A5100461484- Reservoir Engineering and Simulation Methods
- Hydraulic Fracturing and Reservoir Analysis
- Drilling and Well Engineering
- Oil and Gas Production Techniques
- Enhanced Oil Recovery Techniques
- Metaheuristic Optimization Algorithms Research
- Groundwater flow and contamination studies
- Advanced Multi-Objective Optimization Algorithms
- Water resources management and optimization
- Innovations in Concrete and Construction Materials
- Geophysical Methods and Applications
- Advanced Manufacturing and Logistics Optimization
- Advanced Data Processing Techniques
- Remote-Sensing Image Classification
- Mineral Processing and Grinding
- Modular Robots and Swarm Intelligence
- Advanced Image Fusion Techniques
- Seismic Imaging and Inversion Techniques
- Remote Sensing and Land Use
- Hydrocarbon exploration and reservoir analysis
- Hydraulic and Pneumatic Systems
- Microgrid Control and Optimization
- Advanced Cellulose Research Studies
- Dam Engineering and Safety
- Constraint Satisfaction and Optimization
China University of Petroleum, East China
2014-2024
China University of Petroleum, Beijing
2017-2023
Zhongyuan University of Technology
2022
Nanjing University of Posts and Telecommunications
2020
Shandong University
2018
Fudan University
2007
Evolutionary multitasking (EMT) is a newly emerging research topic in the community of evolutionary computation, which aims to improve convergence characteristic across multiple distinct optimization tasks simultaneously by triggering knowledge transfer among them. Unfortunately, most existing EMT algorithms are only capable boosting performance for homogeneous problems explicitly share same (or similar) fitness landscapes. Seldom efforts have been devoted generalize solving heterogeneous...
Summary Surrogate models, which have become a popular approach to oil-reservoir production-optimization problems, use computationally inexpensive approximation function replace the expensive objective computed by numerical simulator. In this paper, new optimization algorithm called global and local surrogate-model-assisted differential evolution (GLSADE) is introduced for waterflooding problems. The proposed method consists of two parts: (1) differential-evolution (DE) part, in DE used...
In practical engineering optimization problems (such as risk assessments), the parameters of objective functions can be intervals because noise and uncertainty; however, such cannot solved by traditional multiobjective methods. Yet, very little study has addressed interval methods compared to Therefore, a novel method called Interval Cooperative Multiobjective Artificial Bee Colony Algorithm (ICMOABC) based on multiple populations for objectives credibility is proposed. selected dominant...
Production optimization has gained increasing attention from the smart oilfield community because it can increase economic benefits and oil recovery substantially. While existing methods could produce high-optimality results, they cannot be applied to real-time for large-scale reservoirs due high computational demands. In addition, most generally assume that reservoir model is deterministic ignore uncertainty of subsurface environment, making obtained scheme unreliable practical deployment....
Waterflooding is one of the most common reservoir development programs, driving oil in porous media to production wells by injecting high-pressure water into reservoir. In process development, identifying underground flow distribution, so as take measures such plugging and profile control for high permeability layers prevent channeling, great importance oilfield management. However, influenced heterogeneous geophysical properties media, there strong uncertainty distribution. this paper, we...
The reservoir characterization aims to provide the analysis and quantification of injection-production relationship, which is fundamental work for production management. connectivity between injectors producers dominated by geological properties, especially permeability. However, permeability parameters are very heterogenous in oil reservoirs, expensive collect well logging. commercial simulators enable get accurate simulation but require sufficient properties consume excessive computation...
Abstract The objective of infill well placement optimization is to determine the optimal locations that maximize net present value (NPV). most common method infilling in oil field based on engineer’s knowledge, which risky. Additionally, numerous techniques have been proposed address issues. However, locating global optimum a large-scale practical reservoir model computationally expensive, even more so realistic extra-low permeability reservoir, where fractures are generated and underground...
Summary During sucker rod pump production, there is a commonly seen problem of class imbalance, which refers to the differences in amount data accumulated under different working conditions. This diagnosis can lead unsatisfactory classification results surface dynamometer cards conditions with fewer samples. Therefore, this study adopts conditional generative adversarial nets (CGANs) improved by mini-batch method address imbalance. CGAN an efficient multiclass generation, learns properties...
For a long time, well pattern optimization mainly relies on human experience, numerical simulations are used to test different development plans and then preferred program is chosen for field implementation. However, this kind of method cannot provide suitable optimal layout geological reservoirs. In recent years, more attentions have been paid propose placement theories combining algorithm with reservoir simulation. But these mostly applied in situation small amount wells. numerous wells...
Hydraulic fracturing is a pivotal technology in the development of unconventional tight reservoirs, which accurate monitoring fracture parameters significant. This paper proposes an improved differential evolution algorithm (EMDE) to calculate Effective Propped Volume (EPV) accurately. The forward simulation results demonstrate that when transmitting source plane particular position, relationship between signals and specific parameter most obvious, providing basis for application inversion...