Autonomous health management method for lunar surface mobile system based on SCNN

By applying an autonomous health management method based on SCNN in the lunar surface mobile system, the problems of fault prediction and autonomous handling in complex systems are solved, and the comprehensiveness and autonomy of health management are achieved, which significantly improves the accuracy of fault identification and handling.

CN119741005APending Publication Date: 2025-04-01CHINA ORDNANCE SCI INST +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202411827262.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-12
Publication Date
2025-04-01

AI Technical Summary

Technical Problem

The prior art is difficult to achieve accurate prediction and autonomous handling of faults in complex lunar detection systems, especially in combination and deep-level faults, with limited identification and processing capabilities.

Method used

The autonomous health management method of the lunar surface mobile system based on SCNN is adopted, and the lightweight SCNN network is used to conduct fault prediction training and inference through the input of multi-dimensional telemetry data matrix, so as to achieve accurate prediction of asynchronous heterologous telemetry faults, and independently deal with them based on the fault prediction results.

Benefits of technology

The comprehensiveness, autonomy, real-timeness and accuracy of the health management of the lunar mobile system has been improved, and faults can be located more accurately and autonomously handled. Compared with traditional methods, the accuracy of fault identification and handling has been significantly improved.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an SCNN-based autonomous health management method for a lunar surface mobile system, and relates to the technical field of lunar surface detection equipment management, and the method comprises the following steps: 1, collecting the telemetry data of each subsystem in the lunar surface mobile system; 2, describing the telemetry data by adopting a telemetry data queuing model to obtain unified telemetry data; 3, preprocessing the unified telemetering data to obtain a telemetering matrix; 4, inputting the telemetering matrix into a trained health state prediction model to obtain a diagnosis result; and 5, generating a maintenance and repair strategy according to the diagnosis result. According to the method, fault prediction training and reasoning are carried out by inputting the multi-dimensional telemetering data matrix into the lightweight SCNN network, accurate prediction of asynchronous different-source telemetering faults is realized, and autonomous disposal is realized based on a fault prediction result.
Need to check novelty before this filing date? Find Prior Art