[HTML][HTML] Data-driven production optimization using particle swarm algorithm based on the ensemble-learning proxy model

SY Du, XG Zhao, CY Xie, JW Zhu, JL Wang, JS Yang… - Petroleum Science, 2023 - Elsevier
Production optimization is of significance for carbonate reservoirs, directly affecting the
sustainability and profitability of reservoir development. Traditional physics-based numerical …

User repurchase behavior prediction for integrated energy supply stations based on the user profiling method

X Cen, Z Chen, H Chen, C Ding, B Ding, F Li, F Lou… - Energy, 2024 - Elsevier
Under the guidance of the “Dual Carbon” goal, integrated energy supply stations have
gradually become an essential facility for the energy transition. Promoting user repurchase …

An intelligent data-driven model for virtual flow meters in oil and gas development

S Song, M Wu, J Qi, H Wu, Q Kang, B Shi… - … Research and Design, 2022 - Elsevier
Abstract In this work, Back Propagation (BP) neural network, Long Short-Term Memory
(LSTM) network and Random Forest algorithm are applied to establish an intelligent data …

[HTML][HTML] Characterizations of gas-liquid interface distribution and slug evolution in a vertical pipe

HY Yu, Q Xu, YQ Cao, B Huang, HX Wang, LJ Guo - Petroleum Science, 2023 - Elsevier
Large vertical pipes are key structures connecting subsea wells to offshore platforms.
However, existing studies mainly focus on small vertical pipes. In a vertical acrylic pipe with …

Damage identification for thermoplastic composite pipes using Transformer neural network and variational mode decomposition

X Bao, J Li, M Liu, J Wang, H Zhou, M Wang, W Wu… - Ocean …, 2024 - Elsevier
A damage identification method for Thermoplastic Composite Pipes (TCPs) is proposed,
which consists of two parts: firstly, a response signal preprocessing method based on …

Spatiotemporal simulation of gas-liquid transport in the production process of continuous undulating pipelines

X Li, Q Yang, X Xie, S Chen, C Pan, Z He, J Gong… - Energy, 2023 - Elsevier
Large sections of gas accumulation easily form in continuously undulating liquid pipelines to
impede the commissioning process affecting the safe operation of the pipeline. To solve the …

Detection Method for Bolt Loosening and Washer Damage in Flange Assembly Structures Based on Phased Array Ultrasonics

F Shang, B Sun, H Li, H Zhang, Z Liu… - Research in …, 2024 - Taylor & Francis
During the service life of flange assembly components, factors such as corrosion and
vibration can lead to washer damage and loosening of fastening bolts, resulting in fluid …

Prediction of instantaneous flow characteristics of hydrocyclone with long short-term memory network based on computational fluid dynamics data

E Dianyu, G Xu, J Cui, Q Ye, C Tan, R Zou, A Yu… - Powder Technology, 2024 - Elsevier
Accelerating the prediction time of separation performance and flow field characteristics in
industrial hydrocyclones holds paramount importance for real-time control. Machine learning …

Data-driven wireline sticking risk assessment and control factor analysis

F Qu, H Liao, XY Yan, K Wei, Y Xu, Z Lu - Geoenergy Science and …, 2023 - Elsevier
The risk of wireline sticking cannot be accurately predicted at wireline logging site. Once the
wireline is sticked on the wellbore, it seriously affects the logging process. A data-driven risk …

[HTML][HTML] A multiscale adaptive framework based on convolutional neural network: Application to fluid catalytic cracking product yield prediction

N Liu, CM Zhu, MX Zhang, XY Lan - Petroleum Science, 2024 - Elsevier
Since chemical processes are highly non-linear and multiscale, it is vital to deeply mine the
multiscale coupling relationships embedded in the massive process data for the prediction …