摘要
为了解决缺少大量数据样本情况下油气管道剩余寿命预测问题,采用GM(1,1)模型预测管道腐蚀趋势。考虑到GM(1,1)模型自身存在的缺陷,采用指数变换预处理原始数据和动态生成系数重构背景值两种方法改进GM(1,1)模型的建模过程,并运用改进的蜂群算法(IABC)求解全局最优动态生成系数,进而建立改进的蜂群算法优化的指数变换灰色模型(IABC-EGM(1,1))。利用弯头测厚数据进行验证分析,GM(1,1)模型的平均相对误差为4.92%,IABC-EGM(1,1)模型的平均相对误差为2.28%,表明模型的预测精度得到了提高。
In order to solve the problem of predicting the remaining life of oil-gas pipelines in the absence of abundant data samples, the GM(1, 1) model was used to predict the corrosion trend for pipelines. Considering the defects of the existing GM(1, 1) model, the modeling process was improved by using an exponential transformation to preprocess the original data and a dynamic generation coefficient to reconstruct the background value. In addition, an improved artificial bee colony algorithm was used to solve the global optimal dynamic generation coefficient. The resulting model is denoted IABC-EGM(1, 1) model. According to the validation analysis of elbow thickness data, the average relative error of the GM(1, 1) model was 4.92%, and that of the IABC-EGM(1, 1) model was 2.28%, showing that the prediction accuracy has been significantly improved by our modification.
作者
秦谢勋
刘文彬
陈良超
QIN XieXun;LIU WenBin;CHEN LiangChao(College of Mechanical and Electrical Engineering,Beijing University of Chemical Technology,Beijing 100029,China;College of Information Science and Technology,Beijing University of Chemical Technology,Beijing 100029,China)
出处
《北京化工大学学报（自然科学版）》
CAS
CSCD
北大核心
2021年第1期74-80,共7页
Journal of Beijing University of Chemical Technology(Natural Science Edition)
基金
国家重点研发计划(2018YFC0809004)。
关键词
灰色模型
蜂群算法
指数变换
油气管道
腐蚀预测
grey model
artificial bee colony algorithm
exponential transformation
oil-gas pipelines
corrosion prediction
