Pumping well multi-well working fluid level depth prediction method based on dynamic and static information feature fusion neural network
A feature fusion and neural network technology, applied in the field of soft measurement, can solve problems such as abnormal data in data sets, and achieve the effect of improving model accuracy and increasing robustness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0055] like figure 1 In the present invention, the drawing of the oil-based well multi-well fluid surface prediction method based on dynamic static information feature fusion neural network, including the following steps:
[0056] Step 1: Some ports are collected in the historical data; including the well number, stroke start time, stroke end time, suspension point displacement, hoping load, stroke, row, yield, water content, moving surface depth, Hydraulic, set pressure, pump diameter, pump deep, pumping, formation crude oil density, ground crude oil density, gas oil ratio, saturated pressure, dissolution coefficient, penetrating rod length, range rod diameter, various type oil pipes Long and range of oil pipes parameters;
[0057] Step 2: Mechanism analysis of the rod pump pumping oil surface, resulting in a factor in the deep correlation with the lower moving liquid surface, including the function map parameters, water content, hydraulic pressure, rocker, formation crude oil de...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap