Satellite Fault Diagnosis and Prediction Method Based on Evidence Reasoning

A technology for fault diagnosis and satellite faults, which is applied in the field of satellite fault management and can solve problems such as sensitivity of uncertain information

Active Publication Date: 2018-10-19
NANJING UNIV OF POSTS & TELECOMM
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The application of ER method in the field of satellite fault and diagnosis can effectively solve the shortcomings of existing methods that are sensitive to uncertain information

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
  • Satellite Fault Diagnosis and Prediction Method Based on Evidence Reasoning
  • Satellite Fault Diagnosis and Prediction Method Based on Evidence Reasoning
  • Satellite Fault Diagnosis and Prediction Method Based on Evidence Reasoning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The invention includes two aspects of fault diagnosis and fault prediction.

[0032] Troubleshooting:

[0033] The invention models satellite fault diagnosis based on the ER method and utility theory. The model first obtains the reliability of each attribute based on the existing satellite telemetry data, and converts the fault diagnosis input into the reliability distribution form. When all the input variables describe the reliability distribution form, the ER algorithm is directly applied to combine all the attributes to obtain the fault diagnosis result of the reliability distribution form. Finally, through the utility theory, the result of the evidence fusion is digitized and compared with the reference value to determine whether the satellite device being diagnosed is faulty.

[0034] Failure prediction:

[0035] For prediction problems, the input of the prediction model is the characteristic parameters of the system health in the past moment, which lags behind the curre...

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 present invention provides a satellite fault diagnosis and prediction method based on evidence reasoning. The analytical ER method is applied to the satellite fault diagnosis, and the fault diagnosis result at the previous p moment and the diagnosis result at the current moment are respectively used as the input and the diagnosis result of the neural network. The output trains the neural network to find out the relationship between the previous p time and the current time, and then complete the fault prediction. The invention provides a nonlinear complex system fault diagnosis and prediction method under multi-parameter condition. Predictive modeling using the characteristic parameters output by fault diagnosis can more intuitively and effectively reflect the health status of the inertial platform at the next moment.

Description

Technical field [0001] The present invention relates to an intelligent fault diagnosis and prediction method based on evidence thrust applied to satellite equipment. The present invention can not only be used in satellites, but also can be applied to other mechanical equipment with a higher degree of automation and convenient for information collection. It belongs to satellite fault management field. Background technique [0002] Fault diagnosis is to ensure the normal operation of the designated system, using instruments, equipment and computer technology to monitor, inspect and test the system, and obtain system fault information. Fault prediction technology is a subject technology developed on the basis of fault diagnosis technology. Through advanced instrumentation and computer technology, it monitors and recognizes the symptoms that indicate the occurrence of faults, so as to achieve the effect of fault prediction and avoid the occurrence of faults. Early fault diagnosis me...

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): G06N5/04G06N3/04G06Q10/00
CPCG06N3/04G06N5/04G06Q10/20
Inventor 孙力娟韩稳稳王汝传周剑肖甫叶晓国郭剑
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap