Particle swarm optimization based nonlinear observer

Particle swarm optimization algorithm is a new and efficient evolutionary computation method. A particle swarm optimization based nonlinear observer design method is proposed. It belongs to moving horizon estimation method. The basic idea of the method is that the state estimation of nonlinear continuous-time system is converted into an on-line optimization of nonlinear functions, and then the particle swarm optimization algorithm is employed to find optimal estimation of the system states. Simulation result shows that the proposed observer is not sensitive to the initial conditions and has a good tracking ability to the variations of the states.