Physics-informed Student’s t mixture regression model applied to predict mixed oil length
Real-time estimation of thelength of mixed oil in a multi-product pipeline is a critical task during batch transportation. In previous studies, various predictive models have been built while they merely depended on a single predictive model to fulfill the regression work, and model performance seve...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co. Ltd.
2023-03-01
|
Series: | Journal of Pipeline Science and Engineering |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2667143322000774 |
_version_ | 1797894699715919872 |
---|---|
author | Ziyun Yuan Lei Chen Gang Liu Weiming Shao Yuhan Zhang Yunxiu Ma |
author_facet | Ziyun Yuan Lei Chen Gang Liu Weiming Shao Yuhan Zhang Yunxiu Ma |
author_sort | Ziyun Yuan |
collection | DOAJ |
description | Real-time estimation of thelength of mixed oil in a multi-product pipeline is a critical task during batch transportation. In previous studies, various predictive models have been built while they merely depended on a single predictive model to fulfill the regression work, and model performance severely deteriorated with the presence of outliers. The Student’s t mixture regression (SMR) model can identify multimode characteristics and reduce the impact of outliers. However, ignorance of physics knowledge and the simplistic assumption of a linear relationship between variables in the SMR may lead to unsatisfactory performance. In addition, the possible singularity problem can make the SMR fails to work. Motivated by resolving these issues, this paper proposes a physics-informed SMR modeling method by integrating the physics knowledge and the SMR to develop a robust hybrid predictive model for predicting the mixed oil length in a multi-product pipeline. Case studies are carried out on the measured dataset to demonstrate the effectiveness and advantages of the proposed new modeling method compared to the model entirely based on the SMR method and two state-of-the-art predictive models. |
first_indexed | 2024-04-10T07:13:29Z |
format | Article |
id | doaj.art-ec0483514d994232adca21753e199286 |
institution | Directory Open Access Journal |
issn | 2667-1433 |
language | English |
last_indexed | 2024-04-10T07:13:29Z |
publishDate | 2023-03-01 |
publisher | KeAi Communications Co. Ltd. |
record_format | Article |
series | Journal of Pipeline Science and Engineering |
spelling | doaj.art-ec0483514d994232adca21753e1992862023-02-26T04:28:34ZengKeAi Communications Co. Ltd.Journal of Pipeline Science and Engineering2667-14332023-03-0131100105Physics-informed Student’s t mixture regression model applied to predict mixed oil lengthZiyun Yuan0Lei Chen1Gang Liu2Weiming Shao3Yuhan Zhang4Yunxiu Ma5Key Laboratory of Oil & Gas Storage and Transportation Safety, China university of Petroleum (East China), Qingdao, 266580, ChinaKey Laboratory of Oil & Gas Storage and Transportation Safety, China university of Petroleum (East China), Qingdao, 266580, China; Corresponding authors.Key Laboratory of Oil & Gas Storage and Transportation Safety, China university of Petroleum (East China), Qingdao, 266580, China; Corresponding authors.Key Laboratory of Oil & Gas Storage and Transportation Safety, China university of Petroleum (East China), Qingdao, 266580, ChinaPipeChina Eastern Storage and Transportation Company Huangdao Oil Depot, Qingdao, 266580, ChinaKey Laboratory of Oil & Gas Storage and Transportation Safety, China university of Petroleum (East China), Qingdao, 266580, China; PipeChina (Xuzhou) Pipeline Inspection & Testing Co., Ltd., Xuzhou, 221008, ChinaReal-time estimation of thelength of mixed oil in a multi-product pipeline is a critical task during batch transportation. In previous studies, various predictive models have been built while they merely depended on a single predictive model to fulfill the regression work, and model performance severely deteriorated with the presence of outliers. The Student’s t mixture regression (SMR) model can identify multimode characteristics and reduce the impact of outliers. However, ignorance of physics knowledge and the simplistic assumption of a linear relationship between variables in the SMR may lead to unsatisfactory performance. In addition, the possible singularity problem can make the SMR fails to work. Motivated by resolving these issues, this paper proposes a physics-informed SMR modeling method by integrating the physics knowledge and the SMR to develop a robust hybrid predictive model for predicting the mixed oil length in a multi-product pipeline. Case studies are carried out on the measured dataset to demonstrate the effectiveness and advantages of the proposed new modeling method compared to the model entirely based on the SMR method and two state-of-the-art predictive models.http://www.sciencedirect.com/science/article/pii/S2667143322000774Mixed oil lengthMulti-product pipelineStudent’s t mixture regression modelPhysics-dataRobustness |
spellingShingle | Ziyun Yuan Lei Chen Gang Liu Weiming Shao Yuhan Zhang Yunxiu Ma Physics-informed Student’s t mixture regression model applied to predict mixed oil length Journal of Pipeline Science and Engineering Mixed oil length Multi-product pipeline Student’s t mixture regression model Physics-data Robustness |
title | Physics-informed Student’s t mixture regression model applied to predict mixed oil length |
title_full | Physics-informed Student’s t mixture regression model applied to predict mixed oil length |
title_fullStr | Physics-informed Student’s t mixture regression model applied to predict mixed oil length |
title_full_unstemmed | Physics-informed Student’s t mixture regression model applied to predict mixed oil length |
title_short | Physics-informed Student’s t mixture regression model applied to predict mixed oil length |
title_sort | physics informed student s t mixture regression model applied to predict mixed oil length |
topic | Mixed oil length Multi-product pipeline Student’s t mixture regression model Physics-data Robustness |
url | http://www.sciencedirect.com/science/article/pii/S2667143322000774 |
work_keys_str_mv | AT ziyunyuan physicsinformedstudentstmixtureregressionmodelappliedtopredictmixedoillength AT leichen physicsinformedstudentstmixtureregressionmodelappliedtopredictmixedoillength AT gangliu physicsinformedstudentstmixtureregressionmodelappliedtopredictmixedoillength AT weimingshao physicsinformedstudentstmixtureregressionmodelappliedtopredictmixedoillength AT yuhanzhang physicsinformedstudentstmixtureregressionmodelappliedtopredictmixedoillength AT yunxiuma physicsinformedstudentstmixtureregressionmodelappliedtopredictmixedoillength |