The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Pour connaître la situation de travail des puits souterrains pompés à tige, nous devons toujours analyser les diagrammes du dynamomètre, qui sont générés par le capteur de charge et le capteur de déplacement. Les puits pompés par tige sont généralement situés dans des endroits soumis à des conditions météorologiques extrêmes, et ces capteurs sont installés sur certains équipements pétroliers spéciaux en plein air. Au fil du temps, les capteurs ont tendance à générer des données instables et incorrectes. Malheureusement, les capteurs de charge sont trop coûteux pour être réinstallés fréquemment. Par conséquent, les diagrammes dynamométriques obtenus ne peuvent parfois pas établir un diagnostic précis. Au lieu de cela, en tant qu'équipement absolument nécessaire du puits pompé à tige, le moteur électrique a une durée de vie beaucoup plus longue et ne peut pas être facilement impacté par les intempéries. La courbe de puissance électrique pendant une période de prélèvement peut également refléter la situation de travail sous terre, mais elle est beaucoup plus difficile à expliquer que le diagramme du dynamomètre. Cette lettre présentait une nouvelle architecture d'apprentissage en profondeur, capable de transformer la courbe de puissance électrique en image de diagramme de dynamomètre sans dimension. Nous menons nos expériences sur un ensemble de données du monde réel et les résultats montrent que notre méthode peut obtenir une précision de transformation impressionnante.
Junfeng SHI
Petro China
Wenming MA
Yantai University
Peng SONG
Yantai University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Junfeng SHI, Wenming MA, Peng SONG, "Transform Electric Power Curve into Dynamometer Diagram Image Using Deep Recurrent Neural Network" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 8, pp. 2154-2158, August 2018, doi: 10.1587/transinf.2018EDL8027.
Abstract: To learn the working situation of rod-pumped wells under ground, we always need to analyze dynamometer diagrams, which are generated by the load sensor and displacement sensor. Rod-pumped wells are usually located in the places with extreme weather, and these sensors are installed on some special oil equipments in the open air. As time goes by, sensors are prone to generating unstable and incorrect data. Unfortunately, load sensors are too expensive to frequently reinstall. Therefore, the resulting dynamometer diagrams sometimes cannot make an accurate diagnosis. Instead, as an absolutely necessary equipment of the rod-pumped well, the electric motor has much longer life and cannot be easily impacted by the weather. The electric power curve during a swabbing period can also reflect the working situation under ground, but is much harder to explain than the dynamometer diagram. This letter presented a novel deep learning architecture, which can transform the electric power curve into the dimensionless dynamometer diagram image. We conduct our experiments on a real-world dataset, and the results show that our method can get an impressive transformation accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8027/_p
Copier
@ARTICLE{e101-d_8_2154,
author={Junfeng SHI, Wenming MA, Peng SONG, },
journal={IEICE TRANSACTIONS on Information},
title={Transform Electric Power Curve into Dynamometer Diagram Image Using Deep Recurrent Neural Network},
year={2018},
volume={E101-D},
number={8},
pages={2154-2158},
abstract={To learn the working situation of rod-pumped wells under ground, we always need to analyze dynamometer diagrams, which are generated by the load sensor and displacement sensor. Rod-pumped wells are usually located in the places with extreme weather, and these sensors are installed on some special oil equipments in the open air. As time goes by, sensors are prone to generating unstable and incorrect data. Unfortunately, load sensors are too expensive to frequently reinstall. Therefore, the resulting dynamometer diagrams sometimes cannot make an accurate diagnosis. Instead, as an absolutely necessary equipment of the rod-pumped well, the electric motor has much longer life and cannot be easily impacted by the weather. The electric power curve during a swabbing period can also reflect the working situation under ground, but is much harder to explain than the dynamometer diagram. This letter presented a novel deep learning architecture, which can transform the electric power curve into the dimensionless dynamometer diagram image. We conduct our experiments on a real-world dataset, and the results show that our method can get an impressive transformation accuracy.},
keywords={},
doi={10.1587/transinf.2018EDL8027},
ISSN={1745-1361},
month={August},}
Copier
TY - JOUR
TI - Transform Electric Power Curve into Dynamometer Diagram Image Using Deep Recurrent Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 2154
EP - 2158
AU - Junfeng SHI
AU - Wenming MA
AU - Peng SONG
PY - 2018
DO - 10.1587/transinf.2018EDL8027
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2018
AB - To learn the working situation of rod-pumped wells under ground, we always need to analyze dynamometer diagrams, which are generated by the load sensor and displacement sensor. Rod-pumped wells are usually located in the places with extreme weather, and these sensors are installed on some special oil equipments in the open air. As time goes by, sensors are prone to generating unstable and incorrect data. Unfortunately, load sensors are too expensive to frequently reinstall. Therefore, the resulting dynamometer diagrams sometimes cannot make an accurate diagnosis. Instead, as an absolutely necessary equipment of the rod-pumped well, the electric motor has much longer life and cannot be easily impacted by the weather. The electric power curve during a swabbing period can also reflect the working situation under ground, but is much harder to explain than the dynamometer diagram. This letter presented a novel deep learning architecture, which can transform the electric power curve into the dimensionless dynamometer diagram image. We conduct our experiments on a real-world dataset, and the results show that our method can get an impressive transformation accuracy.
ER -