matlab仿真请教

luoqiwuhui

请教： 在lqe设计中，Q,R,N应该怎么选取？
    Given the system
        .
        x = Ax + Bu + Gw            {State equation}
        y = Cx + Du + v             {Measurements}

    with unbiased process noise w and measurement noise v with
    covariances

        E{ww'} = Q,    E{vv'} = R,    E{wv'} = N ,

    [L,P,E] = lqe(A,G,C,Q,R,N)  returns the observer gain matrix L
    such that the stationary Kalman filter
        .
        x_e = Ax_e + Bu + L(y - Cx_e - Du)

anbcjys

这是设计的权重