The Theoretical Study Of The Flight Control System Fault Detection And Software System Design

Self-Repairing Flight Control System (SRFCS) is a kind of active-and passive failure tolerant control based on the Fly-by-wire flight control system, and it is also an important tendency of the future flight control system. Using aircraft's onboard computer thoroughly, the SRFCS could enhance the flight control system's reliability, survivability, maintainability and lower Life Circle Cost (LCC) while do not use more hardware. Failure Detection and Isolation (FDI) is the key technique of SRFCS, which can forecast the occurrence of potential failure, tell why and where it occurs, and then provide relevant information for trigger test, control law reconfiguration and automated maintenance diagnostic.Artificial Neural Network(ANN) is a information processing system which is composed of a number of nonlinear computational elements which operate in parallel and are arranged in a manner reminiscent of biological neural interconnection. In this thesis, the ANN is designed to a failure sorter which is used to detect the failure of control surfaces in order to get the losing status of each control surface and improve the rapidity and precision of the control surface failure detection. The main contributions of this thesis are shown as follows: Firstly, A kind of model based residual generation algorithm, deduced from parity space and aircraft model, is presented to get actuators' and control surfaces' failure signals.Secondly, Binary probability hypothesis detection is studied and is utilized as actuators' FDI residual decision.Thirdly, Multi-layer Feed-forward ANN and Error Backward Propagation(BP) algorithm are studied and are utilized as control surfaces' failure detection and sortation.Finally, the real-time simulation software according to the corresponding theory and the specification of software engineer is presented, and software testing(offline) is processed later to prove the validity of the theory.