Supercharge Your Innovation With Domain-Expert AI Agents!

Centrifugal compressor regulation and control method based on deep reinforcement learning algorithm

A centrifugal compressor, reinforcement learning technology, used in general control systems, control/regulation systems, instruments, etc.

Active Publication Date: 2021-05-18
XI AN JIAOTONG UNIV
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the successful application of the A3C algorithm in industrial control and other related fields, the A3C deep reinforcement learning algorithm has become a feasible solution to realize the intelligent control of compressors, and no relevant literature has been published yet.

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
  • Centrifugal compressor regulation and control method based on deep reinforcement learning algorithm
  • Centrifugal compressor regulation and control method based on deep reinforcement learning algorithm
  • Centrifugal compressor regulation and control method based on deep reinforcement learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0055] refer to figure 1 , a centrifugal compressor control method based on a deep reinforcement learning algorithm, including the following steps:

[0056] Step 1) According to the present embodiment figure 1 Process design centrifugal compressor system control method such as figure 2 As shown, the centrifugal compressor system is modeled through the Simulink simulation model, and the selected Simulink simulation model is as follows image 3 As shown, the present embodiment adopts the Greitzer model of the centrifugal compressor, which consists of four subsystems: the air cavity mass conservation subsystem, the compressor momentum conservation subsystem, the throttle valve dynamic characteristic subsystem, and the approximate steady-state compressor characteristic subsystem Composition; Wherein, the compressor valve coefficient is 7.375, ...

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

A centrifugal compressor regulation and control method based on a deep reinforcement learning algorithm aims at the multi-target and multi-parameter control optimization problem of a centrifugal compressor and comprises the steps of: firstly, designing a controller for an opening degree of an inlet valve; then setting an A3C algorithm to calculate the number of workers in parallel, setting an updating interval, establishing an evaluation index according to control requirements of shortening adjustment time and reducing overshoot, designing an A3C algorithm reward function by using the evaluation index, determining A3C algorithm action parameters according to a control compensation link, and determining an algorithm iteration termination condition; and operating an A3C algorithm, and determining an optimal compensation parameter. The centrifugal compressor regulation and control method improves system operation efficiency, ensures a system pressure ratio, and optimizes system safety.

Description

technical field [0001] The invention belongs to the technical field of centrifugal compressor control, and in particular relates to a centrifugal compressor control method based on a deep reinforcement learning algorithm. Background technique [0002] As a representative of large-scale industrial-grade systems, compressors are key equipment in chemical industries such as various large-scale chemical plants and oil refineries, and occupy a very important position in the national economy, especially the entire heavy industry system. With the continuous and in-depth development of fluid machinery and control theory, the compressor industry has developed rapidly and is widely used in various industries such as aerospace and large chemical industries. In this process, due to the advantages of high power density and high efficiency, centrifugal compressors have been widely used. Due to the strong coupling characteristics of the control parameters, the operation performance of the...

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): G05B17/02
CPCG05B17/02
Inventor 张庆魏晓晗蒋婷婷
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

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com