Fault Diagnosis Of Satellite Attitude Control System Based On Quantum Neural Network

With the rapid development of science and technology,every country pays more and more attention to the development of aerospace science and technology.Satellite has become an indispensable important support in different fields.Attitude control system(ACS)is one of the most complex subsystems in satellite system.Once the ACS fails,it is very likely that the satellite will lose control of its posture in a short period of time,resulting in serious consequences and even a disaster.The high reliability and security of satellite attitude control system is an important requirement of space mission,and fault diagnosis technology is an effective way to improve the reliability of various complex control systems.Therefore,the fault diagnosis of satellite attitude control system is very important.Quantum computing has the characteristics of high parallelism,exponential storage capacity and exponential acceleration.Neural network is an effective intelligent tool,which can approximate any nonlinear system.Combining quantum computation with neural network for fault diagnosis of satellite attitude control system can quickly diagnose system faults and provide a strong guarantee for the successful completion of space missions.In this paper,based on BP neural network and universal quantum gate in quantum computing,a universal quantum gate BP neural network is proposed,and a quantum circuit neural network is proposed according to quantum circuits of quantum gates,which improves the learning speed and convergence performance of the network.Then,taking satellite attitude control system as the research background,this paper analyzes the kinematics and dynamics state space models of satellite attitude,and establishes the model of satellite attitude control system and some fault models.On this basis,state observer based on general quantum gate BP neural network and fault diagnosis observer based on quantum circuit neural network are designed,and the stability of the observer is proved by Lyapunov stability theory.Finally,taking the actuator of satellite attitude control system as the analysis object.this paper detects and diagnoses the fault online by the universal quantum gate BP neural network and quantum circuit neural network.The simulation of fault diagnosis proves the feasibility and accuracy of the adaptive fault diagnosis state observer based on the universal quantum gate BP neural network and the fault diagnosis observer based on quantum circuit neural network.Thereby this paper achieves the purpose of fault diagnosis for the actuator of satellite attitude control system using the quantum neural network.