FLIP Research Group

ESP Multiphase Boosting Mechanisms and Condition Diagnosis

Fri, 09 Oct 2026 00:00:00 +0000

When free gas enters an electrical submersible pump (ESP), boosting pressure degrades, then surges, and may end in gas lock. Traditional homogeneous-flow design applies only at very low gas fractions. The group studies the chain from bubble breakup and coalescence in the rotating impeller to in-situ gas void fraction, flow-pattern transition and boosting degradation, extending to high-viscosity, emulsion and sand-laden conditions.

Boosting degradation and surging under gassy conditions: experiment vs. mechanistic model

Experiments and mechanistic models. On the TUALP multistage two-phase ESP loop (14-stage TE-2700 with stage-by-stage taps) and the CUP centrifugal-pump visualization rig, high-speed imaging captures impeller flow patterns and surge onset. Critical bubble diameter, in-situ gas fraction and flow-pattern boundaries are modeled; a “best-matching rate” concept supports unified boosting models for single-phase, viscous, emulsified and gas–liquid conditions, validated on three ESP types (typical error within ±20%, average ~10%).

TUALP multistage two-phase ESP loop: schematic and stage-by-stage pressure taps

High-speed imaging of gas–liquid flow in a rotating impeller: bubble migration and gas-pocket formation

CFD. Eulerian two-fluid CFD with interfacial forces captures multistage gas–liquid flow and cross-stage pattern evolution; dynamic mode decomposition extracts dominant impeller modes. An NSFC General Program project addresses deep-sea mixed-flow ESPs.

CFD isosurface of in-situ gas fraction in a multistage ESP impeller

Wide-range offshore ESP hydraulic design and automated CFD optimization. For mid-to-late-life offshore wells with large rate swings and high gas fractions, the group designs wide-passage mixed-flow ESP impellers/diffusers (400/538 series): similarity scaling, Euler-head correction and specific-speed checks seed the base model; Python drives CFturbo–Workbench–PyFluent for geometry batching, mesh update, batch solve and surrogate-model search (Latin hypercube + Gaussian process). First-round sensitivity (Spearman) shows impeller exit width b₂ dominates BEP location (ρ≈0.74), cutting the design space from 10-D to 5-D.

Parametric impeller/diffuser models and automated CFD optimization workflow

Spearman sensitivity of impeller geometry on BEP and high-rate head

Condition diagnosis. Mechanistic boosting models are fused with machine learning into a real-time ESP management framework (condition recognition, fault diagnosis/early warning, remaining life), delivered as the “Intelligent ESP Management System V1.0” algorithm module.

Representative papers

L Peng, L Feng, Q Guang, J Zhu, H Liu, Z Nie, C Ma, C Di, Q Wu. Real-Time ESP Management Framework Using Hybrid Physics-Based and ML Models. SPE Offshore Europe Conference and Exhibition, D021S009R008, 2025.
Y Li, J Zhu, H Zeng, Y Zhang, Y Lu, Y Fan, H Zhu. An Indirect Approach for Flow Pattern Transition Identification Inside a Low-Specific-Speed Centrifugal Pump with Experimental Verification and Theoretical Modeling. SPE Journal 28 (01), 184-200, 2023.
H Zhu, J Zhu, HQ Zhang. Mechanistic modeling of gas effect on Multi-stage Electrical submersible pump (ESP) performance with experimental validation. Chemical Engineering Science 252, 117288, 2022.
J Zhu, H Zhao, G Cao, H Banjar, H Zhu, J Peng, HQ Zhang. A New Mechanistic Model for Emulsion Rheology and Boosting Pressure Prediction in Electrical Submersible Pumps (ESPs) under Oil-Water Two-Phase Flow. SPE Journal 26 (02), 667-684, 2021.
J Zhu, H Zhu, G Cao, J Zhang, J Peng, H Banjar, HQ Zhang. A New Mechanistic Model To Predict Boosting Pressure of Electrical Submersible Pumps Under High-Viscosity Fluid Flow with Validations by Experimental Data. SPE Journal 25 (02), 744-758, 2020.
J Zhu, J Zhang, G Cao, Q Zhao, J Peng, H Zhu, HQ Zhang. Modeling flow pattern transitions in electrical submersible pump under gassy flow conditions. Journal of Petroleum Science and Engineering 180, 471-484, 2019.
J Zhu, HQ Zhang. A review of experiments and modeling of gas-liquid flow in electrical submersible pumps. Energies 11 (1), 180, 2018.
J Zhu, X Guo, F Liang, HQ Zhang. Experimental study and mechanistic modeling of pressure surging in electrical submersible pump. Journal of Natural Gas Science and Engineering 45, 625-636, 2017.
J Zhu, HQ Zhang. Mechanistic modeling and numerical simulation of in-situ gas void fraction inside ESP impeller. Journal of Natural Gas Science and Engineering 36, 144-154, 2016.
J Zhu, H Banjar, Z Xia, HQ Zhang. CFD simulation and experimental study of oil viscosity effect on multi-stage electrical submersible pump (ESP) performance. Journal of Petroleum Science and Engineering 146, 735-745, 2016.

Facilities

Fri, 09 Oct 2026 00:00:00 +0000

The group’s experiments rely on the in-house centrifugal-pump gas–liquid visualization rig at China University of Petroleum (Beijing) and on the TUALP multistage ESP loop used by the PI at The University of Tulsa. A multistage pump visualization platform is being planned and built. Numerical simulation and model training run on the group’s two high-performance computing servers.

Centrifugal pump gas–liquid visualization rig (CUP)

Rebuilt from a centrifugal-pump hydraulic test bench (supported by NSFC Young Scientists Fund 52004304), the rig is used to test the boosting performance of ultra-low specific-speed centrifugal pumps at high water cut and high gas–liquid ratio, and to film the full flow passage of the rotating impeller at high speed. Main instruments include a PHANTOM V1212 high-speed motion analysis system, 8530B-200 high-frequency pressure transducers, 8530C-50 high-frequency differential-pressure transducers and a multichannel data acquisition system. Visualization has identified dispersed-bubble, bubbly, gas-pocket and segregated flow inside the impeller. Since 2025 the rig has been upgraded under an NSFC General Program grant: temperature control from 0 to 60 °C (±0.5 °C) and 5000 fps high-speed imaging.

Centrifugal pump test rig for high water cut and high gas–liquid ratio: flow loop, layout and main instruments, with boosting curves at different gas fractions

Visualization of the rotating impeller passage: high-speed camera, sensors and key specifications, with dispersed-bubble, bubbly and intermittent flow in the impeller

Labyrinth pump tests under high viscosity and gas entrainment

A labyrinth screw pump test rig is used to measure labyrinth pump performance with viscous and gassy fluids. The system includes a gas tank, a two-phase separator, a torque sensor, a variable-frequency drive and a data acquisition system; head–flow curves have been measured at different speeds and viscosities.

Labyrinth pump tests under high viscosity and gas entrainment: rotor and stator, test-rig flow loop, and head–flow curves at different speeds and viscosities

TUALP multistage ESP two-phase loop (The University of Tulsa)

University of Tulsa facility

This loop belongs to Tulsa University Artificial Lift Projects (TUALP) and is not a facility of this group. The PI, Jianjun Zhu, used it for ESP gas–liquid experiments during his Ph.D. study and work as a research associate at The University of Tulsa (2012–2019).

Main specifications: a 14-stage radial TE-2700 ESP (538 series) with stage-by-stage pressure taps; a 7.62 cm closed two-phase loop with a 24 m³ separator at 345/689/1034 kPa; speed 1800–3500 rpm; tap water and compressed air as working fluids, with optional IPA surfactant injection. The loop supports two-phase, high-viscosity, emulsion and sand-laden tests.

TUALP two-phase ESP loop schematic

TUALP test piping, 14-stage test pump and stage-by-stage pressure taps

Multistage pump impeller/diffuser multiphase visualization platform

Under construction / planned

This platform is at the planning and construction stage and has not been built yet. It is led by Jianjun Zhu, with a construction period from October 2025 to September 2028. The figures below are design targets from the feasibility report, not measured performance.

Three-stage impeller–diffuser train, switchable between 1 and 3 stages, with diffuser outlet angle adjustable by ±5°; transparent passages and quartz-glass windows.
4K high-speed imaging (1000 fps at full frame) and PIV to measure transient velocity fields and identify vortex structures.
Gas–liquid and solid–liquid transport: gas fraction ≤15%, particle size ≤1 mm, solid concentration ≤5%.
16-channel synchronized acquisition at 10 kHz; interlocked shutdown within 0.1 s when vibration or displacement exceeds limits.
Permanent-magnet synchronous motor with vector frequency control, 0–6000 rpm; flow 0–30 m³/h, pressure 0.6–3.0 MPa.

Platform concept (planned design, not a photo of built equipment)

Computing resources

The group operates two servers of its own, used for full-scale 3-D transient CFD of ESPs, wellbore multiphase-flow computation, and training of deep neural networks such as PINNs.

	Dual EPYC 9965 CPU–GPU server (2025)	Dual EPYC 7742 compute server
CPU	2 × AMD EPYC 9965, 384 physical cores in total	2 × AMD EPYC 7742, 128 cores / 256 threads
Memory	1 TB DDR5 (16 × 64 GB)	256 GB
GPU	2 × NVIDIA RTX 5090 (32 GB)	2 × NVIDIA RTX 4090 (24 GB), added in 2023
Storage	about 20 TB	about 10 TB
Main use	Large-scale parallel CFD, multiphysics coupling, PINN training	CFD simulation, deep-learning model training

The dual EPYC 9965 server, with two RTX 5090 GPUs, forms a CPU–GPU heterogeneous computing environment.

Liquid-cooled dual EPYC CPUs and 16 DIMMs

RTX 5090 GPU and liquid-cooling lines

Closed chassis

Hydraulic Jet Pumps for Gas-Well Deliquification

Fri, 09 Oct 2026 00:00:00 +0000

Research / Area 4

Hydraulic jet pumps have no moving parts downhole and tolerate sand, high gas–liquid ratio and deep wells, making them an important deliquification method for tight and horizontal gas wells. Cavitation and gas blocking in the throat, however, keep efficiency low, and nozzle/throat design methods for gas wells are lacking.

Concentric dual-tubing jet pump: 3D model, section and pressure distribution along nozzle–suction–throat–diffuser

Jet-pump deliquification performance curves

Gas–liquid two-phase CFD fields in a concentric dual-tubing jet pump

The group develops performance models and gas-blocking boundaries for concentric dual-tubing jet pumps, VOF simulations of gas–liquid flow, surrogate-model–based multi-objective optimization of nozzle and throat parameters, and field application analysis (including the Maoping-1 well).

Representative papers

J Zhu, A Li, Y Ji, J Peng, Y Zhang, H Zhu. Optimization of gas-liquid two-phase flow characteristic parameters in a concentric dual-tube hydraulic jet pump. The Chinese Journal of Process Engineering 26 (3), 233-244, 2026.

Intelligent Defect Recognition in Pipeline MFL In-Line Inspection

Fri, 09 Oct 2026 00:00:00 +0000

Research / Area 5

Magnetic flux leakage (MFL) in-line inspection is the main method for detecting corrosion and cracks in long-distance pipelines. One run produces massive signal data, while defect samples with excavation labels are scarce.

Cascaded framework: MFL acquisition and augmentation, YOLOv5 localization, ViT classification

MFL pull-test loop used for labeled defect signals

With Prof. Jianli Wang’s group at Southeast University, the group proposes cascaded deep learning: a pretrained YOLO network locates defects on MFL images, then a Vision Transformer or multi-input parallel CNN regresses defect length, width and depth. Diffusion models generate samples and reconstruct under-sampled signals.

Representative papers

J Xie, J Yang, K Fu, L Tai, X Wang, J Zhu, J Wang. Quantitative Assessment of Pipeline Defects Utilizing a Dual-Stage Deep Learning Framework: Integration of Pretrained YOLO Network and Multi-input Parallel Convolution …. Journal of Pipeline Science and Engineering, 100282, 2025.
J Yang, Y Zhang, C Su, K Fu, J Zhu, J Wang. Multi-Priors Tensor Completion for Highly Under-sampled Magnetic Flux Leakage Signal Reconstruction. Journal of Pipeline Science and Engineering, 100382, 2025.
J Yang, J Xie, X Gao, K Fu, J Zhu, J Wang. Synthetic Magnetic Flux Leakage Signal Generation Using Diffusion Models: A Novel Approach to Improve Pipeline Defect Detection Accuracy. Journal of Pipeline Science and Engineering, 100363, 2025.
X Chen, M Fu, X Liu, J Zhu. Synthesizing Labeled Magnetic Flux Leakage Signals for Pipeline Integrity Assessment: A Generation and Evaluation Methodology. IEEE Transactions on Instrumentation and Measurement, 2025.
P Chen, R Li, K Fu, Z Zhong, J Xie, J Wang, J Zhu. A cascaded deep learning approach for detecting pipeline defects via pretrained YOLOv5 and ViT models based on MFL data. Mechanical Systems and Signal Processing 206, 110919, 2024.

Jianjun Zhu

Fri, 09 Oct 2026 00:00:00 +0000

Jianjun Zhu PI

Associate Professor; Ph.D. and master's supervisor

Vice Dean, College of Mechanical and Transportation Engineering, China University of Petroleum (Beijing)

Faculty page · Google Scholar

Jianjun Zhu is Associate Professor and Vice Dean of the College of Mechanical and Transportation Engineering, China University of Petroleum (Beijing); Ph.D. and master’s supervisor. Discipline: Power Engineering and Engineering Thermophysics.

Biography

Young talent of the university. His work covers multiphase-flow modeling, artificial-lift system design and optimization, and oil and gas production data mining — including steady/transient multiphase flow, artificial-lift equipment and processes (ESP, plunger lift, jet pump, gas lift), and production big data with intelligent diagnosis. He was listed in the Elsevier–Stanford World’s Top 2% Scientists (single year, 2025–2026). He has led one NSFC Young Scientists Fund project, one NSFC General Program, one National Science and Technology Major Project sub-task, one CUP interdisciplinary frontier grant, open funds of national and Sinopec key labs, and more than 15 industry projects with CNPC, Sinopec and PipeChina. He has published over 100 papers (60+ SCI) with more than 3,500 Google Scholar citations (h-index 32, i10-index 61); given 21 oral talks and 4 invited talks at major international conferences; and published one translated book. Outstanding Reviewer for SPE Production & Operations (2022–2024) and SPE Journal (2025); First Prize, Science and Technology Progress Award, Chinese Nuclear Society (2025, 13/29).

Education and experience

2019–present, China University of Petroleum (Beijing)
2017–2019, Tulsa University Artificial Lift Projects (TUALP), Research Associate
2012–2017, Ph.D. in Petroleum Engineering, The University of Tulsa
2009–2012, M.S. in Power Engineering and Engineering Thermophysics, Tsinghua University
2005–2009, B.S. in Thermal Energy and Power Engineering, University of Science and Technology Beijing

Teaching

Fundamentals of Process Equipment Control; Modern Multiphase Flow Theory

Honors

First Prize, Science and Technology Progress Award, Chinese Nuclear Society (2025, 13/29), for data-driven key technologies in in-situ leach uranium mining
Elsevier–Stanford World’s Top 2% Scientists (single year, 2025–2026)
Honorary Young Editorial Board Member, Petroleum Science (2025)
Outstanding Reviewer, SPE Production & Operations (2022–2024) and SPE Journal (2025)

Professional service

Advisory committee member, SPE Data Science and Engineering Analytics (DSEA) section (2020–2023)
Young committee member, Heat and Mass Transfer Division, Chinese Society of Engineering Thermophysics
SPE award committee member: Cedric K. Ferguson Award (2026–2029); Distinguished Achievement Award for Petroleum Engineering Faculty (2024–2027); Production & Operations Award (2025–2028); Projects, Facilities & Construction Award (2025–2028)
SPE ATCE committee member (since 2022): Well Operations (2023); Production and Operations Subcommittee (since 2023)
Reviewer for NSFC and the Czech Science Foundation
Young editorial boards: Petroleum Science (appointed 2020; honorary 2025); Chemical Engineering & Machinery (since 2022); Third Young Editorial Board of China Petroleum Machinery (2027–2028)
Guest editor: Energies / Applied Sciences (since 2021); Frontiers in Physics (since 2021)
Member of SPE and ASME
Regular reviewer for SPE Journal, Journal of Energy Storage, Mechanical Systems and Signal Processing, Geoenergy Science and Engineering, Engineering Applications of Artificial Intelligence, Petroleum Science, Neural Computing and Applications, IEEE TIM, IEEE Sensors Journal, and others

Main collaborators

On campus: Zhongli Ji, Yongxue Zhang, Yan Li, Hongwu Zhu, Jianfei Song and others
External: Prof. Jianli Wang, Southeast University (co-PI); Haiwen Zhu and Hong-Quan Zhang, The University of Tulsa

Jianli Wang

Fri, 09 Oct 2026 00:00:00 +0000

Jianli Wang co-PI

Professor; Ph.D. and master's supervisor

Department of Design Science, School of Mechanical Engineering, Southeast University

Faculty page

Jianli Wang is Professor in the School of Mechanical Engineering, Southeast University; Ph.D. and master’s supervisor. Department: Design Science.

Biography

His research covers test-system development and sensing, machine learning, and energy-system optimization. He received his B.S. from Xi’an Jiaotong University (Energy and Power Engineering, 2005) and Ph.D. from Tsinghua University (Power Engineering and Engineering Thermophysics, 2010), then joined Southeast University. He visited Caltech (2012) and Purdue (2014). He received the First Prize for Outstanding Doctoral Dissertation of Tsinghua University (2010) and a nomination for the National 100 Outstanding Doctoral Dissertations (2014). He has led four NSFC projects and industry collaborations with Sinopec, Dongfang Electric, Kunming Institute of Physics and others.

Research interests

Test-system development and sensing; intelligent analysis and inspection; energy-saving system design and optimization.

Education and experience

2005, B.S., School of Energy and Power Engineering, Xi’an Jiaotong University
2010, Ph.D., School of Aerospace Engineering, Tsinghua University (Power Engineering and Engineering Thermophysics)
2010–present, Lecturer / Associate Professor / Professor, School of Mechanical Engineering, Southeast University
Sep 2012 – Feb 2013, Caltech, collaborative research on thermoelectric materials
Oct 2013 – Oct 2014, Purdue University, Mechanical Engineering, thermoelectric thin films

Professional service

Council member, Chinese Society for Micro/Nano Measurement and Instrumentation
Committee member, Thermal Properties Committee, Chinese Society for Measurement
Young committee member, Shanghai Thermal Properties Big-Data Service Center
Committee member, Marine Power Division, Chinese Society of Naval Architects and Marine Engineers
Editorial board member, Acta Metrologica Sinica
Reviewer for NSFC

Selected joint papers with this group

Y Zhang, H Zeng, C Su, J Yang, J Zhu, Jianli Wang*, Lightweight Vision Transformer for Real-Time Threat Level Assessment in Φ-OTDR-Based Pipeline Monitoring, Applied Sciences 2026, 16 (3), 1664
J Yang, J Xie, X Gao, K Fu, J Zhu, Jianli Wang*, Synthetic Magnetic Flux Leakage Signal Generation Using Diffusion Models: A Novel Approach to Improve Pipeline Defect Detection Accuracy, Journal of Pipeline Science and Engineering, 2025, 100363
Saifei Ma, Tiantian Zhang, Haibo Wang, Haoyu Wang, Nan Li, Haiwen Zhu, Jianjun Zhu, Jianli Wang*, Transformer-Based Forecasting for High Frequency Natural Gas Production Data, Energy and AI, 2025, 21:100535
Jialiang Xie, Jie Yang, Kuan Fu, Linxi Tai, Xia Wang, Jianjun Zhu, Wang J L*, Quantitative Assessment of Pipeline Defects Utilizing a Dual-Stage Deep Learning Framework: Integration of Pretrained YOLO Network and Multi-input Parallel Convolution Architectures on Magnetic Flux Leakage Data, Journal of Pipeline Science and Engineering, 2025, 100282
Jiang QM, Zhang Y H, Liu Y, Xu R, Zhu J J, Wang J L*. Structural optimization of serpentine channel water-cooled plate for lithium-ion battery modules based on multi-objective Bayesian optimization algorithm. Journal of Energy Storage 2024, 91: 112136

Full publication list: .

Email: (public on faculty page)

Join Us

Fri, 09 Oct 2026 00:00:00 +0000

Admissions

Programs: Mechanical Engineering; Mechanical Engineering (professional); Power Engineering and Engineering Thermophysics

We admit Ph.D. and master’s students every year. See for our research areas.

Who we welcome

Students with backgrounds in energy and power, mechanical engineering, automation, AI, data science, oil and gas storage and transportation, or petroleum production engineering; solid science/engineering and English foundations; at least one programming language (Python/Julia/Matlab/Octave/Fortran/C++, etc.); curiosity about new technology, and enjoyment of interdisciplinary teamwork.

The group co-supervises students with Prof. Jianli Wang of Southeast University. Students interested in joint training are welcome to get in touch.

Contact

Prospective students are welcome to email us with a CV.

Email:

Address: College of Mechanical and Transportation Engineering, China University of Petroleum (Beijing), 18 Fuxue Road, Changping, Beijing 102249, China

News

Fri, 09 Oct 2026 00:00:00 +0000

Oct 2026 Jianjun Zhu gave an industry talk on advances in gas-well deliquification research.
Sep 2026 Jianjun Zhu joined the Third Young Editorial Board of China Petroleum Machinery (2027–2028).
Sep 2026 Jianjun Zhu chaired a session at the 2nd High-End Oil and Gas Equipment Technology Forum.
Mar 2026 Software “Horizontal Gas Well Transient Simulator V1.0” registered (2026SR0412776).
Dec 2025 Jianjun Zhu named Honorary Young Editorial Board Member of Petroleum Science.
Nov 2025 “Intelligent ESP Management System V1.0”, commissioned by PetroChina Dubai Research Institute, passed acceptance.
2025 First Prize, Science and Technology Progress Award, Chinese Nuclear Society (13/29).
2025 Jianjun Zhu listed in the Elsevier–Stanford World’s Top 2% Scientists (single year).
Jan 2025 NSFC General Program project on deep-sea ESP oil–gas flow mechanisms and transient multiphase modeling (52474064) started.

Oil and Gas Field Big-Data Analytics

Fri, 09 Oct 2026 00:00:00 +0000

Research / Area 6

Wellhead pressure, rate and chemical-injection data accumulate continuously as gas fields mature, but field decisions still rely largely on rules of thumb. The group uses data-driven modeling, risk-aware decision-making and deep anomaly diagnosis to move from post-hoc review to online recommendation.

Overall framework: field data → sample library → world model → planning agent → recommended dosage, in closed loop

Action-conditioned world model for next-step tubing–casing pressure-difference prediction

Risk-aware planning agent (RAPA) with layered risk rewards

Dynamic foaming-agent injection actions: RAPA vs. SAC, PSO, XGBoost and field baseline

Foam-assisted deliquification. With Prof. Jianli Wang’s group, foaming-agent dosage optimization is reformulated as a short-term decision problem driven by tubing–casing pressure-difference risk. An action-conditioned world model predicts the next pressure difference for candidate dosages, and a risk-aware planning agent (RAPA) selects actions with layered risk rewards.

Representative papers

Y Zhang, H Wang, M Chen, N Li, J Zhu, J Wang. A data-driven world-model-based planning agent for risk-aware foam-lifting agent injection optimization in gas wells. Geoenergy Science and Engineering, manuscript submitted (GEOEN-S-26-02523), 2026.
J Zhu, Y Liu, H Wang, M Chen, N Li, G Cao, R Zhong, H Zhu. Enhancing Plunger Lift Anomaly Detection: A Vision Transformer-Based Approach Leveraging Pretrained Models and Graphic Data Augmentation. Processes 14 (13), 2045, 2026.
J Zhu, Y Liu, M Chen, H Wang, Y Li, H Zhu. Enhanced Zero-Shot Classification of Plunger Lift Operating Conditions Using a Modified Clip Architecture with Selective Data Sampling. Results in Engineering, 110368, 2026.
Q Wang, H Zou, C Liang, S Zhang, H Jia, J Zhu. A combined approach for predicting liquid loading onset via clustering and convolutional neural networks. The Canadian Journal of Chemical Engineering, 2026.
QX Liu, JJ Zhu, HB Wang, S Chen, HY Wang, N Li, RZ Zhong, YJ Liu et al. Deep Feature Learning for Anomaly Detection in Gas Well Deliquification using Plunger Lift: A Novel CNN-based Approach. Petroleum Science, 2025.
L Peng, L Feng, Q Guang, J Zhu, H Liu, Z Nie, C Ma, C Di, Q Wu. Real-Time ESP Management Framework Using Hybrid Physics-Based and ML Models. SPE Offshore Europe Conference and Exhibition, D021S009R008, 2025.
Z Zhong, H Wang, N Li, H Zhu, J Zhu, J Wang. Prediction of Plunger Lift Dynamics Using a Bidirectional Long Short-Term Memory Neural Network with an Innovative Forecasting Strategy. 2024 IEEE 3rd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), 2024.
Z Xu, H Lin, Y Jia, J Du, J Mao, J Zhu, J Chen, F Li, N Li. Data Augmentation and Recognition for Plunger Lift Based on Variational Autoencoders. 2024 6th International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP), 2024.
Y Xie, S Ma, H Wang, N Li, J Zhu, J Wang. Unsupervised clustering for the anomaly diagnosis of plunger lift operations. Geoenergy Science and Engineering 231, 212305, 2023.
J Zhu, G Cao, W Tian, Q Zhao, H Zhu, J Song, J Peng, Z Lin, HQ Zhang. Improved data mining for production diagnosis of gas wells with plunger lift through dynamic simulations. SPE Annual Technical Conference and Exhibition, D021S030R001, 2019.

Outputs

Fri, 09 Oct 2026 00:00:00 +0000

Representative papers

The group has published over 100 papers (60+ SCI-indexed) with more than 3,500 Google Scholar citations (h-index 32, i10-index 61). Representative papers by year are listed below; the full list is on . Selected papers by research area are on the detail pages.

2026

Q Wang, H Zou, C Liang, S Zhang, H Jia, J Zhu. A combined approach for predicting liquid loading onset via clustering and convolutional neural networks. The Canadian Journal of Chemical Engineering, 2026.
J Zhu, Y Liu, H Wang, M Chen, N Li, G Cao, H Zhu. Optimizing Plunger Lift Systems for Gas Well Deliquification: A Bayesian Approach with Comparative Algorithmic Analysis. SPE Journal, 1-15, 2026.
J Zhu, Y Liu, H Wang, M Chen, N Li, G Cao, R Zhong, H Zhu. Enhancing Plunger Lift Anomaly Detection: A Vision Transformer-Based Approach Leveraging Pretrained Models and Graphic Data Augmentation. Processes 14 (13), 2045, 2026.
J Zhu, Y Liu, M Chen, H Wang, Y Li, H Zhu. Enhanced Zero-Shot Classification of Plunger Lift Operating Conditions Using a Modified Clip Architecture with Selective Data Sampling. Results in Engineering, 110368, 2026.
J Zhu, A Li, Y Ji, J Peng, Y Zhang, H Zhu. Optimization of gas-liquid two-phase flow characteristic parameters in a concentric dual-tube hydraulic jet pump. The Chinese Journal of Process Engineering 26 (3), 233-244, 2026.
C Zhang, Q Li, J Zhang, J Zhu, Y Wang. Energy conversion mechanisms and flow boundaries of gas–liquid multiphase flow in a mixed-flow electrical submersible pump for offshore oilfields. Physics of Fluids 38 (9), 2026.
C Zhang, H Jia, X Zhang, Q Li, Y Li, Y Zhang, H Zhu, J Zhu. Flow Structure Analysis in a Rotating Centrifugal Impeller under Gassy Conditions Using Dynamic Mode Decomposition. Journal of Energy Resources Technology, Part B: Subsurface Energy and Carbon , 2026.
Y Zhang, H Zeng, C Su, J Yang, J Zhu, J Wang. Lightweight Vision Transformer for Real-Time Threat Level Assessment in Φ-OTDR-Based Pipeline Monitoring. Applied Sciences 16 (3), 1664, 2026.

2025

J Yang, M Chen, H Wang, R Zheng, Z Li, H Zhou, J Zhu. Fast Calculation Method of Two-Phase Flow in Horizontal Gas Wells Based on PI-DeepONet. Processes 13 (10), 3363, 2025.
L Peng, L Feng, Q Guang, J Zhu, H Liu, Z Nie, C Ma, C Di, Q Wu. Real-Time ESP Management Framework Using Hybrid Physics-Based and ML Models. SPE Offshore Europe Conference and Exhibition, D021S009R008, 2025.
QX Liu, JJ Zhu, HB Wang, S Chen, HY Wang, N Li, RZ Zhong, YJ Liu et al. Deep Feature Learning for Anomaly Detection in Gas Well Deliquification using Plunger Lift: A Novel CNN-based Approach. Petroleum Science, 2025.
J Xie, J Yang, K Fu, L Tai, X Wang, J Zhu, J Wang. Quantitative Assessment of Pipeline Defects Utilizing a Dual-Stage Deep Learning Framework: Integration of Pretrained YOLO Network and Multi-input Parallel Convolution …. Journal of Pipeline Science and Engineering, 100282, 2025.
J Yang, Y Zhang, C Su, K Fu, J Zhu, J Wang. Multi-Priors Tensor Completion for Highly Under-sampled Magnetic Flux Leakage Signal Reconstruction. Journal of Pipeline Science and Engineering, 100382, 2025.
J Yang, J Xie, X Gao, K Fu, J Zhu, J Wang. Synthetic Magnetic Flux Leakage Signal Generation Using Diffusion Models: A Novel Approach to Improve Pipeline Defect Detection Accuracy. Journal of Pipeline Science and Engineering, 100363, 2025.
X Chen, M Fu, X Liu, J Zhu. Synthesizing Labeled Magnetic Flux Leakage Signals for Pipeline Integrity Assessment: A Generation and Evaluation Methodology. IEEE Transactions on Instrumentation and Measurement, 2025.
S Ma, T Zhang, H Wang, H Wang, N Li, H Zhu, J Zhu, J Wang. Transformer-based forecasting for high-frequency natural gas production data. Energy and AI 21, 100535, 2025.

2024

H Zhu, Y Liu, D Tychus, D Zheng, SP Adiraju, TS Tatu, J Zhu, HQ Zhang. Sensitivity analysis on tailpipe design for mitigating terrain slug in horizontal wells. Geoenergy Science and Engineering 235, 212598, 2024.
M Chen, J Zhu, G Cao, N Li, H Wang, H Zhu, M Jia, X Yang, D Guo. Plunger Lift Working Cycle Optimization using a Dynamic Full-Cycle Model Coupled with Simultaneous Perturbation Stochastic Approximation (SPSA) Algorithm. Abu Dhabi International Petroleum Exhibition and Conference, D021S036R003, 2024.
P Chen, R Li, K Fu, Z Zhong, J Xie, J Wang, J Zhu. A cascaded deep learning approach for detecting pipeline defects via pretrained YOLOv5 and ViT models based on MFL data. Mechanical Systems and Signal Processing 206, 110919, 2024.
Z Zhong, H Wang, N Li, H Zhu, J Zhu, J Wang. Prediction of Plunger Lift Dynamics Using a Bidirectional Long Short-Term Memory Neural Network with an Innovative Forecasting Strategy. 2024 IEEE 3rd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), 2024.
Z Xu, H Lin, Y Jia, J Du, J Mao, J Zhu, J Chen, F Li, N Li. Data Augmentation and Recognition for Plunger Lift Based on Variational Autoencoders. 2024 6th International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP), 2024.
J Zhu, Y Ji, J Peng, H Zhu. A new mechanistic model on boosting pressure of Electrical Submersible Pumps (ESPs) under gas-liquid two-phase flow. Petroleum Science Bulletin 9 (1), 130-147, 2024.

2023

Z Wang, W Fu, H Li, J Zhu. Multiphase flow behavior in the deep-stratum and deep-water wellbores. Frontiers Media SA, 2023.
H Wang, J Du, J Chen, G Cao, N Li, J Zhu, M Jia, X Yang. A New Method to Calculate Loading Liquid Water of Gas Wells in Qinghai Oilfield. International Petroleum Technology Conference, D032S052R001, 2023.
Y Li, J Zhu, H Zeng, Y Zhang, Y Lu, Y Fan, H Zhu. An Indirect Approach for Flow Pattern Transition Identification Inside a Low-Specific-Speed Centrifugal Pump with Experimental Verification and Theoretical Modeling. SPE Journal 28 (01), 184-200, 2023.
Y Xie, S Ma, H Wang, N Li, J Zhu, J Wang. Unsupervised clustering for the anomaly diagnosis of plunger lift operations. Geoenergy Science and Engineering 231, 212305, 2023.
W Ke, H Zeng, Z Wang, H Yu, Y Liu, D Zheng, J Zhu, H Zhu. A Numerical Study on Labyrinth Screw Pump (LSP) Performance under Viscous Fluid Flow. Energies 16 (16), 5997, 2023.

2022

H Jia, J Zhu, G Cao, Y Lu, B Lu, H Zhu. A model ranking approach for liquid loading onset predictions. SPE Production & Operations 37 (03), 370-382, 2022.
H Zhu, J Zhu, HQ Zhang. Mechanistic modeling of gas effect on Multi-stage Electrical submersible pump (ESP) performance with experimental validation. Chemical Engineering Science 252, 117288, 2022.

2021

J Zhu, H Zhao, G Cao, H Banjar, H Zhu, J Peng, HQ Zhang. A New Mechanistic Model for Emulsion Rheology and Boosting Pressure Prediction in Electrical Submersible Pumps (ESPs) under Oil-Water Two-Phase Flow. SPE Journal 26 (02), 667-684, 2021.
Q Zhao, J Zhu, G Cao, H Zhu, HQ Zhang. Transient modeling of plunger lift for gas well deliquification. SPE Journal 26 (05), 2928-2947, 2021.
J Zhu, H Jia, H Wang, G Cao, H Zhu. Modeling and applications of plunger lift for gas well deliquification via a transient multiphase simulator. Petroleum Science Bulletin 6 (4), 626-637, 2021.
Y Shi, J Zhu, H Wang, H Zhu, J Zhang, HQ Zhang. Experiments and mechanistic modeling of viscosity effect on a multistage ESP performance under viscous fluid flow. Proceedings of the Institution of Mechanical Engineers, Part A: Journal of , 2021.
H Zhu, J Zhu, Z Lin, Q Zhao, R Rutter, HQ Zhang. Performance degradation and wearing of Electrical Submersible Pump (ESP) with gas-liquid-solid flow: Experiments and mechanistic modeling. Journal of Petroleum Science and Engineering 200, 108399, 2021.
H Zhu, J Zhu, R Rutter, HQ Zhang. Experimental Study on Deteriorated Performance, Vibration, and Geometry Changes of an Electrical Submersible Pump Under Sand Water Flow Condition. Journal of Energy Resources Technology 143 (8), 082104, 2021.

2020

J Zhu, H Zhu, G Cao, J Zhang, J Peng, H Banjar, HQ Zhang. A New Mechanistic Model To Predict Boosting Pressure of Electrical Submersible Pumps Under High-Viscosity Fluid Flow with Validations by Experimental Data. SPE Journal 25 (02), 744-758, 2020.
C Wang, Y Zhang, J Zhang, J Zhu. Flow pattern recognition inside a rotodynamic multiphase pump via developed entropy production diagnostic model. Journal of Petroleum Science and Engineering 194, 107467, 2020.

2019

SY Nahri, Y Chen, W Williams, O Santos, L Thibodeaux, J Zhu. Understanding the Phenomenon of Dissolved Gas Migration of Gas in Riser During Drilling Operations. International Conference on Offshore Mechanics and Arctic Engineering 58875 …, 2019.
J Zhu, J Zhang, G Cao, Q Zhao, J Peng, H Zhu, HQ Zhang. Modeling flow pattern transitions in electrical submersible pump under gassy flow conditions. Journal of Petroleum Science and Engineering 180, 471-484, 2019.
J Zhu, G Cao, W Tian, Q Zhao, H Zhu, J Song, J Peng, Z Lin, HQ Zhang. Improved data mining for production diagnosis of gas wells with plunger lift through dynamic simulations. SPE Annual Technical Conference and Exhibition, D021S030R001, 2019.
J Zhu, H Zhu, Q Zhao, W Fu, Y Shi, HQ Zhang. A transient plunger lift model for liquid unloading from gas wells. International Petroleum Technology Conference, D021S047R002, 2019.
H Zhu, J Zhu, R Rutter, HQ Zhang. A numerical study on erosion model selection and effect of pump type and sand characters in electrical submersible pumps by sandy flow. Journal of Energy Resources Technology 141 (12), 122004, 2019.
J Zhu, H Zhu, J Zhang, HQ Zhang. A numerical study on flow patterns inside an electrical submersible pump (ESP) and comparison with visualization experiments. Journal of Petroleum Science and Engineering 173, 339-350, 2019.

2018

J Zhu, HQ Zhang. A review of experiments and modeling of gas-liquid flow in electrical submersible pumps. Energies 11 (1), 180, 2018.
J Zhu, H Zhu, Z Wang, J Zhang, R Cuamatzi-Melendez, JAM Farfan, .... Surfactant Effect on Air/Water Flow in a Multistage Electrical Submersible Pump (ESP). Experimental Thermal and Fluid Science, 2018.

2017

J Zhu, X Guo, F Liang, HQ Zhang. Experimental study and mechanistic modeling of pressure surging in electrical submersible pump. Journal of Natural Gas Science and Engineering 45, 625-636, 2017.
J Zhu, HQ Zhang. Numerical study on electrical-submersible-pump two-phase performance and bubble-size modeling. SPE Production & Operations 32 (03), 267-278, 2017.

2016

J Zhu, HQ Zhang. Mechanistic modeling and numerical simulation of in-situ gas void fraction inside ESP impeller. Journal of Natural Gas Science and Engineering 36, 144-154, 2016.
J Zhu, H Banjar, Z Xia, HQ Zhang. CFD simulation and experimental study of oil viscosity effect on multi-stage electrical submersible pump (ESP) performance. Journal of Petroleum Science and Engineering 146, 735-745, 2016.

Research projects

Government-funded projects

Project	Source	Period
Deep-sea ESP oil–gas multiphase flow mechanisms and transient multiphase modeling	NSFC General Program	2025–2028
Gas-production process selection and fine optimization across coal-measure gas stages (sub-task)	National Science and Technology Major Project	2025–2029
Multiphase flow theory for complex media in ultra-deep wellbores under HTHP	CUP Beijing interdisciplinary frontier exploration grant	2025–2028
Gas–liquid flow-pattern transition mechanisms and dynamics in high-shear ESP fields	NSFC Young Scientists Fund	2021–2023
Gas–liquid transport mechanisms in multistage ESPs	CUP Beijing talent start-up fund	2019–2022

Industry-sponsored projects

Project	Source	Period
Intelligent ESP Management System V1.0	PetroChina Dubai Research Institute	2025
Transient two-phase modeling and module development for horizontal gas wells	PetroChina Research Institute of Petroleum Exploration & Development	2024–2025
Jet-pump gas-blocking critical conditions and operating-parameter optimization	Bohai Drilling Engineering Technology Research Institute	2023
Plunger-lift intelligent optimization packaging and multi-parameter downhole plunger tests	PetroChina Research Institute of Petroleum Exploration & Development	2023
3D inversion of corrosion defects and quantitative recognition of IMU ILI data	PipeChina Science & Technology Research Institute	2023
Complex wellbore multiphase modeling coupled with artificial-lift systems	CNPC Science and Technology Research Institute	2022–2023
Big-data diagnosis of abnormal plunger-lift conditions	PetroChina Research Institute of Petroleum Exploration & Development	2022–2023
Full-cycle plunger-lift dynamics and intelligent optimization for gas wells	Sinopec shale oil & gas key lab open fund	2021–2023
Multi-condition ESP wellbore lift-parameter simulation methods	Sinopec Shengli Oilfield	2021–2022
Applicability analysis and software testing of liquid-loading diagnosis models for vertical and horizontal gas wells	PetroChina Research Institute of Petroleum Exploration & Development	2021–2022
Testing and refinement of ML-based plunger-lift condition diagnosis	PetroChina Research Institute of Petroleum Exploration & Development	2020
Plunger-lift anomaly diagnosis, classification and production-data mining (TUALP, University of Tulsa)	eLynx Technologies (USA)	2018–2020
ESP technology for viscous, emulsified and sandy conditions — development and training (TUALP, University of Tulsa)	Mexican Petroleum Institute (IMP)	2016–2018

Software copyrights

Software / module	Main functions	Registration / delivery
Horizontal Gas Well Transient Simulator V1.0	Drift-flux transient model, OLGA data management, dynamic visualization	Software copyright 2026SR0412776 (2026)
Intelligent ESP Management System V1.0（algorithm module）	Condition recognition, fault early warning, life prediction, mechanistic models	PetroChina Dubai Research Institute (2025)
ESP multi-condition hydraulic design and performance analysis software v1.0	Performance prediction for single-phase, viscous, emulsified and gas–liquid conditions	NSFC Young Scientists Fund
Intelligent jet-pump condition analysis software	Two-/three-phase calculation, gas-block check, parameter optimization	Bohai Drilling (2023)
Plunger-lift anomaly diagnosis program	CNN diagnosis and online diagnosis UI	PetroChina Research Institute of Petroleum Exploration & Development（2023）
Gas-well liquid-loading diagnosis model library	48 liquid-loading models with clustering-based selection	PetroChina Research Institute of Petroleum Exploration & Development（2022）

Horizontal Gas Well Transient Simulator V1.0

Intelligent ESP Management System V1.0

Intelligent jet-pump condition analysis software

Awards

First Prize, Science and Technology Progress Award, Chinese Nuclear Society (2025), for data-driven key technologies in in-situ leach uranium mining
Listed in the Elsevier–Stanford World’s Top 2% Scientists (single-year, 2025–2026)
Honorary Young Editorial Board Member, Petroleum Science (2025)
Outstanding Reviewer Contribution Award, SPE Journal (2025)
Outstanding Reviewer Contribution Award, SPE Production & Operations (2022–2024, three consecutive years)

Plunger Lift Transient Modeling and Intelligent Diagnosis

Fri, 09 Oct 2026 00:00:00 +0000

Research / Area 3

Plunger lift is the main intermittent deliquification method for gas wells, but plunger motion cannot be observed downhole and schedules are often set by experience.

Typical plunger-lift installation (left) and tubing/casing pressure and rate over one lift cycle (right)

Transient models. OLGA well–plunger–controller–reservoir models are history-matched with field pressures, and an in-house full-cycle plunger dynamics model coupled with the unified multiphase flow model matches OLGA on the main operating parameters with about 90% accuracy. Using it as a digital well, open/shut-in schedules are optimized with SPSA and Bayesian optimization.

Intelligent diagnosis. CNN, ViT, VAE-based data augmentation and zero-shot CLIP-style models identify abnormal plunger-well conditions from tubing/casing pressure curves.

Representative papers

J Zhu, Y Liu, H Wang, M Chen, N Li, G Cao, H Zhu. Optimizing Plunger Lift Systems for Gas Well Deliquification: A Bayesian Approach with Comparative Algorithmic Analysis. SPE Journal, 1-15, 2026.
J Zhu, Y Liu, H Wang, M Chen, N Li, G Cao, R Zhong, H Zhu. Enhancing Plunger Lift Anomaly Detection: A Vision Transformer-Based Approach Leveraging Pretrained Models and Graphic Data Augmentation. Processes 14 (13), 2045, 2026.
J Zhu, Y Liu, M Chen, H Wang, Y Li, H Zhu. Enhanced Zero-Shot Classification of Plunger Lift Operating Conditions Using a Modified Clip Architecture with Selective Data Sampling. Results in Engineering, 110368, 2026.
QX Liu, JJ Zhu, HB Wang, S Chen, HY Wang, N Li, RZ Zhong, YJ Liu et al. Deep Feature Learning for Anomaly Detection in Gas Well Deliquification using Plunger Lift: A Novel CNN-based Approach. Petroleum Science, 2025.
M Chen, J Zhu, G Cao, N Li, H Wang, H Zhu, M Jia, X Yang, D Guo. Plunger Lift Working Cycle Optimization using a Dynamic Full-Cycle Model Coupled with Simultaneous Perturbation Stochastic Approximation (SPSA) Algorithm. Abu Dhabi International Petroleum Exhibition and Conference, D021S036R003, 2024.
Y Xie, S Ma, H Wang, N Li, J Zhu, J Wang. Unsupervised clustering for the anomaly diagnosis of plunger lift operations. Geoenergy Science and Engineering 231, 212305, 2023.
Q Zhao, J Zhu, G Cao, H Zhu, HQ Zhang. Transient modeling of plunger lift for gas well deliquification. SPE Journal 26 (05), 2928-2947, 2021.
J Zhu, H Jia, H Wang, G Cao, H Zhu. Modeling and applications of plunger lift for gas well deliquification via a transient multiphase simulator. Petroleum Science Bulletin 6 (4), 626-637, 2021.
J Zhu, G Cao, W Tian, Q Zhao, H Zhu, J Song, J Peng, Z Lin, HQ Zhang. Improved data mining for production diagnosis of gas wells with plunger lift through dynamic simulations. SPE Annual Technical Conference and Exhibition, D021S030R001, 2019.
J Zhu, H Zhu, Q Zhao, W Fu, Y Shi, HQ Zhang. A transient plunger lift model for liquid unloading from gas wells. International Petroleum Technology Conference, D021S047R002, 2019.

Research

Fri, 09 Oct 2026 00:00:00 +0000

FLIP’s research covers flow, lift and production data of oil and gas wells from the bottom hole to the surface, in six areas. Experiments, numerical simulation (CFD, OLGA), mechanistic modeling and data-driven methods are combined and cross-validated. Full publication list: .

Wellbore Multiphase Flow Modeling and Liquid-Loading Prediction

Steady-state unified wellbore multiphase flow model and transient drift-flux model for horizontal gas wells; PINN-based fast computation; liquid-loading prediction and critical-velocity model selection.

Details →

ESP Multiphase Boosting Mechanisms and Condition Diagnosis

Boosting degradation of electrical submersible pumps under gassy, viscous and emulsified conditions; hydraulic design and CFD optimization of wide-range offshore ESPs; mechanism–data fusion diagnosis.

Details →

Plunger Lift Transient Modeling and Intelligent Diagnosis

Full-cycle plunger dynamics model and OLGA transient simulation; open/shut-in schedule optimization; deep-learning diagnosis of abnormal plunger-well conditions.

Details →

Hydraulic Jet Pumps for Gas-Well Deliquification

Two-/three-phase performance models of concentric dual-tubing jet pumps and gas-blocking limits; VOF simulation, surrogate models and multi-objective optimization.

Details →

Intelligent Defect Recognition in Pipeline MFL In-Line Inspection

Cascaded deep learning for defect detection and sizing from magnetic flux leakage signals; diffusion-model sample generation and reconstruction of under-sampled signals.

Details →

Oil and Gas Field Big-Data Analytics

Data-driven world models and risk-aware planning agents built on production time series such as foaming-agent injection; diagnosis for plunger and ESP wells.

Details →

Team

Fri, 09 Oct 2026 00:00:00 +0000

Group leaders

Jianjun Zhu PI

Associate Professor; Ph.D. and master's supervisor

Vice Dean, College of Mechanical and Transportation Engineering, China University of Petroleum (Beijing)

Profile → · Google Scholar

Jianli Wang co-PI

Professor; Ph.D. and master's supervisor

Department of Design Science, School of Mechanical Engineering, Southeast University

Profile → · Faculty page

Students

Current

Qin Ziyi（Ph.D. student）

Mechanistic models for gas–liquid two-phase flow in wellbores and pipelines; intelligent diagnosis of abnormal production in shale-gas and plunger-lift wells

Wu Yuxi（Ph.D. student）

One-dimensional mechanistic head model and CFD for ESP oil–gas(–water) multiphase flow

Jia Hao（Ph.D. student）

uranium in-situ leaching equipment, artificial lift, etc.

Nan Zibin（Master's student）

Gas–liquid multiphase CFD and structural optimization of all-metal single-screw pumps

Cheng Yuni（Master's student）

Dynamic response of FLNG liquefaction modules under multi-source coupled excitation

Li Jianing（Master's student）

Transient gas–liquid two-phase flow in pipelines: drift-flux model and X-PINN reconstruction

Li Jinhua（Master's student）

CFD of oil–water and gas–liquid two-phase flow in ESPs (VOF, emulsification)

Qin Shengjie（Master's student）

Hydraulic design and automated CFD optimization of wide-range offshore ESP impellers and diffusers

Yu Quan（Master's student）

Minute-scale production-data diagnosis of abnormal conditions in shale-gas wells

Li Xiaoqian（Master's student）

OLGA simulation of intermittent production and liquid unloading in tight-gas wells

Zhuo Jinyang（Master's student）

CFD of gas–liquid two-phase flow in ESPs

Zhang Zhenyu（Master's student）

CO₂ long-distance pipeline transport modeling

Co-supervised with Prof. Jianli Wang (Southeast University)

Zhang Yuhan（Master's student）

Data-driven modeling, equipment condition monitoring and intelligent decision-making for complex industrial systems

Shi Chenghao（Master's student）

Product UX and 3D modeling; applied machine learning and reinforcement learning

Li Xinyi（Master's student）

Cross-scale system design and practical industrial design

Alumni

2026 Feng Long (SPIC Guodian Nuclear), Zhou Hang (Chuanqing Drilling), Liu Yujun (Nanjing High Speed Gear), Gao Xiaochen* (Geely Auto), Yang Jie* (Shenzhen Xinkailai)
2025 Jia Yujiang (Xinjiang Oilfield), Gao Xue (Qingdao Sailun), Zhang Xiaocheng (PipeChina Gansu), Li Aodong (PetroChina Engineering Technology Research Institute), Xie Jialiang* (CETC), Ma Saifei* (Geely Auto)
2024 Xie Yukun* (Jiangnan Shipyard), Zhong Zikang* (destination to be confirmed)
2023 Chen Shuo (AVIC Institute of Aeronautical Materials)
2022 Jia Hao (CNNC Mining), Li Yuanyuan (Jingwei Hirain)

* Co-supervised with Prof. Jianli Wang, Southeast University

Wellbore Multiphase Flow Modeling and Liquid-Loading Prediction

Fri, 09 Oct 2026 00:00:00 +0000

Research / Area 1

Gas–liquid flow from the bottom hole to the surface passes through vertical, deviated and horizontal sections, with stratified, slug, churn and annular patterns whose pressure-drop and holdup behavior differ widely. Wellbore multiphase flow models are the common basis for artificial-lift design, liquid-loading diagnosis and production optimization; the group develops both steady-state and transient models.

Transient three-phase flow model compared with OLGA

Unified multiphase model: slug-unit control volume and flow-pattern boundary verification

Steady state. A unified model built on the slug-unit control volume covers all inclinations and oil–gas–water three-phase flow, with improved closure relations for interfacial friction, emulsion rheology, slug holdup and translational velocity. It serves as the wellbore backbone of the plunger-lift, ESP and jet-pump models.

Transient and PINN. A transient drift-flux model for horizontal gas wells is benchmarked against OLGA, and physics-informed neural networks (PI-DeepONet, time-block XPINN) are used for fast computation. Liquid-loading onset is predicted with clustering and convolutional neural networks.

Representative papers

Q Wang, H Zou, C Liang, S Zhang, H Jia, J Zhu. A combined approach for predicting liquid loading onset via clustering and convolutional neural networks. The Canadian Journal of Chemical Engineering, 2026.
J Yang, M Chen, H Wang, R Zheng, Z Li, H Zhou, J Zhu. Fast Calculation Method of Two-Phase Flow in Horizontal Gas Wells Based on PI-DeepONet. Processes 13 (10), 3363, 2025.
H Zhu, Y Liu, D Tychus, D Zheng, SP Adiraju, TS Tatu, J Zhu, HQ Zhang. Sensitivity analysis on tailpipe design for mitigating terrain slug in horizontal wells. Geoenergy Science and Engineering 235, 212598, 2024.
Z Wang, W Fu, H Li, J Zhu. Multiphase flow behavior in the deep-stratum and deep-water wellbores. Frontiers Media SA, 2023.
H Wang, J Du, J Chen, G Cao, N Li, J Zhu, M Jia, X Yang. A New Method to Calculate Loading Liquid Water of Gas Wells in Qinghai Oilfield. International Petroleum Technology Conference, D032S052R001, 2023.
H Jia, J Zhu, G Cao, Y Lu, B Lu, H Zhu. A model ranking approach for liquid loading onset predictions. SPE Production & Operations 37 (03), 370-382, 2022.
SY Nahri, Y Chen, W Williams, O Santos, L Thibodeaux, J Zhu. Understanding the Phenomenon of Dissolved Gas Migration of Gas in Riser During Drilling Operations. International Conference on Offshore Mechanics and Arctic Engineering 58875 …, 2019.