Reconstruction Based On Neural Network Flight Control System Theory And Simulation Study

Self-Repairing Flight Control System (SRFCS) is a kind of active and passive failure tolerant control based on the Fly-by-Ewire 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. Flight control law reconstruction is the another core. These are the key technologies of SRFCS. So, there is far trying in reconstruction field.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. Here ,it is a control law robust, learning kinds of faults peculiarity ,adopting in-out data to training net.Causing training ,we can raise its precision and speed.The main contributions of this thesis are shown as follows:Firstly, Researching for kinds of reconstruction theories, and certifying the feasibility of control law reconstruction using ANN.Secondly, Introducing the control law reconstruction method,and verdicting that it is hold true.Finally, the real-time reconstruction emulation according to the ANN RBF method ,and to verify the validity of the theory.