K
Kai Zhang
Researcher at China University of Petroleum
Publications - 414
Citations - 6148
Kai Zhang is an academic researcher from China University of Petroleum. The author has contributed to research in topics: Computer science & Geology. The author has an hindex of 31, co-authored 303 publications receiving 3787 citations. Previous affiliations of Kai Zhang include Wuhan University of Science and Technology & Shandong University.
Papers
More filters
Journal ArticleDOI
An efficient infill well placement optimization approach for extra-low permeability reservoir
Qinyang Dai,Liming Zhang,Kai Zhang,Guodong Chen,Xiaopeng Ma,Jian Wang,Huaqing Zhang,Xi Yan,Piyang Liu,Yongmei Yang +9 more
TL;DR: This paper proposes an infill well optimization strategy based on the divide-and-conquer principle that divides the large-scale realistic reservoir model into several types of small-scale conceptual models using human knowledge and then uses the surrogate-assisted evolutionary algorithm to obtain theinfill well laws for this reservoir.
Journal ArticleDOI
Waterflooding Interwell Connectivity Characterization and Productivity Forecast with Physical Knowledge Fusion and Model Structure Transfer
Yu-chun Jiang,Huaqing Zhang,Kai Zhang,Jian Wang,Jianfa Han,Shi-Ming Cui,Liming Zhang,Hanjun Zhao,Piyang Liu,Honglin Song +9 more
TL;DR: Zhang et al. as discussed by the authors proposed a physical knowledge fusion neural network (PKFNN) to inherit the knowledge learned from different injector-producer pairs, fully improving the training efficiency.
Journal ArticleDOI
Digital Rock Mechanical Properties by Simulation of True Triaxial Test: Impact of Microscale Factors
W.-L. Ma,Yongmei Yang,Wendong Yang,Changran Lv,Jiangshan Yang,Wenhui Song,Hai Sun,Lei Zhang,Kai Zhang,Jun Yao +9 more
TL;DR: In this article , the effects of microscale factors are critical in mechanical properties such as rock strength, elastic modulus, and stress-strain state under the triaxial stress state.
Proceedings ArticleDOI
Deep Conditional Generative Adversarial Network for History Matching with Complex Geologies
TL;DR: In this paper, a deep conditional generative adversarial network (CGAN) method was proposed for automatic reservoir history matching for the first time, where the mapping relationship between static geological reservoir parameters and dynamic production data is found through the training generative network, which reduces the uncertainty of the reservoir model obtained by automatic history matching and explains parallel offline processing.