基于遗传-神经网络算法的含均匀腐蚀缺陷油气管线爆破压力预测研究*

为提高含均匀腐蚀缺陷油气管线爆破压力的预测精度，保障长输油气管线的安全运行，将遗传算法和BP神经网络相结合，建立含均匀腐蚀缺陷油气管线爆破压力预测的遗传-BP神经网络（GA-BPNNs）模型。采用已有文献实验数据，分析对比该模型与AGA NG-18，ASME B31G，修正B31G，PCORRC，DNV RP-F101和SHELL 92等方法用于X46，X52，X60，X65，X80等材质油气管线含均匀腐蚀缺陷时爆破压力的计算误差。结果表明:GA-BPNNs模型用于含均匀腐蚀缺陷油气管线爆破压力预测时，误差在-7.78%～6.06%之间，预测精度明显高于目前国内外通用规范的计算结果；该模型操作简单，适用范围广，工程实用性好，为含缺陷压力管道爆破压力的预测提供更好的思路和方案。

Research on burst pressure prediction of oil and gas pipelines with uniform corrosion defects based on GA-BPNNs algorithm

In order to improve the prediction accuracy of burst pressure for the oil and gas pipelines with the uniform corrosion defects,and ensure the safe operation of long distance oil and gas pipelines,a genetic algorithm and BP neural networks (GA-BPNNs) model for predicting the burst pressure of oil and gas pipelines with the uniform corrosion defects was established by combining the genetic algorithm with the BP neural network.Based on the test data of existing literatures,the calculation error of burst pressure by the GA-BPNNs model and the AGA NG-18,ASME B31G,modified B31G,PCORRC,DNV RP-F101 and SHELL 92 for the X46,X52,X60,X65 and X80 pipelines with the uniform corrosion defects were analyzed and compared.The results showed that when the GA-BPNNs model was used to predict the burst pressure of oil and gas pipelines with the uniform corrosion defects,the error was between -3.09% and 7.78%,and the prediction accuracy was significantly higher than the calculation results of the current domestic and foreign general standards.The model is simple to operate and has a wide range of application and good engineering practicability,and it provides an advanced and reasonable new way for the burst pressure prediction of the defective pressure pipeline.