Autonomous fault tolerance and fault recovery method for on-orbit processing system

Abstract

According to the autonomous fault tolerance and fault recovery method for the on-orbit processing system, the on-orbit processing system can be verified and corrected based on FPGA internal software, and normal operation of a satellite is guaranteed. Checking and correcting are carried out based on FPGA internal software so as to solve the influence of single event upset, including TMR (triple modular redundancy), EDAC (single bit error correction) and program reloading, and the TMR is mainly used for ensuring that system loading can still be realized after single event upset is carried out on a satellite stand-alone burning application file; the EDAC mainly ensures that error correction can still be realized after key data such as all configuration variables are subjected to single event upset in application program loading operation of a single machine, and normal operation is ensured. The method further comprises a program reloading process which mainly ensures that ground on-orbit uploading can still be realized after three application files burnt by a single satellite machine are all subjected to single event upset, and normal operation of the satellite is ensured.

Description

technical field [0001] The invention relates to the technical field of on-orbit fault preplan reliability, in particular to an autonomous fault tolerance and fault recovery method of an on-orbit processing system. Background technique [0002] With the continuous advancement of technology, the requirements for satellite data processing capabilities are getting higher and higher. FPGAs are gradually used in aerospace engineering and become the core components of satellite data processing and control. However, the space working environment where the satellite is located is relatively special, and there are various external factors, including the sun's electromagnetic radiation field and various high-energy particles such as neutral particles and plasma at various temperatures, among which high-energy charged particles are incident on electronic devices. The radiation effect is called single event effect. Depending on the mechanism of the effect, it includes single event upset...

AI Technical Summary

Problems solved by technology

[0003] Judging from the current application of satellite products, the FPGA logic state is often limited in availability and reliability due to the single event effect. After a single event flip occurs, it will cause a jump in the potential state, "0" becomes "1", or "1" becomes "0". When a single event occurs in the device, although data retransmission, device restart or power-off operations can be performed on the device or functional modules, the functional performance of the satellite product will be greatly affected. There is a certain risk to the system's in-orbit operation

Images