海洋大气环境下架空管道腐蚀失重预测  

Prediction of corrosion weight loss of overhead pipelines in marine atmospheric environment

作　　者：骆正山[1] 杨赛星 王小完[1] LUO Zheng-shan;YANG Sai-xing;WANG Xiao-wan(School of Management,Xi'an University of Architecture and Technology,Xi'an 710055,China)

机构地区：[1]西安建筑科技大学管理学院,西安710055

出　　处：《安全与环境学报》2023年第4期1031-1037,共7页Journal of Safety and Environment

基　　金：国家自然科学基金项目(41877527);陕西省社科基金项目(2018S34)。

摘　　要：为提高海洋大气环境下油气管道腐蚀失重预测精度,提出了一种基于IWOA-DGM(1, 1,λ)的架空管道腐蚀失重预测模型。首先用佳点集理论优化鲸鱼优化算法(Whale Optimization Algorithm, WOA)初始种群的布局以增强寻优能力,并用非线性自适应权重和改进黄金正弦算法避免WOA模型的随机性,以提高收敛速度。然后利用指数变换、变权弱化缓冲算子和新陈代谢改进离散灰色模型(Discrete Grey Model, DGM(1, 1)),指数变换可以提高原始数据的光滑度,变权弱化缓冲算子可以抵消冲击扰动的干扰,加入新陈代谢可以实现动态的中长期预测。再用改进鲸鱼优化算法(Improve Whale Optimization Algorithm, IWOA)对改进DGM(1,1,λ)模型中的参数λ进行寻优,最后建立改进鲸鱼优化算法的优化离散灰色预测模型(IWOA-DGM(1, 1,λ)),并用该模型对西沙Q235碳钢管道腐蚀失重情况进行预测。结果表明,改进模型的灰色绝对关联度、平均绝对百分比误差和拟合度分别为98.99%、2.43%和98.73%,各项评价指标均优于其他对比模型,且预测精度得到了极大的提高,证明该模型有较好的鲁棒性。Corrosion of oil and gas pipelines is the primary reason for pipeline failure.Although the research on corrosion prediction of buried pipelines and submarine pipelines is relatively mature,the overhead pipeline is rarely researched.This paper studies pipeline corrosion in the marine atmospheric environment.To improve the prediction accuracy of oil and gas pipeline corrosion and weight loss in the marine atmospheric environment,the DGM(1,1)model was used to predict the corrosion weight loss trend of pipelines,and the DGM(1,1)model was improved by using the exponential transformation,variable weight weakening buffer operator,and metabolism.Among them,the exponential transformation can improve the smoothness of original data,variable weight softening buffer operator can offset the interference of shock disturbance,and adding metabolism can realize dynamic medium and long-term prediction.For the parameter optimization in the improved DGM(1,1,λ)model,the best point set theory was first used to optimize the layout of the initial population of the Whale Optimization Algorithm(WOA)to enhance the optimization ability.In addition,nonlinear adaptive weights and an improved golden sine algorithm were used to avoid the randomness of WOA and improve the convergence speed.Then,IWOA was adopted to optimize the parameters in the improved DGM(1,1,λ)model.Finally,an optimized discrete gray prediction model of the Improved Whale Optimization Algorithm(IWOA-DGM(1,1,λ))was established.Taking an overhead pipeline in Xisha as an example for verification and analysis,the results reveal that the gray absolute correlation degree,average absolute percentage error,and fitting degree of the model were 98.99%,2.43%,and 98.73%,respectively.Each index of the optimized model was better than that of the original model.Both had improved,and the prediction accuracy had been greatly improved,proving that the model has better robustness and fitting effect.Apart from that,in the absence of a large amount of corrosion data,this model can be used to p

关 键 词：安全工程 海洋大气环境 架空管道 腐蚀失重 改进鲸鱼优化算法(IWOA) DGM(1 1)模型 

分 类 号：X937[环境科学与工程—安全科学]