论文部分内容阅读
针对海洋环境中油气管线腐蚀速率预测的复杂问题,提出了灰色关联分析与模糊神经网络结合的新方法对管线腐蚀速率进行预测。首先使用灰色关联分析对管线腐蚀速率与环境因素进行关联度计算,优选关联度较高的若干参数,然后应用模糊神经网络寻找管线腐蚀速率与优选环境因素之间的映射关系,使得影响管线腐蚀的主要因素数量明显减少,降低了预测难度。还根据管线已有腐蚀速率统计数据对该方法进行了测试,结果表明,管线腐蚀速率预测的平均相对误差为5.96%,方法在减少环境因素数量的情况下仍具有良好的预测精度。因此,基于灰色关联分析与模糊神经网络的新方法能够根据环境因素快速准确地预测管线的腐蚀速率,对保障管线的安全运营具有指导意义。
Aiming at the complicated problem of oil and gas pipelines corrosion rate prediction in marine environment, a new method combining gray relational analysis and fuzzy neural network is proposed to predict pipeline corrosion rate. Firstly, the gray relational analysis was used to calculate the degree of correlation between pipeline corrosion rate and environmental factors, and some parameters with high degree of correlation were selected. Then the fuzzy neural network was used to find the mapping relationship between pipeline corrosion rate and environmental factors, The number of major factors is significantly reduced, reducing the difficulty of prediction. The method is also tested based on the statistical data of existing pipeline corrosion rate. The results show that the average relative error of pipeline corrosion rate prediction is 5.96%. The method still has a good prediction accuracy when the number of environmental factors is reduced. Therefore, the new method based on gray relational analysis and fuzzy neural network can quickly and accurately predict pipeline corrosion rate based on environmental factors, which is instructive for ensuring the safe operation of pipeline.