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

A Method for Predicting the Remaining Life of Aeroengine Based on Transfer Learning

An aero-engine and life prediction technology, applied in neural learning methods, computer-aided design, instruments, etc., can solve the problems of difficult to obtain degradation data, low prediction accuracy, poor engineering usability, etc., to achieve improved accuracy, high prediction accuracy, The effect of improving prediction accuracy

Active Publication Date: 2021-12-17
BEIHANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to disclose a method for predicting the remaining life of an aero-engine based on transfer learning. The technical problem solved by this method is that the current data-driven prediction method is difficult to obtain degradation data, poor engineering usability, and low prediction accuracy.

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
  • A Method for Predicting the Remaining Life of Aeroengine Based on Transfer Learning
  • A Method for Predicting the Remaining Life of Aeroengine Based on Transfer Learning
  • A Method for Predicting the Remaining Life of Aeroengine Based on Transfer Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The flow chart of the method for predicting the remaining life of aero-engine based on transfer learning proposed by the present invention is as follows: figure 1 shown. The specific steps of the method for predicting the remaining life of aero-engine based on transfer learning are as follows:

[0067] Step 1. Sensitive parameter analysis S1: Carry out sensitivity analysis on all the condition monitoring parameters of the aero-engine, so as to obtain several monitoring parameter sets X={x that can characterize the performance degradation of the aero-engine 1 , x 2 ,...,x n}

[0068] Step 2: Data preprocessing S2: smoothing and normalizing the selected sequence of aero-engine performance degradation characteristic parameters, and obtaining c preprocessed parameter data X={x 1 , x 2 ,...x c}, c is the number of engine operating cycles, where X c ={x c1 , x c2 ,...,x cn}

[0069] Step 3: Calculation of similarity distance based on dynamic time warping algorithm ...

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 method for predicting the remaining life of an aero-engine based on migration learning, including the following steps: performing sensitivity analysis on the multi-dimensional degradation parameters of the aero-engine, screening out the degraded sensitive parameters and performing preprocessing to improve the data expression ability; based on the dynamic time warping algorithm to treat Measure the transferability of the test samples and use the sliding time window to complete the time-domain sensitive data matching; screen the transferable samples based on the transferability measurement results and calculate the migration weight; construct the training data set by cutting the transferable sample data; use each transferable sample Multiple remaining life prediction models are trained with the training data; based on transferable weights, the prediction results of multiple life prediction models are fused to obtain the final prediction result.

Description

technical field [0001] The invention relates to the technical field of remaining life prediction of aero-engine, in particular to a method for predicting remaining life of aero-engine based on migration learning. Background technique [0002] Aero-engine is the most important part of the aircraft. Due to its complex structure and harsh working environment, the failure mode of aero-engine is more diverse and more prone to failure than other parts of the aircraft. Accurate prediction of the remaining service life of aero-engines is of great significance for improving the safety and reliability of aero-engines and avoiding the waste of maintenance resources caused by excessive maintenance. [0003] Existing methods for predicting the remaining service life of aero-engines can be divided into model-based methods, statistical analysis-based methods and data-driven methods. Although the model-based prediction method can more accurately reflect the performance degradation mechanis...

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 Patents(China)
IPC IPC(8): G06F30/27G06N3/04G06N3/08G06F119/02G06F119/04
CPCG06F30/27G06N3/049G06N3/08G06F2119/02G06F2119/04G06N3/044
Inventor 程玉杰周安马剑吕琛
Owner BEIHANG UNIV
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