Fault Diagnosis and Reliable Configuration of Uncertain Strip Area Based on MPSO-SVM

For a class of linear uncertain flight control systems, in terms of the strip region, the problem of actuator continuous gain fault and reliable control is studied. At the same time, in order to solve the difficulty of selecting parameters of support vector machine, a parameter optimization algorithm based on improved Particle Swarm Optimization (MPSO) is proposed. Compared with grid search method, particle swarm optimization and genetic algorithm, this method has the advantages of fast convergence, short time consuming and high accuracy. For the problem that the pole information is difficult to obtain, the algorithm theory of pole observer is given to realize the real-time observation of unknown system. Finally, the effectiveness of reliable controller design is further proved by numerical simulation.