Supercharge Your Innovation With Domain-Expert AI Agents!

Nuclear reactor power and axial power distribution reinforcement learning decoupling control method

A technology of axial power distribution and reinforcement learning, which is applied in the control of nuclear reactions, reactors, nuclear engineering, etc., can solve the problems of weakening the control ability of axial power distribution of the core and reducing the safe operation margin of the reactor, so as to achieve strong robustness Sex and generalization ability, less time-consuming training, good decoupling effect

Pending Publication Date: 2022-08-09
XI AN JIAOTONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this blocking design can largely alleviate the interference of the strong coupling effect of M rod group and AO rod adjustment on the stability of the control system, it also weakens the ability to control the axial power distribution of the core, and to a certain extent reduces the Reactor Safe Operating Margin

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
  • Nuclear reactor power and axial power distribution reinforcement learning decoupling control method
  • Nuclear reactor power and axial power distribution reinforcement learning decoupling control method
  • Nuclear reactor power and axial power distribution reinforcement learning decoupling control method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0055] In the description of the present invention, it is to be understood that the terms "comprising" and "comprising" indicate the presence of the described features, integers, steps, operations, elements and / or components, but do not exclude one or more other features, The existence or addition of a whole, step, operation, element, component, and / or a collection thereof.

[0056] It should also be understood that the terminology used in t...

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 nuclear reactor power and axial power distribution reinforcement learning decoupling control method. A reinforcement learning technology is utilized to eliminate a coupling effect between a reactor core coolant average temperature control subsystem and an axial power offset control subsystem in a pressurized water reactor mechanical compensation operation mode; two independent reinforcement learning feed-forward compensation modules are respectively used for compensating the rod speeds of the M rod group and the AO rod given by the reactor core coolant average temperature control subsystem and the axial power offset control subsystem, and the coupling effect of the M rod group and the AO rod in the process of adjusting the distribution of the reactor core power and the axial power is eliminated. According to the invention, decoupling control of reactor core power and axial power distribution in a pressurized water reactor mechanical compensation operation mode can be realized.

Description

technical field [0001] The invention belongs to the technical field of nuclear reactor control, and in particular relates to a nuclear reactor power and axial power distribution reinforcement learning decoupling control method. Background technique [0002] The pressurized water reactor is the mainstream reactor type in the active nuclear power plants in the world today. The operating PWR basically adopts the traditional operation control mode (A mode or G mode) based on chemical compensation. During the load tracking process, the operator needs to adjust the core boron concentration frequently, and the reactivity adjustment speed is very slow. , the output of waste liquid is large, which affects the economy, safety and ecological benefits of the nuclear power plant; and, at the end of the service life, when the fuel consumption is high and the boron concentration is very low, the power improvement capability of the reactor is very weak, and the output of boron waste liquid ...

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): G06F30/27G21C7/36G06F119/02
CPCG06F30/27G21C7/36G06F2119/02Y02E30/30
Inventor 王鹏飞龚辉俊梁文龙万甲双吴世发
Owner XI AN JIAOTONG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More