肖聪

  • 所在单位:
    石油工程学院/油气田开发工程系
  • 所在学科:
    石油与天然气工程
  • 个人学位:
    博士
  • 职称名称:
    副教授
  • 教师类别:
    专任教师
  • 导师类型:
    博士生导师,硕士生导师
  • 招生专业:
    石油与天然气工程,人工智能
  • 电子邮箱:
    xclmjtud@yahoo.com
  • 联系方式:
    18706219348

教育经历

  • 2016-09至2020-09, 荷兰代尔夫特理工大学, 应用数学, 博士研究生
  • 2013-09至2016-06, 中国石油大学(北京), 油气田开发工程, 硕士研究生
  • 2009-09至2013-06, 长江大学, 石油工程, 大学本科

个人概况

姓名:肖聪  
电子邮箱:xclmjtud@yahoo.com  
联系电话:18706219348  
 
申请人教育与工作经历:  
2009.9 - 2013.6  长江大学石油工程系,石油工程,学士  
2013.9 - 2016.6  中国石油大学(北京)石油工程系,油气田开发工程,硕士  
2016.9 - 2021.1  荷兰代尔夫特理工大学应用数学系,应用数学,博士  
2021.4 - 至今  中国石油大学(北京),教师,校青年拔尖人才引进。  
 
研究方向:  
油田大数据分析方法研究;  
基于深度学习和代理模型的智能反演算法研究;  
智慧油藏闭环管理理论与方法(自动历史拟合和生产制度优化);  
智能压裂理论与方法  
 
近年来主要从事油田大数据,数据同化及其在油田智能决策方面的研究。博士课题《基于机器学习代理模型的油藏历史拟合研究》旨在油气田开发和储层管理的数字&智能化工作流程。系统建立了多种结合模型降维,传统机器学习模型,以及基于卷积神经网络的深度学习框架的石油替代模型和油藏参数反演优化算法。目前加入中国石油大学(北京)储层增产改造实验室,开展基于大数据挖掘与人工智能技术的非常规油气藏智能压裂设计优化,裂缝参数反演及产能预测研究工作。  
 
代表性论文:  
[1]Xiao, C., Lin, H.X, Leeuwenburgh, O., Heemink, A. Surrogate-assisted inversion for large-scale history matching: Comparative study between projection-based reduced-order modeling and deep neural network[J]. Journal of Petroleum Science and Engineering, 2022.  
 
[2] Xiao, C., Leeuwenburgh, O , Heemink, A., Lin, H.X. Conditioning of Deep-Learning Surrogate Models to Image Data with Application to Reservoir Characterization[J]. Knowledge-Based Systems, 2021, 3.  
 
[3] Xiao C , Deng Y, Wang GD . Deep-Learning-Based Adjoint State Method: Methodology and Preliminary Application to Inverse Modeling[J]. Water Resources Research, 2021, 2.  
 
[4] Xiao, C., Leeuwenburgh, O ,Heemink, A., Lin, H.X. Efficient estimation of space varying parameters in numerical models using non-intrusive subdomain reduced order modeling[J]. Journal of Computational Physics, 2020, 424.  
 
[5] Xiao C , Tian L . Surrogate‐Based Joint Estimation of Subsurface Geological and Relative Permeability Parameters for High‐Dimensional Inverse Problem by Use of Smooth Local Parameterization[J]. Water Resources Research, 2020, 56(7).  
 
[6] Xiao C , Tian L . Modelling of fractured horizontal wells with complex fracture network in natural gas hydrate reservoirs[J]. International Journal of Hydrogen Energy, 2020, 45( 28):14266-14280.  
 
[7] Xiao C , Tian L , Zhang L , et al. Distributed Gauss-Newton Optimization with Smooth Local Parameterization for Large-Scale History-Matching Problems[J]. SPE Journal, 2020, 25(1):056-080.  
 
[8] Xiao C , Zhan M B , Leng T C . Semi-analytical modeling of productivity analysis for five-spot well pattern scheme in methane hydrocarbon reservoirs[J]. International Journal of Hydrogen Energy, 2019, 44( 49):26955-26969.  
 
[9] Xiao, C., Leeuwenburgh, O ,Heemink, A., Lin, H.X. Non-intrusive Subdomain POD-TPWL Algorithm for Reservoir History Matching[J]. Computational Geosciences, 2018, 23(6).  
 
[10] Xiao C , Dai Y , Tian L , et al. A Semi-analytical Methodology for Pressure-Transient Analysis of Multi-well-Pad-Production Scheme in Shale Gas Reservoirs, Part 1: New Insights Into Flow Regimes and Multi-well Interference[J]. SPE Journal, 2018.  
 
[11] Xiao C , Tian L , Zhang Y , et al. A Novel Approach To Detect Interacting Behavior Between Hydraulic Fracture and Natural Fracture Using Semi-analytical Pressure-Transient Model[J]. SPE Journal, 2017.  
 
[12] Xiao C , Tian L , et al. Comprehensive application of semi-analytical PTA and RTA to quantitatively determine abandonment pressure for CO2 storage in depleted shale gas reservoirs[J]. Journal of Petroleum Science and Engineering, 2016.  
 
会议报告:  
[1] 肖聪,张士诚,马新仿等。基于深度学习代理模型的油藏自动历史拟合算法研究,第七届数字油田国际学术会议,2021年11月3日-5日。  
 
[2] Xiao, C., et al, O., Projection-based autoregressive neural network for model-reduced adjoint-based variational data assimilation, Presented at The 82nd EAGE Annual Conference & Exhibition. Netherlands, 18 - 23, October, 2021.  
 
[3] Xiao, C., et al, O., Deep Learning Surrogate-Assisted Assimilation of Image-type Data, Presented at International EnKF Workshop. Norway, 11 - 15, June, 2021.  
 
[4] Xiao, C., Heemink, A., Lin, H.X. and Leeuwenburgh, O., Efficient Deep-Learning Inversion for Big-Data Assimilation: Application to Seismic History Matching, Presented at ECMOR XVII, Edinburgh, United Kingdom, 14-17 September, 2020.  
 
[5] Xiao, C., Heemink, A., Lin, H.X. and Leeuwenburgh, O., Subdomain Reduced-Order Modelling with Smooth Local Parameterization for Large-Scale Inversion Problem, Presented at ENUMATH 2019 conference, The Netherlands, 30 September - 4 October, 2019.  
 
[6] Xiao, C., Heemink, A., Lin, H.X. and Leeuwenburgh, O., A machine-learning Based Subdomain POD-TPWL for Large-Scale Inversion Problems, Presented at InterPore2019, Valencia, Spain, 6 -10 May, 2019.  
 
[7] Xiao, C., Heemink, A., Lin, H.X. and Leeuwenburgh, O., Subdomain Adjoint-Based Variational Data Assimilation for Reservoir History Matching, Presented at 13th International EnKF Workshop. Bergen, Norway, 28 - 30, May, 2018.  
 
 
专著和译著:  
《Surrogate-Assisted Reservoir History Matching》,Delft University of Technology, 2021. ISBN:978-94-6366-365-6.  
 
目前承担或参与科研项目如下:  

(1)《页岩油平台井闷井压力干扰响应机理与智能诊断方法研究》,国家自然科学基金青年科学基金项目,2024-2026,主研。  

(2)《基于机器学习和智能算法的体积压裂缝网-井网自动优化技术研究》,页岩油气富集机理与有效开发国家重点实验室开发基金,2021,主研。  
(3)《基于深度学习的页岩压裂缝网智能反演与产能预测一体化研究》,中国石油大学(北京)青年拔尖人才引进启动项目,2021-2024年,主研。  
(4)《玛湖砾岩油藏水平井段内多簇射孔分段压裂关键技术攻关》,2021年,参与。  
(5)《顺北超深断溶体油藏高效酸压技术研究-顺北酸压改造低效井原因分析及地质工程一体化对策论证》,2021年,参与。  
(6)《页岩油气藏水平井分段分簇压裂与组合粒径支撑剂运移模拟技术》,2021年,参与。  
 
主要学术团体兼职:  
Journal of Petroleum Science and Engineering, Journal of Natural Gas Science and Engineerin, SPE Journal以及Water Resource Research等国际权威期刊审稿人。