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

Embedded high-efficiency computation platform oriented to onboard fault prediction and health management, and method

A fault prediction and health management technology, applied in the registration/indication of vehicle operation, instruments, registration/indication, etc., can solve the problems such as the inability of the aircraft PHM system to monitor and diagnose the status of the fault, and the failure of the aircraft to be discovered in time. Achieving the effect of rich extensible interfaces, strong expansion ability and strong expansibility

Inactive Publication Date: 2019-12-06
HARBIN INST OF TECH
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims to solve the problem that the existing aircraft PHM system cannot perform complex state monitoring and fault diagnosis, and the complex state assessment needs the help of the ground analysis system, resulting in the problem that aircraft faults cannot be discovered in time, and now provides an airborne fault prediction Embedded high-energy-efficiency computing platform and method for health management

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
  • Embedded high-efficiency computation platform oriented to onboard fault prediction and health management, and method
  • Embedded high-efficiency computation platform oriented to onboard fault prediction and health management, and method
  • Embedded high-efficiency computation platform oriented to onboard fault prediction and health management, and method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0032] Specific implementation mode one: refer to Figure 1 to Figure 10 Specifically, an embedded high-energy-efficiency computing platform oriented to airborne fault prediction and health management described in this embodiment includes: a data processing unit, a data cache and storage unit, and an onboard bus interface unit;

[0033] The onboard bus interface unit is used to collect flight parameters on the onboard bus in real time, and is also used to send the analysis results sent by the data processing unit to the onboard bus.

[0034] The data processing unit communicates with the on-board bus through the on-board bus interface unit, and is used to analyze the flight parameters on the on-board bus to obtain analysis results.

[0035] Among them, the ARMA model is embedded in the data processing unit, and the flight parameters on the airborne bus are used to fit the model using the RLS algorithm, and the fitting result is obtained as the analysis result of the data proce...

specific Embodiment approach 2

[0070] Specific implementation mode two: An embedded high-energy-efficiency computing method for airborne fault prediction and health management described in this implementation mode, the method is:

[0071] Collect and store flight parameters on the onboard bus,

[0072] Use standard parameters to initialize the ARMA model (Auto-Regressive and Moving Average Model, auto-regressive and moving average model),

[0073] Use the currently collected flight parameters to use the RLS algorithm to fit the ARMA model to obtain the fitting result. The fitting result is the predicted value of the flight parameters at the next moment, and the predicted value is used as the analysis result of the flight parameters.

[0074] send analysis results to the onboard bus,

[0075] Determine whether to end the analysis, if yes, end the analysis, otherwise re-acquire and store the flight parameters on the current on-board bus.

[0076] In actual operation of this embodiment, if Figure 11 as sho...

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 embedded high-efficiency computation platform oriented to onboard fault prediction and health management, and a method, and relates to the field of the aircraft onboard fault diagnosis and health management. The problem that the aircraft fault cannot be discovered in time since the existing aircraft PHM system cannot perform complex state monitoring and fault diagnosis and the complex state assessment needs to use a ground analysis system is solved. The method comprises the following steps: collecting a flight parameter on an onboard bus and storing the same, fittingan ARMA model by using a RLS algorithm by utilizing the currently collected flight parameter, thereby acquiring a fitting result, wherein the fitting result is a prediction value of the flight parameter at the next moment; and serving the prediction value as an analysis result of the flight parameter, and sending the analysis result to the onboard bus. And the computation real-time requirements of the onboard fault prediction and health management algorithm under the power consumption, the volume, the weight and multiple limitation conditions are satisfied.

Description

technical field [0001] The invention belongs to the field of aircraft airborne fault diagnosis and health management. Background technique [0002] Fault prediction and health management (Prognostics and Health Management, PHM) technology refers to the use of advanced sensor technology to obtain the operating status information of the system, with the help of information technology, artificial intelligence and other reasoning algorithms, to realize the status monitoring, analysis and evaluation of the system The health status of the system itself predicts the failure of the system before it fails, and provides a series of maintenance guarantee suggestions or decisions in combination with existing resource information. PHM technology is a comprehensive technology that integrates fault detection, isolation, health prediction and evaluation, and maintenance decision-making. [0003] The performance of aircraft represented by unmanned aerial vehicles continues to improve, and t...

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): G07C5/08G07C5/00
CPCG07C5/008G07C5/0808G07C5/0841
Inventor 刘大同王本宽蒋闵彭宇彭喜元
Owner HARBIN INST OF TECH