Predicting the Residual Strength of Oil and Gas Pipelines Using the GA-BP Neural Network

Zhanhui Wang, Mengzhao Long, Wenlong Duan, Aimin Wang, Xiaojun Li
{"title":"Predicting the Residual Strength of Oil and Gas Pipelines Using the GA-BP Neural Network","authors":"Zhanhui Wang, Mengzhao Long, Wenlong Duan, Aimin Wang, Xiaojun Li","doi":"10.2174/0124055204315589240502052118","DOIUrl":null,"url":null,"abstract":"\n\nMost NN (neural network) research only conducted qualitative analysis,\nanalyzing its accuracy, with certain limitations, without studying its NN model, error convergence\nprocess, and pressure ratio. There is relatively limited research on the application of\nNN optimized by GA (genetic algorithm) to oil and gas pipelines; Moreover, the residual\nstrength evaluation of GA-BP NN (genetic algorithm backpropagation neural network) has the\nadvantages of high global search ability, efficiency not limited by constant differences, and the\nuse of probability search instead of path search, which has a wide application prospect.\n\n\n\nUsing MATLAB software, establish GA-BP NN models under five residual strength\nevaluation criteria and introduce the relative error of the parameters and the pressure ratio to\ncomprehensively analyze the accuracy and applicability of GA-BP NN.\n\n\n\nUsing MATLAB software to estimate the residual strength of oil and gas pipelines with the GA, artificial NN BP, and GA-BP NN.\n\n\n\nFirstly, using MATLAB software, a GA-BP NN model was established based on five\nresidual strength evaluation criteria: ASME B31G Modified, BS7910, PCORRC, DNV RP\nF101, and SHELL92, by changing five factors that affect the residual strength of oil and gas\npipelines: diameter, wall thickness, yield strength, corrosion length, and corrosion depth; Second,\nthe trained GA-BP NN model is used to predict the residual strength of the same set of evaluation\ncriteria test data and compared with the calculation results of five residual strength evaluation\ncriteria. The relative error of the parameters and pressure ratio are introduced to comprehensively\nanalyze the accuracy and applicability of the GA-BP NN.\n\n\n\nThe error convergence time of the BP NN is longer, and the optimized GA-BP NN has\na shorter convergence time. By comparing the convergence training times of different models, it\ncan be obtained that for the five sets of residual strength evaluation criteria of ASME B31G\nModified, BS7910, PCORRC, DNV RP F101, and SHELL92, the optimized GA-BP NN model\nsignificantly reduces convergence training times, significantly improves convergence speed, and\nfurther evolves the system performance. From the relative error and local magnification, it can\nbe seen that for the ASME B31G Modified evaluation criteria, the maximum relative error of\nthe BP NN model is 1.4008%, and the maximum relative error of the GA-BP NN model is\n0.7304%. For the evaluation criterion BS7910, the maximum relative error of the BP NN model\nis 0.7239%, and the maximum relative error of the GA-BP NN model is 0.5242%; for the evaluation\ncriteria of DNV RP F101, the maximum relative error of the BP NN model is 1.1260%,\nand the maximum relative error of the GA-BP NN model is 0.4810%; for the PCORRC evaluation\ncriteria, the maximum relative, error and the maximum relative error of the GA-BP NN\nmodel is 0.8004%; for the SHELL92 evaluation criterion, the maximum relative error of the BP\nNN model is 1.2292%, and the maximum relative error of the GA-BP NN model is 0.8346%.\nThe results of the GA-BP NN prediction are closer to the results of the calculation of the five\nresidual strength evaluation criteria, and the prediction effect is better, which can more accurately\npredict the residual strength of the oil and gas pipelines. Based on the pressure ratio, the average\npressure ratio A of the BP NN model under the five residual strength criteria is 1.0004, and\nthe average pressure ratio A of the GA-BP NN model is 0.9998. The results predicted by the\nGA-BP NN model are more accurate.\n\n\n\nThese findings have crucial implications for the forecast of the residual strength of\ncorrosive oil and gas pipelines.\n","PeriodicalId":20833,"journal":{"name":"Recent Innovations in Chemical Engineering (Formerly Recent Patents on Chemical Engineering)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Recent Innovations in Chemical Engineering (Formerly Recent Patents on Chemical Engineering)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2174/0124055204315589240502052118","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Most NN (neural network) research only conducted qualitative analysis, analyzing its accuracy, with certain limitations, without studying its NN model, error convergence process, and pressure ratio. There is relatively limited research on the application of NN optimized by GA (genetic algorithm) to oil and gas pipelines; Moreover, the residual strength evaluation of GA-BP NN (genetic algorithm backpropagation neural network) has the advantages of high global search ability, efficiency not limited by constant differences, and the use of probability search instead of path search, which has a wide application prospect. Using MATLAB software, establish GA-BP NN models under five residual strength evaluation criteria and introduce the relative error of the parameters and the pressure ratio to comprehensively analyze the accuracy and applicability of GA-BP NN. Using MATLAB software to estimate the residual strength of oil and gas pipelines with the GA, artificial NN BP, and GA-BP NN. Firstly, using MATLAB software, a GA-BP NN model was established based on five residual strength evaluation criteria: ASME B31G Modified, BS7910, PCORRC, DNV RP F101, and SHELL92, by changing five factors that affect the residual strength of oil and gas pipelines: diameter, wall thickness, yield strength, corrosion length, and corrosion depth; Second, the trained GA-BP NN model is used to predict the residual strength of the same set of evaluation criteria test data and compared with the calculation results of five residual strength evaluation criteria. The relative error of the parameters and pressure ratio are introduced to comprehensively analyze the accuracy and applicability of the GA-BP NN. The error convergence time of the BP NN is longer, and the optimized GA-BP NN has a shorter convergence time. By comparing the convergence training times of different models, it can be obtained that for the five sets of residual strength evaluation criteria of ASME B31G Modified, BS7910, PCORRC, DNV RP F101, and SHELL92, the optimized GA-BP NN model significantly reduces convergence training times, significantly improves convergence speed, and further evolves the system performance. From the relative error and local magnification, it can be seen that for the ASME B31G Modified evaluation criteria, the maximum relative error of the BP NN model is 1.4008%, and the maximum relative error of the GA-BP NN model is 0.7304%. For the evaluation criterion BS7910, the maximum relative error of the BP NN model is 0.7239%, and the maximum relative error of the GA-BP NN model is 0.5242%; for the evaluation criteria of DNV RP F101, the maximum relative error of the BP NN model is 1.1260%, and the maximum relative error of the GA-BP NN model is 0.4810%; for the PCORRC evaluation criteria, the maximum relative, error and the maximum relative error of the GA-BP NN model is 0.8004%; for the SHELL92 evaluation criterion, the maximum relative error of the BP NN model is 1.2292%, and the maximum relative error of the GA-BP NN model is 0.8346%. The results of the GA-BP NN prediction are closer to the results of the calculation of the five residual strength evaluation criteria, and the prediction effect is better, which can more accurately predict the residual strength of the oil and gas pipelines. Based on the pressure ratio, the average pressure ratio A of the BP NN model under the five residual strength criteria is 1.0004, and the average pressure ratio A of the GA-BP NN model is 0.9998. The results predicted by the GA-BP NN model are more accurate. These findings have crucial implications for the forecast of the residual strength of corrosive oil and gas pipelines.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用 GA-BP 神经网络预测油气管道的残余强度
大多数 NN(神经网络)研究只是进行定性分析,分析其精度,具有一定的局限性,没有对其 NN 模型、误差收敛过程和压力比进行研究。此外,GA-BP 神经网络(遗传算法反向传播神经网络)的剩余强度评价具有全局搜索能力强、效率不受常量差异限制、用概率搜索代替路径搜索等优点,具有广泛的应用前景。利用 MATLAB 软件,在五种残余强度评价准则下建立 GA-BP NN 模型,并引入参数相对误差和压力比,全面分析 GA-BP NN 的准确性和适用性。首先,利用 MATLAB 软件,基于五种残余强度评价准则建立了 GA-BP NN 模型:首先,利用 MATLAB 软件,基于 ASME B31G Modified、BS7910、PCORRC、DNV RPF101 和 SHELL92 五种残余强度评价标准,通过改变直径、壁厚、屈服强度、腐蚀长度和腐蚀深度五个影响因素,建立了 GA-BP NN 模型;其次,利用训练好的 GA-BP NN 模型预测同一组评价标准试验数据的残余强度,并与五种残余强度评价标准的计算结果进行比较。引入参数相对误差和压力比来综合分析 GA-BP NN 的准确性和适用性。通过比较不同模型的收敛训练时间,可以得出对于 ASME B31GModified、BS7910、PCORRC、DNV RP F101 和 SHELL92 五套残余强度评价标准,优化后的 GA-BP NN 模型显著减少了收敛训练时间,明显提高了收敛速度,系统性能得到进一步提高。从相对误差和局部放大率可以看出,对于 ASME B31G Modified 评价标准,BP NN 模型的最大相对误差为 1.4008%,而 GA-BP NN 模型的最大相对误差为 0.7304%。在 BS7910 评估标准中,BP NN 模型的最大相对误差为 0.7239%,GA-BP NN 模型的最大相对误差为 0.5242%;在 DNV RP F101 评估标准中,BP NN 模型的最大相对误差为 1.1260%,GA-BP NN 模型的最大相对误差为 0.4810%;在 PCORRC 评估标准中,GA-BP NN 模型的最大相对误差和最大相对误差均为 0.8004%;在 SHELL 评估标准中,BP NN 模型的最大相对误差为 0.7239%,GA-BP NN 模型的最大相对误差为 0.5242%。GA-BP NN的预测结果与五种剩余强度评价标准的计算结果较为接近,预测效果较好,可以较为准确地预测油气管道的剩余强度。根据压力比,BP NN 模型在五种残余强度标准下的平均压力比 A 为 1.0004,GA-BP NN 模型的平均压力比 A 为 0.9998。这些发现对腐蚀性油气管道残余强度的预测具有重要意义。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Role of Biomass Gasification in Achieving Circular Economy Regulation of the Properties of Polymers based on Thiirane using Mixtures of Amine Hardeners Predicting the Residual Strength of Oil and Gas Pipelines Using the GA-BP Neural Network Thermo-Acoustic Behaviour of K2CrO4 and K4 [Fe(CN)6] in Aqueous Dimethylformamide at Different Temperatures Predictive Modeling and Optimization of Plywood Drying: An Artificial Neural Network Approach
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1