Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Self-optimization decision control system of electric submersible pump

A technology of control system and electric submersible pump, applied in the direction of general control system, control/regulation system, adaptive control, etc., can solve the changeable and complex submersible electric pump that does not consider the environmental problems of injection and production The basic needs of intelligent control and other issues

Active Publication Date: 2021-06-01
CHINA UNIV OF PETROLEUM (BEIJING) +1
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the submersible electric pump intelligent control system provided by this patent document does not take into account the changeable and complex environmental problems of injection and production. The established control model or c

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
  • Self-optimization decision control system of electric submersible pump
  • Self-optimization decision control system of electric submersible pump
  • Self-optimization decision control system of electric submersible pump

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] This embodiment provides a self-optimizing decision-making control system for electric submersible pumps, including an acquisition module 100 , a control module 200 , and an execution module 300 . Preferably, a collection module 100 for interacting with the environment is arranged in the injection-production wellbore. The acquisition module 100 is arranged downhole. The collection module 100 is capable of collecting environmental states. The environment is the entire drainage system including the reservoir. Environmental status includes reservoir information and drainage system information. For example, downhole flow rate, temperature, pressure, water content, liquid level height, liquid volume, electrical parameters and the diameter of the wellhead nozzle 402 for drainage by the electric submersible pump 400 . The electrical parameters include the parameters of the submersible motor 401, such as the frequency, voltage, and power consumption of the motor. Preferably...

Embodiment 2

[0091] This embodiment is a further improvement / supplement to Embodiment 1, and repeated content will not be repeated.

[0092] In Example 1, reinforcement learning is used for learning training and optimization decision-making, but the optimization decision in Example 1 is based on the fact that the state space S and action space A are discrete and the data dimension is small, which can achieve better convergence. However, the decision variable of the present invention, that is, the action space A is not a column vector, and not only the frequency of the submersible motor 401 but also the valve opening of the wellhead nozzle 402 are considered. Moreover, in actual situations, the number n of single wells may be large. In this case, it is unrealistic to store a large number of states and values ​​corresponding to actions in the value table in reinforcement learning. Therefore, this embodiment combines deep learning on the basis of Embodiment 1 to solve the problem that the sta...

Embodiment 3

[0100] This embodiment is a further improvement / supplement to Embodiments 1 and 2 and their combination, and the repeated content will not be repeated.

[0101] The start-stop times, the first time and the second time in the thinning system in Embodiments 1 and 2 are fixed. Although production with this constant interval pumping system facilitates field management in the oilfield, the natural energy of the downhole formation of each single well is different, and the rate of rise and fall of the dynamic fluid level in the annulus is also different. Therefore, fixed first and second times do not apply to all single wells. Moreover, in the actual production process, the natural energy of the reservoir decreases continuously with the increase of the production time, and the corresponding thinning system should change dynamically.

[0102] On the other hand, if the number of starts and stops, the first time and the second time change dynamically, this makes the optimization decisi...

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 relates to a self-optimization decision control system of an electric submersible pump. The system at least comprises an acquisition module and a control module, and the control module generates an optimization decision executed by the electric submersible pump through a reinforcement learning algorithm based on environmental information acquired by the acquisition module so as to realize self-optimization. The control module is configured to construct a loss function in a reinforcement learning algorithm in a mode of fusing online learning and offline learning on the basis of dividing the start-stop times, the well opening time and the well closing time of each single well in a pump inspection period based on the state space. Through the setting mode, optimization control of the control module on the execution module is divided into different stages based on the start-stop times, the well opening time, the well closing time and the like, and the loss function in learning updating is constructed based on the mode of fusing online learning and offline learning according to the different stages.

Description

technical field [0001] The invention relates to the technical field of oil exploitation, in particular to a self-optimization decision-making control system of a submersible electric pump. Background technique [0002] The electric submersible pump is a multi-stage centrifugal pump that works downhole and is lowered into the well together with the tubing. The surface power supply is transmitted to the underground submersible motor through transformers, power cables, etc., so that the submersible motor drives the multi-stage centrifugal pump to rotate, converts electrical energy into mechanical energy, and lifts the well fluid in the oil well to the surface. Compared with the oil production method of the beam pumping unit, the submersible electric pump has low investment cost, low energy consumption, and better adaptability to the medium. Compared with the previous oil production method, not only the economic cost is low, but also the failure rate is lower. lower. However, ...

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
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 檀朝东赵小雨邓涵文冯钢宋健牛会钊宋文容
Owner CHINA UNIV OF PETROLEUM (BEIJING)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com