IAFSA-GRNN在油田集输管道CO_(2)腐蚀速率预测中的应用

Application of IAFSA-GRNN in CO_(2) corrosion rate prediction of oil gathering and transportation pipelines

为提高油田集输管道CO_(2)腐蚀速率预测的准确性,针对原始广义回归神经网络(GRNN)预测精度低的问题,提出改进的群智能算法优化原始GRNN的预测模型;分别使用GRNN模型、人工鱼群算法(AFSA)优化的GRNN(AFSA-GRNN)模型和自适应改进的AFSA-GRNN(IAFSA-GRNN)模型预测X65管线钢的CO_(2)腐蚀速率。结果表明:采用AFSA和IAFSA优化光滑因子S后,能大大提高GRNN模型的预测精度,预测结果的平均相对误差由36.09%分别减小至7.20%和6.90%;与AFSA相比,IAFSA优化的GRNN不仅具有更高的预测精度,还具有更快的收敛速度。AFSA-GRNN在第164次迭代计算时收敛,而IAFSA-GRNN在第109次迭代计算时收敛,说明AFSA经自适应优化能提高优化过程的收敛速度和GRNN的预测精度。

In order to achieve more accurate prediction of CO_(2) corrosion rate of oil gathering and transportation pipelines,considering the low prediction accuracy of original GRNN,an improved swarm intelligence algorithm was proposed to optimize it.Then,GRNN model,AFSA optimized GRNN(AFSA-GRNN)model and adaptive improved AFSA-GRNN(IAFSA-GRNN)model were used to predict CO_(2) corrosion rate of X65 pipeline steel.The results show that the prediction accuracy of GRNN model is greatly improved by using AFSA and IAFSA to optimize smoothing factor S,with its mean relative error of prediction results being reduced from 36.09%to 7.20%and 6.90%,respectively.Compared with AFSA,IAFSA optimized GRNN has not only higher prediction accuracy,but also faster convergence rate.The AFSA-GRNN converges at the 164th iteration,while the IAFSA-GRNN does that at the 109th one,indicating that AFSA could improve convergence rate of optimization process and further improve prediction accuracy of GRNN through adaptive optimization.