Layered water injection optimization method based on long short-term memory neural network and particle swarm optimization algorithm

A long-term memory, particle swarm optimization technology, applied in biological neural network model, neural architecture, design optimization/simulation and other directions, can solve the problem of not considering the impact of historical time series data, achieve short calculation time, simple on-site operation, Reliable results

Pending Publication Date: 2022-04-15
CHINA FRANCE BOHAI GEOSERVICES
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

BP neural network is widely used in production forecasting, but does not consider the influence of historical time series data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Layered water injection optimization method based on long short-term memory neural network and particle swarm optimization algorithm
  • Layered water injection optimization method based on long short-term memory neural network and particle swarm optimization algorithm
  • Layered water injection optimization method based on long short-term memory neural network and particle swarm optimization algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0075] A hierarchical water injection optimization method based on long short-term memory neural network and particle swarm optimization algorithm:

[0076] like figure 1 , 2 shown in figure 2 in, x t is the input state; h t-1 is the short-term hidden state; c t-1 is the long-term hidden state; y t is the output state; c t is the long-term hidden state at update time t; h t is the short-term hidden state at update time t; f t i t , o t Determined by the activation function σ, respectively control the parameters of the forget gate, input gate and output gate; g t It is determined by the nonlinear activation function f, and i t Control the parameters of the input gate together; f is the nonlinear activation function; σ is the activation function; FC is the fully connected layer;

[0077] Step 1. Determine the data set and divide the data set into a training set and a test set. The specific method is as follows:

[0078] S1.1: Identify the dataset

[0079] Determin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a layered water injection optimization method based on a long short-term memory neural network and a particle swarm optimization algorithm. The method comprises the following steps: determining a data set and dividing the data set into a training set and a test set; the importance degree of contribution of each water injection layer section to the oil well liquid production capacity is analyzed through an MDI method, and main water injection layer sections affecting the oil well liquid production capacity are screened out; after main water injection layer sections influencing the oil well liquid production capacity are screened out, the water injection rate of each water injection layer section is subjected to normalization processing; an LSTM model is built, trained and verified, and the LSTM model of the oil well is obtained through training; and optimizing the layered water injection rate of each water injection well by adopting a PSO algorithm. According to the method, the long-short-term memory neural network and the particle swarm optimization algorithm are utilized to overcome the defects of a traditional separated layer water injection optimization method based on reservoir numerical simulation.

Description

technical field [0001] The invention belongs to the technical field of oil and gas exploitation, and in particular relates to a layered water injection optimization method based on a long-short-term memory neural network and a particle swarm optimization algorithm. Background technique [0002] At present, most oilfields in my country have entered the middle and late stages of development, with rising water cut and declining development benefits. In the process of oilfield production, layered water injection is an important means to improve the contradiction between injection and production between layers and improve the effect of water flooding development. The research on optimization of layered water injection is of great significance to maintain high-efficiency water control and oil-increasing development of oilfields. [0003] The layered water injection optimization based on reservoir numerical simulation has the disadvantages of strong uncertainty of geological model, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06K9/62G06N3/00G06N3/04G06F111/10
Inventor 赵洪绪于伟强毛敏杨毅赵洪涛房鑫磊
Owner CHINA FRANCE BOHAI GEOSERVICES
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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