公开(公告)号：US20190330980A1

公开(公告)日：2019-10-31

申请号：US16475138

申请日：2018-09-06

Applicant: University of Science and Technology Beijing

Inventor： Weiyao ZHU ,  Ming YUE ,  Dongxu MA ,  Ziheng ZHOU ,  Hongyan HAN ,  Zhiyong SONG ,  Wenchao LIU

IPC: E21B49/00 ,  G01N15/08

Abstract: A device and a method for evaluating a gas-water two-phase flow fracture conductivity of a fractured shale. The device includes a seepage system, an injection system, a data collecting and processing system and a three-axis shale core holder, wherein the seepage system is subjected to two stages including a water injection stage and a gas flooding stage. When using the device, firstly the initial permeability and initial mass of the shale sample are determined; the water influx test is performed by injecting water to the shale sample until flow rate of the water discharged from the shale core is stable, then the water injection is ended. After the drying device is installed, the shale sample is subjected to gas flooding, and the aqueous fracturing fluid discharged by the gas flooding is collected until the flow meter determines that the gas volume is stable, and then the gas flooding is ended.

公开(公告)号：US20230358123A1

公开(公告)日：2023-11-09

申请号：US18143660

申请日：2023-05-05

Applicant: University of Science and Technology Beijing ,  Beijing Zhongke Zhishang Technology Co., Ltd.

Inventor： Hongqing SONG ,  Shuyi DU ,  Liying SONG ,  Jiulong WANG ,  Ming YUE

IPC: E21B43/16 ,  E21B43/25

CPC classification number: E21B43/168 ,  E21B43/255

Abstract: The present disclosure provides a reinforcement learning-based decision optimization method of an oilfield production system, including: collecting dynamic production data of an oilfield production site to establish a data cube for reservoir production optimization; training a preset machine learning model based on the data cube to obtain a reinforcement learning-based reservoir injection-production system surrogate model configured to predict oil production according to the dynamic production data available on site; constructing an evaluation function for production optimization of a gas injection reservoir; establishing, during a process of production optimization, an enforced constraint model based on input parameters and a boundary constraint condition; and with the constraint model and the boundary constraint condition as constraints, the reservoir injection-production system surrogate model as a basis, and the evaluation function as an optimization direction, searching reservoir production optimization schemes for an optimal production scheme.

公开(公告)号：US20210003005A1

公开(公告)日：2021-01-07

申请号：US16620657

申请日：2018-09-21

Applicant: University of Science and Technology Beijing

Inventor： Weiyao ZHU ,  Zhiyong SONG ,  Ming YUE ,  Yunfeng LIU ,  Zhen CHEN ,  Dongxu MA ,  Wenchao LIU ,  Qian Qi

IPC: E21B49/02 ,  G01V99/00 ,  G01N3/08

Abstract: A method for identifying a medium structure coupling and a fracture network morphology of a shale gas reservoir includes the following steps. Firstly, performing a fracturing test on shale cores by using a modified Brazilian disc test and categorizing the fracture network morphology. Secondly, performing a shale matrix-fracture structure and stress sensitivity test on the shale cores having different fracture network morphology. After that, determining a stress sensitivity constant of different fracture network morphology according to indoor core data and finally preparing an identification chart of the fracture network morphology based on an indoor core stress sensitivity text combined with a production practice. The identification chart can be applied to an actual fracturing well, and the fracture network morphology is directly identified by a real-time effective stress and a normalized flow.