Residual strength analysis of internally corroded submarine pipeline based on FOA-GRNN model

doi:10.16265/j.cnki.issn1003-3033.2020.06.012

Abstract

Abstract: In order to explore residual strength of submarine pipelines with internal corrosion, and provide reference for maintenance so as to ensure safe operation, a FOA-GRNN calculation method of residual strength was proposed and a prediction model was constructed by using GRNN based on influencing factors like wall thickness, diameter, corrosion depth, length, width and ultimate tensile strength. Then, FOA was used to optimize the model, and negative influence of smooth factors were set artificially. Influencing factors and residual strength database were simulated and generated by finite element method, and trained and predicted through FOA-GRNN model. Finally, with experimental data of pipeline ultimate strength blasting from PETROBRAS Research Institute as an example, the prediction model was verified. The results show that average relative error of FOA-GRNN model is 16.53% for residual strength prediction of finite element simulation data, and 7.81% for experimental data prediction, which are reasonable and accurate.

Key words: internally corroded submarine pipeline, residual strength, fruit fly optimization algorithm (FOA), generalized regression neural network (GRNN), finite element method

CLC Number:

X937

BI Aorui, LUO Zhengshan, SONG Yingying, ZHANG Xinsheng. Residual strength analysis of internally corroded submarine pipeline based on FOA-GRNN model[J]. China Safety Science Journal, 2020, 30(6): 78-83.

References

[1] 狄彦, 帅健, 王晓霖, 等, 油气管道事故原因分析及分类方法研究[J].中国安全科学学报, 2013, 23(7): 109-115.
DI Yan, SHUAI Jian, WANG Xiaolin, et al. Study on methods for classifying oil ＆ gas pipeline incidents[J]. Chnia Safety Science Journal, 2013, 23(7): 109-115.
[2] 李新宏, 朱红卫, 陈国明, 等. 海底油气管道泄漏事故风险分析的贝叶斯动态模型[J].中国安全科学学报, 2015,25(4): 75-80.
LI Xinhong, ZHU Hongwei, CHEN Guoming, et al. Bayesian dynamic model for analyzing risk of meeting submarine oil & gas pipeline leakage accident[J].Chnia Safety Science Journal, 2015,35(4): 75-80.
[3] GOGOI B K, DUTTA N N, GOSWAMI P, et al. A case study of bioremediation of petroleum-hydrocarbon contaminated soil at a crude oil spill site[J]. Advances in Environmental Research, 2003,7(4): 767-782.
[4] ASME B31-1984, Manual for determining the remaining strength of corroded pipelines[S].
[5] ASME B31-1991, Manual for determining the remaining strength of corroded pipelines: a supplement to ASME B31 code for pressure piping[S].
[6] DNV RP F101-1999, Recommended practice corroded pipeline[S].
[7] STEPHENS D R, LEIS B N. Development of an alternative criterion for residual strength of corrosion defects in moderate to high toughness pipe[C]. Proceedings of International Pipeline Conference, 2000: 781-792.
[8] 帅健, 张春娥, 陈福来. 腐蚀管道剩余强度评价方法的对比研究[J].天然气工业,2006,26(11): 122-125.
SHUAI Jian, ZHANG Chun'e, CHEN Fulai. Comparison study on assessment methods for remaining strength of corroded pipeline[J]. Natural Gas Industry, 2006, 26(11): 122-125.
[9] 赵鹏程, 帅健, 唐雨, 等. 轴向应力对腐蚀缺陷管道极限内压的影响[J].中国安全科学学报, 2019, 29(3): 70-75.
ZHAO Pengcheng, SHUAI Jian, TANG Yu, et al. Impact of axial stress on ultimate internal pressure of corroded pipelines[J]. Chnia Safety Science Journal, 2019, 29(3): 70-75.
[10] 崔铭伟, 曹学文, 封子艳, 等. 局部腐蚀油气管道失效压力计算方法[J]. 中国石油大学学报:自然科学版, 2013, 37(6):123-128,134.
CUI Mingwei, CAO Xuewen, FENG Ziyan, et al. Calculation method of oil-gas pipeline failure pressure with localized corrosion[J]. Journal of China University of Petroleum:Edition of Social Sciences, 2013, 37(6):123-128,134.
[11] 焦李成, 杨淑媛, 刘芳, 等. 神经网络七十年:回顾与展望[J]. 计算机学报, 2016, 39(8): 1 697-1 716.
JIAO Licheng, YANG Shuyuan, LIU Fang, et al. Seventy years beyond neural networks: retrospect and prospect[J]. Chinese Journal of Computers, 2016, 39(8): 1 697-1 716.
[12] SPECHT D F. A general regression neural network[J]. IEEE Transactions on Neural Networks, 1991, 2(6): 568-576.
[13] 潘文超.果蝇最佳化演算法[M].台北:沧海书局, 2011: 4-10.
[14] 郑晓龙,王凌,王圣尧. 求解置换流水线调度问题的混合离散果蝇算法[J].控制理论与应用, 2014, 31(2): 159-164.
ZHENG Xiaolong, WANG Ling, WANG Shengyao. A hybrid discrete fruit fly optimization algorithm for solving permutation flow-shop scheduling problem[J].Control Theory and Applications, 2014, 31(2): 159-164.
[15] OSGOOD W R, RAMBERG W. Description of stress-strain curves by three parameters[R]. National Advisory Committee for Aeronautics, 1943.
[16] FU B, KIRKWOOD M G. Predicting failure pressure of internally corroded linepipe using the finite element method[C]. ASME OMAE 13^th International Conference of Mechanic Arctic Engineering, 1995: 175-184.
[17] FREIRE J L F, VIEIRA R D, CASTRO J T P, et al. Part 3: burst tests of pipeline with extensive longitudinal metal loss[J]. Experimental Techniques, 2006,30(6): 60-65.