西南石油大学学报(自然科学版)

• 石油机械工程及其他 • 上一篇    下一篇

改进GA-BP 算法的油气管道腐蚀剩余强度预测

孙宝财1,武建文1,李雷2,佘志刚3   

  1. 1. 甘肃省锅炉压力容器检验研究中心,甘肃兰州730020
    2. 中国石油华东设计院,山东青岛266071
    3. 中国石油克拉玛依石化公司,新疆克拉玛依834003
  • 出版日期:2013-06-01 发布日期:2013-06-01
  • 作者简介:孙宝财,1981 年生,男,汉族,黑 龙江伊春人,硕士,主要从事压力 容器、压力管道检验检测及腐蚀 可靠性评价方面的研究。E-mail: sunbaocai0518@163.com 武建文,1966 年生,男,汉族, 甘肃白银人,主要从事特种设 备的管理与检验工作,E-mail: 463299457@qq.com 李雷,1985 年生,男,汉族,辽 宁抚顺人,硕士,主要从事压 力管道工程设计工作。E-mail: lilei850707@163.com 佘志刚,1983 年生,男,汉族,甘肃 张掖人,硕士,主要从事化工机械 研究及相关工作。E-mail:shezhigang1983@ 126.com

Prediction of Remaining Strength of Corroded Oil and Gas Pipeline Based
on Improved GA-BP Algorithm

Sun Baocai1, Wu Jianwen1, Li Lei2, She Zhigang3   

  1. 1. Gansu Boiler and Pressure Vessel Inspection and Research Center Lanzhou,Lanzhou,Gansu 730020,China
    2. CPECC East-China Design Branch,Qingdao,Shandong 266071,China
    3. Karamay Petrochemical Company,PetroChina,Karamay,Xinjiang 834003,China
  • Online:2013-06-01 Published:2013-06-01

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。

关键词: 遗传算法, 神经网络, GA-BP(L-M)网络, 油气管道, 剩余强度

Abstract:

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.

Key words: genetic algorithm, neural network, GA-BP(L-M)network, oil and gas pipeline, remaining strength