改进GA-BP算法的油气管道腐蚀剩余强度预测
|
摘要
利用人工神经网络能够逼近任意复杂函数的特性,可对在役油气管道的腐蚀剩余强度进行预测,但其缺点在于人工神经网络的权值和阈值的初始化分配具有随机性且只是一种局部优化算法,收敛过程中容易出现局部极小解。引入遗传算法的全局搜索特性和不依赖于梯度信息特性,对采用Levenberg-Marquardt(L-M)算法的BP神经网络的权值和阈值进行优化,并结合由敏感性分析确定的油气管道失效压力的影响因素,建立GA-BP(L-M)网络预测模型。采用Modified ASME B31G计算出的样本数据训练网络并进行预测。预测结果表明,GA-BP(L-M)网络预测模型可以相对更好地预测油气管道的失效压力,在满足工程需要的前提下,是一种更加科学、准确的预测模型。
The remaining strength of the in-service corroded oil and gas pipeline was predicted based on artificial neural network's ability to approximate complex function.But artificial neural network has drawbacks as follows:the initial distribution of weight and threshold value is a stochastic process and it was the local optimization algorithm,and that the local minimum solution tends to appear in the convergence process.Therefore,the weight and threshold value of BP neural network using L-M algorithm were optimized based on the global search ability and independence of the gradient information of genetic algorithm, and with consideration of the influencing factors of failure pressure of oil and gas pipeline determined by sensitivity analysis, the GA-BP(L-M) network model was built.The network was trained using sample of Modified ASME B31G and predictions were made.The results show that the GA-BP(L-M) network model can better predict failure pressure of oil and gas pipeline, which proves to be a more scientific and accurate model.
The remaining strength of the in-service corroded oil and gas pipeline was predicted based on artificial neural network's ability to approximate complex function.But artificial neural network has drawbacks as follows:the initial distribution of weight and threshold value is a stochastic process and it was the local optimization algorithm,and that the local minimum solution tends to appear in the convergence process.Therefore,the weight and threshold value of BP neural network using L-M algorithm were optimized based on the global search ability and independence of the gradient information of genetic algorithm, and with consideration of the influencing factors of failure pressure of oil and gas pipeline determined by sensitivity analysis, the GA-BP(L-M) network model was built.The network was trained using sample of Modified ASME B31G and predictions were made.The results show that the GA-BP(L-M) network model can better predict failure pressure of oil and gas pipeline, which proves to be a more scientific and accurate model.
引文
[1]Ahammed M.Prediction of remaining strength of corroded pressurised pipelines[J].International Journal of Pressure Vessels and Piping,1997,71(3):213-217.
[2]王明春,练章华,代娟,等.管道承压能力逆转原因探讨[J].西南石油大学学报,2007,29(3):126-129. Wang Mingchun,Lian Zhanghua,Dai Juan,et al.A prode inpipes pressuree reversal[J].Journal of Southwest Petroleum University,2007,29(3):126-129.
[3]Li Shuxin,Yu Shurong,Zeng Hailong,et al.Predicting corrosion remaining life of underground pipelines with a mechanically-based probabilistic model[J].Journal of Petroleum Science and Engineering,2009,63(3-4): 162-166.
[4]王海涛,韩恩厚,柯伟.基于人工神经网络模型的铝合金大气腐蚀的预NO[J].中国腐蚀与防护学报,2006, 26(5):272-274,281. Wang Haitao,Han Enhou,Ke Wei.Predictive model for atmospheric corrosion of aluminium alloy by artificial neural nerwork[J].Journal of Chinese Society for Corrosion and Protection,2006,26(5):272-274,281.
[5]胡世鹏.吴小林,马利敏,等.基于BP神经网络和遗传算法的天然气脱水装置能耗优化[J].天然气工业, 2012.32(11):89-94. Hu Shipeng,Wu Xiaolin,Ma Limin,et al.BP and GA based energy consumption optimization of gas dehydration plants[J].Natural Gas Industry,2012,32(11): 89-94.
[6]杨志力,周路,彭文利,等.BP神经网络技术在声波测井曲线重构中的运用[J].西南石油大学学报:自然科学版,2008,30(1):63-66. Yang Zhili,Zhou Lu,Peng Wenli,et al.Application of BP neural network technology in soniclog date rebuilding [J].Journal of Southwest Petroleum University:Science & Technology Edition,2008,30(1):63-66.
[7]刘文超,卢祥国,刘进祥,等.一种基于BP神经网络的调驱增油预测方法[J].西安石油大学学报:自然科学版,2012,27(1):47-52. Liu Wenchao,Lu Xiangguo,Liu Jinxiang,et al.Prediction method of oil increment of profile-control and flooding measures using BP neural network based on core flooding parameters[J].Journal of Xi'an Shiyou University: Natural Science Edition,2012,27(1):47-52.
[8]Silva RCC,Guerreiro J N C,Loula A F D.A study of pipe interacting corrosion defects using the FEM and neural networks[J].Advances in Engineering Software, 2007,38(11-12):868-875.
[9]王金峰,罗省贤,李录明.改进的神经网络并行算法及其在地震初至拾取中的应用[J].成都理工大学学报:自然科学版,2007,34(3):348-353. Wang Jinfeng,Luo Shengxian,Li Luming.An improvedeural network its application in picking papallel arithmetic and seismic first break[J].Journal of Chengdu University of Technology:Science & Technology Edition, 2007,34(3):348-353.
[10]杨中宝,彭省临,李朝艳.基于GIS的人工神经网络矿产预测系统设计及应用[J].地球科学与环境学报, ??2005,27(1):30-33. Yang Zhongbao,Peng Shenglin,Li Chaoyan.Design of the ore prospecting system based on the integrated technology of GIS and ANN[J].Journal of Earth Seiences and Environmen,2005,27(1):30-33.
[1]]王磊,顾宏伟,姚恒申.基于人工神经网络的油气产量组合预测方法[J].新疆石油地质,2005,26(5): 557-558,561. Wang Lei,Gu Hongwei,Yao Hengshen.Artificial neural network based combination forecast method for oilgas production[J].Xinjiang Petroleum Geology,2005, 26(5):557-558,561.
[12]柴毅,尹宏鹏,李大杰,等.基于改进遗传算法的BP神经网络自适应优化设计[J].重庆大学学报:自然科学版,2007,30(4):91-96. Chai Yi,Yin Hongpeng,Li Dajie,et al.Self-adaptation optimize BP neural network design based on the genetic algorithms[J].Journal of Chongqing University:Naturl Science Edition,2007,30(4):91-96.
[13]商杰,朱战立.基于遗传算法的神经网络在预测油管钢腐蚀速率中的应用[J].腐蚀科学与防护技术,2007, 19(3):225-228. Shang Jie,Zhu Zhanli.Application of genetic algorithms neural networks in predicting corrosion rate of carbon steel[J].Corrosion Science and Protection Technology, 2007,19(3):225-228.
[14]傅立军,包忠诩,陈泽中,等.正交试验法、神经网络和遗传算法的结合[J].南昌大学学报:工科版,2003. 25(1):79-82. Fu Lijun,Bao Zongxu,Chen Zezhong,et al.Combination of orthogonal experimental method,neural networks and genetic algorithms[J].Journal of Nanchang University: Engineering & Technology,2003,25(1):79-82.
[15]李自力,孙云峰,张子波,等.基于遗传算法的气田集输管网整体优化方法[J].天然气工业,2011,31(8): 86-89. Li Zili,Sun Yunfeng,Zhang Zibo,et al.A global optimization method based on genetic algorithms for gas gathering pipeline network in a gas field[J].Natural Gas Industry, 2011,31(8):86-89.
[16]李卫华,李长俊.基于遗传算法的天然气集输管网参数优化设计[J].天然气丁业,2005,25(2):158-160. Li Weihua,Li Changjun.Parameter-optimized design of gas gathering and transmission system by heredity solution [J].Natural Gas Industry,2005,25(2):158-160.
[17]杨建军,战红,刘扬,等.星状原油集输管网拓扑优化的混合遗传算法[J].西南石油大学学报:自然科学版, 2008,30(4):166-169. Yang Jianjun,Zhan Hong,Liu Yang,et al.Hybrid genetic algorithm for topology optimization of stellated oil gathering and transportation pipeline network[J].Journal of Southwest Petroleum University:Science & Technology Edition,2008,30(4):166-169.
[18]ASME-B31G.A supplement ofASMEB31G code for pressure piping,1995,Manual for determining the remaining strength of corroded pipelines[S].New York: American Society for Mechanical Engineers,1995.
[19]阎平凡,张长水.人工神经网络与模拟进化计算[M].第2版.北京:清华大学出版社.2005.
[20]王小平,曹立明.遗传算法理论、应用及软件实现[M].西安:西安交通大学出版社.2002.
[2]王明春,练章华,代娟,等.管道承压能力逆转原因探讨[J].西南石油大学学报,2007,29(3):126-129. Wang Mingchun,Lian Zhanghua,Dai Juan,et al.A prode inpipes pressuree reversal[J].Journal of Southwest Petroleum University,2007,29(3):126-129.
[3]Li Shuxin,Yu Shurong,Zeng Hailong,et al.Predicting corrosion remaining life of underground pipelines with a mechanically-based probabilistic model[J].Journal of Petroleum Science and Engineering,2009,63(3-4): 162-166.
[4]王海涛,韩恩厚,柯伟.基于人工神经网络模型的铝合金大气腐蚀的预NO[J].中国腐蚀与防护学报,2006, 26(5):272-274,281. Wang Haitao,Han Enhou,Ke Wei.Predictive model for atmospheric corrosion of aluminium alloy by artificial neural nerwork[J].Journal of Chinese Society for Corrosion and Protection,2006,26(5):272-274,281.
[5]胡世鹏.吴小林,马利敏,等.基于BP神经网络和遗传算法的天然气脱水装置能耗优化[J].天然气工业, 2012.32(11):89-94. Hu Shipeng,Wu Xiaolin,Ma Limin,et al.BP and GA based energy consumption optimization of gas dehydration plants[J].Natural Gas Industry,2012,32(11): 89-94.
[6]杨志力,周路,彭文利,等.BP神经网络技术在声波测井曲线重构中的运用[J].西南石油大学学报:自然科学版,2008,30(1):63-66. Yang Zhili,Zhou Lu,Peng Wenli,et al.Application of BP neural network technology in soniclog date rebuilding [J].Journal of Southwest Petroleum University:Science & Technology Edition,2008,30(1):63-66.
[7]刘文超,卢祥国,刘进祥,等.一种基于BP神经网络的调驱增油预测方法[J].西安石油大学学报:自然科学版,2012,27(1):47-52. Liu Wenchao,Lu Xiangguo,Liu Jinxiang,et al.Prediction method of oil increment of profile-control and flooding measures using BP neural network based on core flooding parameters[J].Journal of Xi'an Shiyou University: Natural Science Edition,2012,27(1):47-52.
[8]Silva RCC,Guerreiro J N C,Loula A F D.A study of pipe interacting corrosion defects using the FEM and neural networks[J].Advances in Engineering Software, 2007,38(11-12):868-875.
[9]王金峰,罗省贤,李录明.改进的神经网络并行算法及其在地震初至拾取中的应用[J].成都理工大学学报:自然科学版,2007,34(3):348-353. Wang Jinfeng,Luo Shengxian,Li Luming.An improvedeural network its application in picking papallel arithmetic and seismic first break[J].Journal of Chengdu University of Technology:Science & Technology Edition, 2007,34(3):348-353.
[10]杨中宝,彭省临,李朝艳.基于GIS的人工神经网络矿产预测系统设计及应用[J].地球科学与环境学报, ??2005,27(1):30-33. Yang Zhongbao,Peng Shenglin,Li Chaoyan.Design of the ore prospecting system based on the integrated technology of GIS and ANN[J].Journal of Earth Seiences and Environmen,2005,27(1):30-33.
[1]]王磊,顾宏伟,姚恒申.基于人工神经网络的油气产量组合预测方法[J].新疆石油地质,2005,26(5): 557-558,561. Wang Lei,Gu Hongwei,Yao Hengshen.Artificial neural network based combination forecast method for oilgas production[J].Xinjiang Petroleum Geology,2005, 26(5):557-558,561.
[12]柴毅,尹宏鹏,李大杰,等.基于改进遗传算法的BP神经网络自适应优化设计[J].重庆大学学报:自然科学版,2007,30(4):91-96. Chai Yi,Yin Hongpeng,Li Dajie,et al.Self-adaptation optimize BP neural network design based on the genetic algorithms[J].Journal of Chongqing University:Naturl Science Edition,2007,30(4):91-96.
[13]商杰,朱战立.基于遗传算法的神经网络在预测油管钢腐蚀速率中的应用[J].腐蚀科学与防护技术,2007, 19(3):225-228. Shang Jie,Zhu Zhanli.Application of genetic algorithms neural networks in predicting corrosion rate of carbon steel[J].Corrosion Science and Protection Technology, 2007,19(3):225-228.
[14]傅立军,包忠诩,陈泽中,等.正交试验法、神经网络和遗传算法的结合[J].南昌大学学报:工科版,2003. 25(1):79-82. Fu Lijun,Bao Zongxu,Chen Zezhong,et al.Combination of orthogonal experimental method,neural networks and genetic algorithms[J].Journal of Nanchang University: Engineering & Technology,2003,25(1):79-82.
[15]李自力,孙云峰,张子波,等.基于遗传算法的气田集输管网整体优化方法[J].天然气工业,2011,31(8): 86-89. Li Zili,Sun Yunfeng,Zhang Zibo,et al.A global optimization method based on genetic algorithms for gas gathering pipeline network in a gas field[J].Natural Gas Industry, 2011,31(8):86-89.
[16]李卫华,李长俊.基于遗传算法的天然气集输管网参数优化设计[J].天然气丁业,2005,25(2):158-160. Li Weihua,Li Changjun.Parameter-optimized design of gas gathering and transmission system by heredity solution [J].Natural Gas Industry,2005,25(2):158-160.
[17]杨建军,战红,刘扬,等.星状原油集输管网拓扑优化的混合遗传算法[J].西南石油大学学报:自然科学版, 2008,30(4):166-169. Yang Jianjun,Zhan Hong,Liu Yang,et al.Hybrid genetic algorithm for topology optimization of stellated oil gathering and transportation pipeline network[J].Journal of Southwest Petroleum University:Science & Technology Edition,2008,30(4):166-169.
[18]ASME-B31G.A supplement ofASMEB31G code for pressure piping,1995,Manual for determining the remaining strength of corroded pipelines[S].New York: American Society for Mechanical Engineers,1995.
[19]阎平凡,张长水.人工神经网络与模拟进化计算[M].第2版.北京:清华大学出版社.2005.
[20]王小平,曹立明.遗传算法理论、应用及软件实现[M].西安:西安交通大学出版社.2002.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心