Deeppipe: Operating Condition Recognition of Multiproduct Pipeline Based on KPCA-CNN

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F22%3APU147471" target="_blank" >RIV/00216305:26210/22:PU147471 - isvavai.cz</a>

Výsledek na webu

<a href="https://ascelibrary.org/doi/10.1061/%28ASCE%29PS.1949-1204.0000641" target="_blank" >https://ascelibrary.org/doi/10.1061/%28ASCE%29PS.1949-1204.0000641</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1061/(ASCE)PS.1949-1204.0000641" target="_blank" >10.1061/(ASCE)PS.1949-1204.0000641</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deeppipe: Operating Condition Recognition of Multiproduct Pipeline Based on KPCA-CNN

Popis výsledku v původním jazyce

Operational monitoring of pipelines can prevent environmental and economic losses. However, pipeline data have the characteristics of high dimension and nonlinear coupling, which makes it difficult to determine the relationship between the data and process, resulting in a high rate of misjudgment of the operating condition. To address this issue, an operating condition recognition model based on kernel principal component analysis (KPCA)-convolutional neural network (CNN) is proposed. Deeppipe refers to the use of deep learning algorithms to solve pipeline-related problems. Considering the spatial and time-series characteristics of the pipeline, the inlet and outlet pressure matrixes of the initial station, intermediate station, and terminal station are constructed. Subsequently, the features of the pressure matrix in the time domain, frequency domain, and energy domain are extracted. KPCA is employed to obtain the reconstructed feature matrix, which is used as the input of the proposed CNN recognition model. Taking two multiproduct pipelines as examples, the effectiveness of the KPCA-CNN recognition model is verified while compared with traditional nonlinear classification models (e.g., artificial neural network, decision tree, random forest, and others). The results show that the proposed model has the highest accuracy, precision, recall, and F1 score, and all reach 100%, which has a certain guiding significance for the monitoring and management of onsite pipelines.

Název v anglickém jazyce

Deeppipe: Operating Condition Recognition of Multiproduct Pipeline Based on KPCA-CNN

Popis výsledku anglicky

Operational monitoring of pipelines can prevent environmental and economic losses. However, pipeline data have the characteristics of high dimension and nonlinear coupling, which makes it difficult to determine the relationship between the data and process, resulting in a high rate of misjudgment of the operating condition. To address this issue, an operating condition recognition model based on kernel principal component analysis (KPCA)-convolutional neural network (CNN) is proposed. Deeppipe refers to the use of deep learning algorithms to solve pipeline-related problems. Considering the spatial and time-series characteristics of the pipeline, the inlet and outlet pressure matrixes of the initial station, intermediate station, and terminal station are constructed. Subsequently, the features of the pressure matrix in the time domain, frequency domain, and energy domain are extracted. KPCA is employed to obtain the reconstructed feature matrix, which is used as the input of the proposed CNN recognition model. Taking two multiproduct pipelines as examples, the effectiveness of the KPCA-CNN recognition model is verified while compared with traditional nonlinear classification models (e.g., artificial neural network, decision tree, random forest, and others). The results show that the proposed model has the highest accuracy, precision, recall, and F1 score, and all reach 100%, which has a certain guiding significance for the monitoring and management of onsite pipelines.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20101 - Civil engineering

Projekt

<a href="/cs/project/EF15_003%2F0000456" target="_blank" >EF15_003/0000456: Laboratoř integrace procesů pro trvalou udržitelnost</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of Pipeline Systems Engineering and Practice

ISSN

1949-1190

e-ISSN

1949-1204

Svazek periodika

2

Číslo periodika v rámci svazku

13

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

11

Strana od-do

04022006-04022006

Kód UT WoS článku

000769062300002

EID výsledku v databázi Scopus

2-s2.0-85124354762