Unlock instant, AI-driven research and patent intelligence for your innovation.

Aircraft telemetry parameter anomaly detection method based on uncertainty estimation

A technology of uncertainty and telemetry parameters, applied in the field of data processing, can solve problems such as abnormal detection of aircraft telemetry parameters, failure to reflect model estimation confidence, and overfitting, so as to reduce overfitting, prevent overfitting, and improve effect of effect

Pending Publication Date: 2021-12-24
HARBIN INST OF TECH +1
View PDF0 Cites 0 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 confidence and overfitting of model estimation cannot be reflected in the existing methods, and to provide an abnormal detection method for aircraft telemetry parameters based on uncertainty estimation

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
  • Aircraft telemetry parameter anomaly detection method based on uncertainty estimation
  • Aircraft telemetry parameter anomaly detection method based on uncertainty estimation
  • Aircraft telemetry parameter anomaly detection method based on uncertainty estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 2

[0068] Embodiment 2. This embodiment is a modification of the method for establishing an LSTM-based multivariate telemetry parameter uncertainty characterization and estimation model for an aircraft in the uncertainty estimation-based aircraft telemetry parameter anomaly detection method described in this embodiment. Further defined, the method specifically includes:

[0069] Obtain the training parameter set of the multivariate telemetry parameters of the aircraft and the training data of the parameters to be detected;

[0070] Preprocessing the training parameter set specifically includes:

[0071] Using the maximum mutual information coefficient method to perform feature extraction on the training parameter set, and obtain the feature parameter set of the parameter to be detected;

[0072] performing feature fusion on the feature parameter set by using a principal component analysis method to obtain a fusion feature parameter set;

[0073] According to the fusion feature ...

Embodiment approach 3

[0074] Embodiment 3. In this embodiment, in the method for anomaly detection of aircraft telemetry parameters based on uncertainty estimation described in Embodiment 2, the method of using the maximum mutual information coefficient method is used to perform feature extraction on the training parameter set to obtain the Further definition of the method of the feature parameter set of the parameter to be detected, the method includes:

[0075] According to the maximum mutual information coefficient method, obtain the maximum mutual information coefficient of the parameters to be detected and all parameters in the training parameter set;

[0076] Setting a threshold of the maximum mutual information coefficient, selecting a parameter related to the parameter to be detected according to the threshold, and obtaining a feature parameter set of the parameter to be detected according to the parameter related to the parameter to be detected.

Embodiment approach 4

[0077] Embodiment 4. In this embodiment, in the method for abnormal detection of aircraft telemetry parameters based on uncertainty estimation described in Embodiment 2, the feature fusion of the feature parameter set is performed using the principal component analysis method to obtain the fusion feature parameters The method of set is further defined, and the method specifically includes:

[0078] Standardizing the feature parameter set to obtain a standardized feature parameter set;

[0079] obtaining the covariance matrix of the standardized parameter feature set;

[0080] Obtain the eigenvector matrix and eigenmatrix of the covariance matrix;

[0081] Obtaining the principal component contribution rate of the standardized characteristic parameters according to the characteristic vector matrix and the characteristic matrix;

[0082] Set the parameter dimensions of the fusion feature parameter set, arrange the principal component contribution rates in descending order, and...

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 aircraft telemetry parameter anomaly detection method based on uncertainty estimation, belongs to the technical field of data processing, and solves the problem that the confidence coefficient and overfitting of model estimation cannot be reflected in an existing method. The method comprises the following steps: establishing an LSTM-based aircraft multi-element telemetry parameter uncertainty representation estimation model; acquiring a test parameter set of multi-element telemetry parameters of the aircraft and test data of to-be-detected parameters, and performing feature selection on the test parameter set; performing feature fusion on the test feature parameter set; repeatedly inputting the test fusion feature parameter set into the LSTM-based aircraft multivariate telemetry parameter uncertainty representation estimation model to obtain an estimated value set of the to-be-detected parameters; obtaining a smooth dynamic threshold interval of the to-be-detected parameters; and judging the health state of the aircraft according to the smooth dynamic threshold interval of the to-be-detected parameters and the test data of the to-be-detected parameters. The invention is suitable for carrying out anomaly detection on the aircraft telemetry parameters.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular to a method for detecting abnormality of aircraft telemetry parameters based on uncertainty estimation. Background technique [0002] With the rapid development of aerospace technology, the aircraft is facing the challenges of increasing task complexity, performance requirements and project costs. The structure of its system is becoming more and more complex. The correlation between them is more closely. Even a small glitch can set off a chain reaction that jeopardizes the safety of the entire aircraft. This puts forward new and higher requirements for the reliability, safety and accuracy of aircraft testing and maintenance. [0003] Telemetry data is an important support to reflect the state of the aircraft system. Timely monitoring its operating state and taking corresponding measures can avoid the occurrence of abnormal operation or failure. Aircraft tele...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06N3/047G06F18/2135G06F18/214G06F18/2415G06F18/253
Inventor 王媛任捷刘大同朱京来彭喜元罗悦
Owner HARBIN INST OF TECH