the subsequent bearing capacity and service state of corrosion pipeline.

参考文献/References:

[1] 柴强飞，肖忠东，高竟喆，等． 基于尖锥网络分析法的管道风险评价研究[J]． 中国安全科学学报，2017，27（7）：88-93．[2] 骆正山，袁宏伟． 基于误差补偿的GM-RBF海底管道腐蚀预测模型[J]． 中国安全科学学报，2018，28（3）：96-101．[3] 陈兆雄，吴明，谢飞，等. 腐蚀管道剩余强度的评价方法及剩余寿命预测[J]. 机械工程材料，2015，39（5）：97-101.[4] MA B，SHUAI J，WANG J，et al. Analysis on the latest assessment criteria of ASME B31G—2009 for the remaining strength of corroded pipelines[J]. Journal of Failure Analysis & Prevention，2011，11（6）：666-671.[5] 马彬，帅健，李晓魁，等. 新版ASME B31G—2009 管道剩余强度评价标准先进性分析[J]. 天然气工业，2011，31（8）：112-115.[6] XU L Y，CHENG Y F. Reliability and failure pressure prediction of various grades of pipeline steel in the presence of corrosion defects and pre-strain[J]. International Journal of Pressure Vessels & Piping，2012，89（1）：75-84.[7] WANG N，ZARGHAMEE M S. Evaluating Fitness for Service of Corroded Metal Pipelines：Structural Reliability Bases[J]. Journal of Pipeline Systems Engineering & Practice，2014，5（1）：1-9.[8] MA B，SHUAI J，LIU D，et al. Assessment on failure pressure of high strength pipeline with corrosion defects[J]. Engineering Failure Analysis，2013，32（9）：209-219.[9] FREIRE J L F，VIEURA R D，CASTRO J T P，et al. PART 3：Burst Tests of Pipeline With Extensive Longi- tudinal Metal Loss[J]. Experimental Techniques，2006，30（6）：60-65.[10] CRONIN D S，PICK R J. Experimental database for corroded pipe：Evaluation of RSTRENG and B31G[C]//International Pipeline Conference. Calgary，Canada：IPC，2010.[11] BENJAMIN A C，VIEIRA R D，FREIRE J L F，et al. Burst tests on pipeline with long external corrosion[C]//International Pipeline Conference. Calgary，Canada：IPC，2010.[12] SOUZA R D，BENJAMIN A C，VIEIRA R D，et al. PART 4：Rupture tests of pipeline segments containing long real corrosion defects[J]. Experimental Techniques，2007，31（1）：46-51.

备注/Memo

备注/Memo:
收稿日期：2021-07-19作者简介：李 明（1974—），男，本科，高级技师，主要从事油气开采领域工作。
更新日期/Last Update: 2022-02-10