PDF下载

[1]刘刚袁子云孙庆峰陈雷李苗潘元昊吴昱辰王子涵.顺序输送管道混油信息软测量方法[J].油气储运,2024,43(11):1-16.
　Liu Gang,Yuan Ziyun,Sun Qingfen,et al.Research on soft sensors for mixed oil information in sequential transportation pipeline[J].Oil & Gas Storage and Transportation,2024,43(11):1-16.

点击复制

顺序输送管道混油信息软测量方法

《油气储运》[ISSN:1000-8241/CN:13-1093/TE] 卷: 43 期数: 2024年11期页码: 1-16 栏目: 出版日期: 2024-11-25

Title:: Research on soft sensors for mixed oil information in sequential transportation pipeline

作者:: 刘刚袁子云孙庆峰陈雷李苗潘元昊吴昱辰王子涵

Author(s):: Liu Gang; Yuan Ziyun; Sun Qingfen; Chen Lei; Li Miao; Pan Yuanhao; Wu Yuchen; Wang Zihan

关键词:: 顺序输送管道; 混油; 软测量; 后行油品密度; 界面定位; 浓度分布; 智慧物流

Keywords:: Sequential transportation pipeline; Mixed oil; Soft sensors; Trailing oil density; Interface locating; Concentration distribution; Intelligent logistics

分类号:: TE88

文献标志码:: A

摘要:: 【目的】混油控制是成品油顺序输送管道亟需解决的难题之一，混油信息则是优化顺序输送管道运行效率的基础数据。现场安装传感器的监测结果存在偏差，且无法满足现场提前获取混油信息的需求；纯数据驱动模型建立的混油软测量方法未考虑管输工艺与仪表测量特性，预测精度欠佳。【方法】通过分析顺序输送管道的管输工艺与测量仪表的监测过程，提出融合物理认知的变分贝叶斯高斯混合回归模型。结合新一维混油浓度演化模型，构建顺序输送管道混油信息软测量方法：基于站场硬传感器获取的管输运行参数，建立表征顺序输送混油信息变化规律的高精度“软”传感器，其主要功能是实现混油界面的定位、后行油品密度测量值的预测、混油界面密度分布信息的预测，从而精准预测混油信息。【结果】新建软测量方法具备更好的适用性，混油界面到站时间预测误差较传感器测量方法减少了76.2%，后行油品测量密度预测RMSE（Root Mean Square Error）较纯数据驱动软测量方法降低了41.4%，混油界面密度分布预测曲线RMSE低于0.9 kg/m3，且计算耗时少于30 s。【结论】融合物理认知与数据的顺序输送管道混油信息软测量方法，可实现混油信息的高效预测，辅助现场操作人员掌握管输批次状态，优化油品批次管理，为顺序输送智慧物流提供技术支撑。

Abstract:: [Objective]Control of mixed oil is a critical challenge in sequential transportation pipelines, where accurate mixed oil information is essential for optimizing operational efficiency. Traditional on-site monitoring instruments often yield biased results, while pure data-driven soft-sensing methods fail to consider pipeline transport processes and instrument characteristics, leading to suboptimal accuracy. [Methods]To address this, we propose a Variational Bayesian Gaussian mixture regression model that integrates physical insights with a novel one-dimensional mixed oil concentration evolution model. [Results]This approach significantly reduces the prediction error for the mixed oil interface arrival time by 76.2% and decreases the RMSE for downstream oil density prediction by 41.4% compared to conventional methods. The method also achieves an RMSE below 0.9 kg/m³ for the mixed oil interface density distribution curve, with computation time under 30 seconds. [Conclusion]By combining physical knowledge with data, the proposed method enhances the efficiency of mixed oil prediction, supports batch management, and provides technical backing for intelligent logistics in sequential transportation pipelines.

相似文献/References:

[1]戴福俊.成品油顺序输送混油的检测与切割[J].油气储运,2011,30(04):255.[doi:10.6047/j.issn.1000-8241.2011.04.004]
　Dai Fujun.Detection and cutting technique of oil contamination in batch transportation process[J].Oil & Gas Storage and Transportation,2011,30(11):255.[doi:10.6047/j.issn.1000-8241.2011.04.004]
[2]李会朵,梁静华,朱峰,等.成品油混油掺混实验与临界比例计算[J].油气储运,2011,30(03):180.[doi:10.6047/j.issn.1000-8241.2011.03.006]
　Li Huiduo,Liang Jinghua,Zhu Feng,et al.Mixing experiment and critical proportion calculation for contamination of products[J].Oil & Gas Storage and Transportation,2011,30(11):180.[doi:10.6047/j.issn.1000-8241.2011.03.006]
[3]王珊,张栋栋,赵会军,等.双时间分裂法在成品油顺序输送中的应用[J].油气储运,2008,27(11):13.[doi:10.6047/j.issn.1000-8241.2008.11.004]
　WANG Shan,ZHANG Dongdong.Application of Double-Time Splitting Method to Batch Transportation of Oil Products[J].Oil & Gas Storage and Transportation,2008,27(11):13.[doi:10.6047/j.issn.1000-8241.2008.11.004]
[4]郑瑜,赵会军,赵书华.顺序输送汽油与柴油混油回掺试验[J].油气储运,2008,27(5):32.[doi:10.6047/j.issn.1000-8241.2008.05.009]
　ZHENG Yu,ZHAO Huijun.A Study on Diesel and Gasoline Mixture in Batch Transportation Process[J].Oil & Gas Storage and Transportation,2008,27(11):32.[doi:10.6047/j.issn.1000-8241.2008.05.009]
[5]赵会军,张青松,赵书华,等.竖直管道两种油品顺序输送的传质数值研究[J].油气储运,2007,26(11):26.[doi:10.6047/j.issn.1000-8241.2007.11.008]
　ZHAO Huijun,ZHANG Qingsong.Numerical Study on Mass Transfer with Two Oil Products in Vertical Batch Pipeline[J].Oil & Gas Storage and Transportation,2007,26(11):26.[doi:10.6047/j.issn.1000-8241.2007.11.008]
[6]王昆,陈保东,郭淑娟,等.管道顺序输送产生混油的问题研究[J].油气储运,2007,26(8):8.[doi:10.6047/j.issn.1000-8241.2007.08.003]
　WANG Kun,CHEN Baodong.A Study on the Product Oil Contamination Caused by Batching Transportation[J].Oil & Gas Storage and Transportation,2007,26(11):8.[doi:10.6047/j.issn.1000-8241.2007.08.003]
[7]刘强,王树立,赵会军,等.停输对混油量影响数值模拟研究[J].油气储运,2007,26(3):13.[doi:10.6047/j.issn.1000-8241.2007.03.004]
　LIU Qiang,WANG Shuli.Study on Numerical Simulation of Contaminated Volume for Shutdown Batching Pipeline[J].Oil & Gas Storage and Transportation,2007,26(11):13.[doi:10.6047/j.issn.1000-8241.2007.03.004]
[8]赵会军,张青松,张国忠,等.基于PHOENICS的顺序输送管道混油浓度数值计算[J].油气储运,2007,26(2):43.[doi:10.6047/j.issn.1000-8241.2007.02.006]
　HAO Huijun,ZHANG Qingsong.PHOENICS-based Numerical Study for Concentration Distribution of International on Batch Pipeline[J].Oil & Gas Storage and Transportation,2007,26(11):43.[doi:10.6047/j.issn.1000-8241.2007.02.006]
[9]刘强,王树立,李恩田,等.利用湍流模式理论模拟顺序输送混油过程[J].油气储运,2006,25(11):22.[doi:10.6047/j.issn.1000-8241.2006.11.006]
　LIU Qiang,WANG Shuli.Study on the Numerical Simulation of the Contamination of Batching Transportation of Products Oil with Turbulent Theory[J].Oil & Gas Storage and Transportation,2006,25(11):22.[doi:10.6047/j.issn.1000-8241.2006.11.006]
[10]周宇,邱姝娟,吴明,等.成品油顺序输送混油浓度的计算[J].油气储运,2006,25(9):25.[doi:10.6047/j.issn.1000-8241.2006.09.007]
　ZHOU Yu,QIU Shujuan.The Mixed Oil Cutting of Product Oil Batch Transportation[J].Oil & Gas Storage and Transportation,2006,25(11):25.[doi:10.6047/j.issn.1000-8241.2006.09.007]

更新日期/Last Update: 2024-09-11