Oil-Net: A Learning-Based Framework for Working Conditions Diagnosis of Oil Well Through Dynamometer Cards Identification
IEEE Sensors Journal · 01.07.2023 · 23 (13) · 14406-14417
DOI: 10.1109/jsen.2023.3275933 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.07.2023. Verfasst von Rong Ma und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Science Foundation of China.
Abstract (Originalsprache)
Working conditions identification of oil well relies on high-cost and slow-speed artificial inspection in past decades. Working conditions diagnosis through dynamometer cards identification based on machine learning has significant economic value and environmental meaning for oil production. In this article, we collect dynamometer cards from the famous Chinese Shengli Oil Field as research data. We first investigate properties of dynamometers under different working conditions and create a dynamometer card dataset. Furthermore, we introduce calibration/visualization preprocess methods and propose the Oil-Net 1-D/2-D identification models from the time-series and computer vision views, respectively. Experimental results indicate that compared with other machine learning and time-series classification methods, Oil-Net 1-D/2-D improves identification accuracy significantly. This study provides guidance for the design and implementation of learning-based oil well working conditions intelligent diagnosis system.
Förderung
- National Science Foundation of China
Zitieren
APA
Ma, R., Tian, H., Cheng, X., Xiao, Y., Xu, Q., & Yu, X. (2023). Oil-Net: A Learning-Based Framework for Working Conditions Diagnosis of Oil Well Through Dynamometer Cards Identification. IEEE Sensors Journal, 23(13), 14406-14417. https://doi.org/10.1109/jsen.2023.3275933
Vancouver
Ma R, Tian H, Cheng X, Xiao Y, Xu Q, Yu X. Oil-Net: A Learning-Based Framework for Working Conditions Diagnosis of Oil Well Through Dynamometer Cards Identification. IEEE Sensors Journal. 2023;23(13):14406-14417. doi:10.1109/jsen.2023.3275933
BibTeX
@article{Ma2023,
author = {Ma, Rong and Tian, Haifeng and Cheng, Xiaochun and Xiao, Yi and Xu, Qingxiao and Yu, Xianchuan},
title = {Oil-Net: A Learning-Based Framework for Working Conditions Diagnosis of Oil Well Through Dynamometer Cards Identification},
journal = {IEEE Sensors Journal},
year = {2023},
volume = {23},
number = {13},
pages = {14406--14417},
doi = {10.1109/jsen.2023.3275933}
}
EUVIMED