Fault diagnosis method of spacecraft based on artificial intelligence

Abstract

The invention discloses a fault diagnosis method of a spacecraft based on a back propagation BP neural network, which mainly solves the problem that prior knowledge is highly dependent in the prior art. The invention utilizes spacecraft environmental data to train back propagation BP neural network to fit probability data of spacecraft abnormal event occurrence. The implementation scheme is as follows: Back Propagation BP neural network model is determined, the training set data and test set data of back propagation BP neural network are obtained, the parameters of back propagation BP neural network is initialized, the BP neural network is trained, the trained BP neural network is optimized, the optimized BP neural network is used to diagnose the new spacecraft data. The invention fully utilizes the adaptive ability and the learning ability of the BP neural network, can well fit the probability data of the occurrence of the abnormal event of the spacecraft, reduces the dependence on the prior knowledge, and can be used in the field of wireless network communication.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, in particular to a spacecraft fault diagnosis method, which can be used in the field of wireless network communication. Background technique [0002] In recent years, with the continuous development of the aerospace field and the continuous breakthrough of aerospace technology, human spaceflight activities have continued to increase, and the health status of spacecraft has also received extensive attention from technicians and experts engaged in spacecraft design. Due to the complexity of the space environment, the limitations of the spacecraft ground test system, and the increase in the complexity of the current spacecraft system, abnormal operation of the spacecraft and system failures are inevitable, and the reliability of the spacecraft will be reduced accordingly. Accurately troubleshooting and repairing spacecraft systems can be costly. Therefore, whether the spacecraft can...

AI Technical Summary

Problems solved by technology

The limitations of this method are: strong dependence on prior knowledge, such as the need to pre-determine the upper and lower limits of parameters, fault knowledge and system model, so this method is insufficient in terms of adaptive ability, learning ability, and processing of inaccurate information.

Images