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

Method for predicating remaining life of turbine engine based on degradation model matching

A turbine engine and degradation model technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem that the prediction effect cannot meet the prediction requirements, etc.

Active Publication Date: 2012-11-21
HARBIN INST OF TECH
View PDF3 Cites 53 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the prediction effect of the general RUL prediction model for the prediction of the remaining life of the existing turbine engine cannot meet the prediction requirements, and to provide a prediction method for the remaining life of the turbine engine based on the degradation model matching

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
  • Method for predicating remaining life of turbine engine based on degradation model matching
  • Method for predicating remaining life of turbine engine based on degradation model matching
  • Method for predicating remaining life of turbine engine based on degradation model matching

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0014] Specific implementation mode one: combine figure 1 Describe this embodiment, the method for predicting the remaining life of a turbine engine based on the degradation model matching described in this embodiment, it includes specific steps as follows:

[0015] Step 1. Data preprocessing: Extract the variable that determines the operating state of the turbine engine from the collected raw data: c 1 is height, c 2 is the Mach number and c 3 is the throttle angle; the numerical values ​​of the running state variables form a set c=(c 1 ,c 2 ,c 3 ) T ; c i means c at time t i Corresponding values ​​of height, Mach number and throttle angle, c i =(c 1i , c 2i ,c 3i ) T , where i is a positive integer;

[0016] The values ​​that can characterize the degradation process of the turbine engine are collected from 21 sensors located at different positions of the turbine engine, and the values ​​form a 21-dimensional feature vector: x=(x 1 ,x 2 ,...,x 21 ) T , x i m...

specific Embodiment approach 2

[0028] Specific implementation mode two: combination figure 2 This embodiment is described. This embodiment is a further limitation of the method for predicting the remaining life of a turbine engine based on the degradation model matching described in Embodiment 1. The specific process of step 1 data preprocessing is as follows:

[0029] Step one one, to determine the set c=(c 1 ,c 2 ,c 3 ) T Use the K-means algorithm to cluster to obtain the p-type operating status Ω={O 1 ,O 2 ,...,O p}, p is a positive integer;

[0030] Step 12, divide the readings of the sensors in each extracted training entity according to the p-type operating status Ω, and divide them into p groups;

[0031] Step 13: Detect the change of the readings of each sensor in all training entities over time in each operating state, and select the sensor set Α={X 1 ,X 2 ,...,X m}, where m is a positive integer;

[0032] Step 14, a certain group of training entities divides the readings of the selecte...

specific Embodiment approach 3

[0042] Specific implementation mode three: combination figure 2 This embodiment is described. This embodiment is a further limitation of the method for predicting the remaining life of a turbine engine based on degradation model matching described in Embodiment 1. The specific process of establishing a degradation model library in step 2 is as follows:

[0043] Step 21. Divide the readings of the selected sensor set B according to the operating state Ω and divide them according to Perform linear regression to obtain the time series of health factors in group p;

[0044] Step 22. The p group of health factor time series is sorted by the time before the state division and restored to a complete set of health factor time series X 0 ={X 0 (k)|};

[0045] Step 23. Repeat steps 21 and 22 for all training entities, so that each training entity has a set of corresponding health factor time series;

[0046] Step two and four, using exponential regression model Fit the time seri...

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 predicating remaining life of a turbine engine based on degradation model matching relates to a remaining life predication method for the turbine engine, and solves the problem that the predication effect cannot reach the predication requirement when a universal RUL (Remaining Useful Life) is adopted to predicate the remaining life of the turbine engine. The method comprises the specific steps as follows: step one, pre-treating data, that is, extracting a running state variable from the acquired data, acquiring a feature vector for a sensor, and fusing the running state variable and the feature vector to form a health factor; step two, building a degradation model base, that is, building degradation models by using the health factor, and forming the degradation model base by the degradation model groups; step three, evaluating the similarity, that is, matching a degradation track with the models in the model base and giving an RUL estimation to each model; and step four, fusing the RUL, that is, fusing by means of similarity weighting to obtain the final remaining life predication value according to the tested matching degree of the turbine engine and the model. The method for predicating remaining life of the turbine engine based on degradation model matching is applicable to the predication of the remaining life of the turbine engine.

Description

technical field [0001] The invention relates to a method for predicting the remaining life of a turbine engine. Background technique [0002] Fault prediction can be divided into two parts: the detection of failure precursors and the prediction of remaining service life. The detection of failure precursors is usually application-related and requires background knowledge related to the system, while RUL (Remaining Useful Life) prediction is relatively independent, so The techniques used to make RUL prediction are roughly the same for all failure prediction applications. As a rapidly developing research field, the research on RUL prediction has introduced techniques and algorithms from many other research fields, such as: reliability engineering, regression analysis, time series modeling, artificial intelligence, etc. Most of the existing RUL prediction algorithms obtain a general prediction model by training historical data. These models may be more effective for application...

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): G06F19/00
Inventor 刘大同李君宝徐勇罗悦庞景月王红彭宇
Owner HARBIN INST OF TECH
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