摘要
将BP神经网络和遗传算法相结合 ,得到一种新的神经网络 ,并将这种神经网络成功用于计算腐蚀管道的剩余强度和最大允许输送压力。通过示例分析 ,得到下面结论 :不同计算方法计算得到的剩余强度和最大允许输送压力相差较大 ,Wes - 2 80 5 - 97规范、ASME -B31G规范、CVDA— 84规范等都比J积分方法计算得到的剩余强度和最大允许输送压力偏大 ;DM断裂力学方法计算得到的剩余强度和最大允许输送压力比J积分偏小 ;J积分方法和基于J积分方法的改进的遗传神经网络方法计算结果比较接近 。
Common criterions about residual strength evaluation at home and abroad were generalized and seven methods were acquired. BP neural network were combined with genetic algorithm(GA) named by modified BP-GA methods to successfully predict residual strength and critical pressure of injecting corrosion pipelines. Examples were shown that calculation results of every kind of method have great difference and calculating values of Wes-2805-97 criterion, ASME-B31G criterion,CVDA-84 criterion and Irwin fracture mechanics model are conservative and higher than those of J integral methods while calculating values of Burdiken model and DM fracture mechanics model are dangerous and less than those of J integral methods and calculating values of modified BP-GA methods are close and moderate to those of J integral methods. Therefore modified BP-GA methods and J integral methods are considered better methods to calculate residual strength and critical pressure of injecting corrosion pipelines.
出处
《压力容器》
2003年第10期22-27,共6页
Pressure Vessel Technology
基金
国家 8 63项目的一部分
石油勘探开发分布式集成应用系统 (863 -3 0 6-ZT0 4-0 3 -3 )
关键词
BP神经网络
遗传算法
腐蚀管道
剩余强度
BP neural network
genetic algorithm
corrosion pipeline
residual strength
