A method for quantitatively evaluating polymer oil displacement wall based on picture recognition
By using a fluorescent tracer-visualized sand-filled pipe system and a convolutional neural network model that fuses multimodal data, combined with physical mechanism constraints, the accuracy and efficiency issues of oil wall development scale evaluation were solved, enabling intelligent feedback and decision support for reservoir development and improving oil recovery.
CN122265774APending Publication Date: 2026-06-23CHINA PETROLEUM & CHEMICAL CORP +1
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN Β· China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA PETROLEUM & CHEMICAL CORP
- Filing Date
- 2024-12-20
- Publication Date
- 2026-06-23
Smart Images
Figure CN122265774A_ABST
Abstract
The application discloses a kind of polymer oil displacement wall quantitative evaluation methods based on picture identification, comprising the following steps: S1 fluorescent tracer visual sand filling pipe system organization;S2 polymer oil displacement wall multi-modal data fusion;S3 automatic evaluation based on physical mechanism constraint;S4 intelligent feedback and decision support, the application is applicable to oilfield development technical field, through fluorescent tracer visual two-dimensional sand filling system, polymer oil displacement wall multi-modal data fusion, automatic evaluation based on physical mechanism constraint and intelligent feedback and decision support four processes, the precise, comprehensive analysis of oil wall development characteristics in polymer flooding process is realized.The system can monitor the thickness, distribution and front advance speed of oil wall in real time, automatically process complex multi-source data, and ensure that the evaluation results meet the physical mechanism.
Need to check novelty before this filing date? Find Prior Art