Related Experiment Video
Updated: Aug 5, 2026
14:33
Optimize Flue Gas Settings to Promote Microalgae Growth in Photobioreactors via Computer Simulations
Published on: October 1, 2013
14.4K
Performance Prediction and Heating Parameter Optimization of Organic-Rich Shale In Situ Conversion Based on Numerical
Yaqian Liu1,2,3, Chuanjin Yao1,2,3, Baishuo Liu1,2,3
1National Key Laboratory of Deep Oil and Gas, China University of Petroleum (East China), Qingdao, Shandong 266580, China.
ACS Omega
|April 8, 2024
Summary
This study introduces a rapid prediction framework for shale in situ conversion using artificial neural networks and particle swarm optimization. It optimizes heating parameters for efficient hydrocarbon production, identifying key factors influencing reservoir performance.
Area of Science:
- Petroleum Engineering
- Geochemistry
- Computational Science
Background:
- In situ conversion technology offers a sustainable method for developing organic-rich shale resources.
- Supercritical CO2 (Sc-CO2) is an effective heating medium for shale in situ conversion.
- Numerical simulations for in situ conversion are computationally intensive, limiting parameter optimization.
Purpose of the Study:
- To develop a computational framework for rapid prediction of shale in situ conversion performance.
- To optimize heating parameters for enhanced hydrocarbon recovery.
- To identify key factors influencing reservoir temperature and hydrocarbon production.
Main Methods:
- Coupling artificial neural networks (ANN) with particle swarm optimization (PSO) for prediction and optimization.
- Constructing a simulation database from numerous in situ conversion experiments.
- Utilizing Pearson correlation analysis and random forest methods to identify controlling factors.
Main Results:
- Kerogen pyrolysis and hydrocarbon release primarily occur within the first two years of conversion.
- ANN models achieved a determination coefficient >97% and MSE <0.3% for prediction.
- Optimal Sc-CO2 injection parameters (350-450°C, 600 m³/day) were determined for a basic reservoir case.
Conclusions:
- The ANN-PSO framework enables accurate prediction and rapid optimization of shale in situ conversion.
- This approach facilitates effective design and development of shale oil resources.
- Understanding key controlling factors is crucial for maximizing hydrocarbon production.
