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

Aero-engine remaining service life estimation method based on deep reinforcement learning

An aero-engine and reinforcement learning technology, which is applied in neural learning methods, machine learning, computer-aided design, etc., can solve problems such as overfitting and performance defects, and achieve strong generalization and accurate estimation of remaining service life.

Pending Publication Date: 2021-02-05
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the current method has a certain risk of overfitting, which will cause certain performance defects.

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
  • Aero-engine remaining service life estimation method based on deep reinforcement learning
  • Aero-engine remaining service life estimation method based on deep reinforcement learning
  • Aero-engine remaining service life estimation method based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present embodiment adopts the status monitoring data of aero-engine sensors, which are collected by 21 sensors and mainly include: total temperature at the fan inlet, total temperature at the outlet of the low-pressure compressor, total temperature at the outlet of the high-pressure compressor, total temperature at the outlet of the low-pressure turbine, fan Inlet pressure, total pressure of external duct, total pressure of high pressure compressor outlet, fan physical speed, core machine physical speed, engine pressure ratio, high pressure compressor outlet static pressure, ratio of fuel consumption rate to high pressure compressor outlet static pressure, correction Fan speed, corrected core machine speed, outside culvert ratio, combustion chamber oil-air ratio, extraction enthalpy, rated fan speed, rated corrected fan speed, high-pressure turbine cooling air extraction volume, low-pressure turbine cooling air extraction volume.

[0046] The original sensor data set...

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 provides an aero-engine remaining service life estimation method based on deep reinforcement learning, and the method comprises the steps: taking the requirements and characteristics ofaero-engine life estimation as a sequential decision problem, and establishing a corresponding Markov decision process model; for the Markov model, formulating interaction rules such as state action rewarding and the like, designing a life estimation rewarding function, and providing a deep learning model of a life estimation strategy according to the characteristics of aero-engine life estimationdata; and finally, learning an optimal aero-engine life estimation strategy in the Markov model by using a deep reinforcement learning algorithm. According to the method, the over-fitting risk brought by a conventional supervised learning method is overcome, a better aero-engine service life estimation strategy can be obtained, the accuracy of aero-engine service life estimation can be improved,the timeliness of maintenance according to conditions is improved, the safety of aircraft flight is enhanced, and unnecessary maintenance cost is saved.

Description

technical field [0001] The present invention aims at the field of remaining service life estimation of aero-engine, and first models the problem of estimating the remaining service life of aero-engine as a Markov sequence decision-making process model, and then uses Deep Reinforcement Learning (Deep Reinforcement Learning) algorithm to obtain the optimal estimate of remaining service life strategy to improve the accuracy of the estimation of the remaining service life of aeroengines. Background technique [0002] Contemporary industrial systems can sometimes fail catastrophically due to aging or other unexpected conditions. Therefore, the maintenance management of machines plays a key role in modern industrial activities. As an efficient maintenance strategy, Condition-based Maintenance (CBM) has been widely used in modern industrial systems. Prognostics, as the key driving force of CBM implementation, plays an important role in CBM. Prediction technology is usually used ...

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): G06F30/27G06N3/04G06N3/08G06N20/00G06F119/02G06F119/04
CPCG06F30/27G06N3/08G06N20/00G06F2119/02G06F2119/04G06N3/045
Inventor 赵永平胡乾坤
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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