China University of Petroleum

Qingdao University of Technology

Xia Yan

Kai Zhang

Jun Yao

Yongfei Yang

Hai Sun

Lei Zhang

Lei Liu

Zifeng Sun

Dongyan Fan

Feng Jia

Liang Zhou

Qian Sang

Huaqing Zhang

Fei Luo

Liming Zhang

Yuda Kan

Zhongzheng Wang

Piyang Liu

Guojing Xin

A differentiated real-time injection-production optimization adjustment method of an intelligent injection-production linkage device belongs to the field of oil reservoir injection-production technologies. The method includes: initializing networks; building an injection-production environment model; by an agent, reading an initial state of an injection-production environment; writing a file by an injection-production policy network; obtaining state data of the moment t+1; reading a next state and an economic net present value within the time step; assigning the next state to the current state until a to-be-optimized production period is completed; by batch training on the model, updating a parameter of the environment agent model; updating a parameter of the action evaluation network and a parameter of the injection-production policy network; repeating the above steps until an optimal model is obtained; based on the stored optimal model, linking the intelligent injection-production device to obtain state information of the oil reservoir.

Differentiated real-time injection-production optimization adjustment method of intelligent injection-production linkage device

Disclosed a method for predicting permeability of a multi-mineral phase digital core based on deep learning. In the present disclosure, a three-dimensional digital core is constructed and a pore structure is randomly generated; after a plurality of multi-mineral digital core images is acquired by performing image segmentation on the three-dimensional digital core, permeability corresponding to each of the multi-mineral digital core images is acquired by simulation using multi-physics field simulation software and a multi-mineral digital core data set is constructed based on the plurality of multi-mineral digital core images and the permeability corresponding to each of the multi-mineral digital core images; an SE-ResNet18 convolutional neural network is constructed and trained with the multi-mineral digital core data set; and an image of a multi-mineral core to be predicted is input into the trained SE-ResNet18 convolutional neural network to determine the permeability of the multi-mineral core.

Method for predicting permeability of multi-mineral phase digital core based on deep learning

Growing community of inventors

Qingdao, China

Xia Yan