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

An aeroengine residual service life prediction method based on LSTM network and ARIMA model

A technology for aero-engine and life prediction, applied in biological neural network models, predictions, neural learning methods, etc., can solve problems such as increased operating costs of airlines, and achieve the effects of reducing maintenance costs, high accuracy and feasibility

Active Publication Date: 2019-03-15
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF3 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, premature maintenance will inevitably increase the operating cost of airlines. Therefore, it is necessary to timely grasp the maintenance time, so as to maximize the use value of the engine

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
  • An aeroengine residual service life prediction method based on LSTM network and ARIMA model
  • An aeroengine residual service life prediction method based on LSTM network and ARIMA model
  • An aeroengine residual service life prediction method based on LSTM network and ARIMA model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0052] A kind of aero-engine residual service life prediction method based on LSTM network and ARIMA model that the present invention illustrates, specifically comprises the following steps:

[0053] Step 1), according to engine historical degradation data, set up n engine health index (LSTM-HI) models based on LSTM deep neural network, construct the health index model library reflecting remaining service life;

[0054] Step 1.1), according to the historical data of aero-engine degradation from health to failure, select appropriate sensor parameters, and perform noise reduction and smoothing processing to form n training data sets;

[0055] Step 1.2), constructing the aeroengine health status evaluation index LSTM-HI based on the deep learning network LSTM and the training data set, the specific expression is as follows:

[0056]

[0057...

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 an aeroengine remaining service life prediction method based on an LSTM network and an ARIMA model. The method comprises the following steps: n engine health index (LSTM-HI) models based on an LSTM depth neural network are established according to engine historical degradation data; According to the engine sensor data, the ARIMA model is trained and the engine sensor parameters are predicted backward in many steps. By predicting the sensor parameters, according to LSTM-HI index is used to evaluate whether the engine is degraded to failure, and the remaining service lifeand its probability distribution are obtained. The invention provides a novel method for predicting the remaining service life of an aeroengine, which has high accuracy and feasibility, and plays anactive role in promoting the real-time health management of the aeroengine and reducing the maintenance cost.

Description

technical field [0001] The invention belongs to the technical field of remaining service life of aero-engines, in particular to an aero-engine remaining service life prediction method based on LSTM (Long Short-Term Memory) network and ARIMA (Autoregressive Integrated Moving Average Model) model. Background technique [0002] Aeroengines work under harsh conditions of high temperature, high pressure, and high load all year round, and their working status changes frequently, which leads to frequent engine failures. Aeroengine is the "heart" of aircraft, and its health directly determines the personal safety of passengers and the safety of civil aviation flight. To ensure its safety, the engine must be repaired in time. However, premature maintenance will inevitably increase the operating cost of airlines. Therefore, it is necessary to timely grasp the maintenance time, so as to maximize the use value of the engine. Accurately predicting the remaining useful life (RUL) of an ...

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): G06F17/50G06N3/08G06Q10/04
CPCG06N3/08G06Q10/04G06F30/15Y02T90/00
Inventor 鲁峰吴金栋黄金泉仇小杰丁华阳金鹏
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