Aiming at a class of affine nonlinear system, a trajectory linearization method is used to equivalently transform the
nonlinear system into a linear time-varying(LTV) system. Then, a pseudo-inverse and a fault dynamic model are established
by using neural network. Finally, the nominal controller and the fault accommodation laws are established by using the
Lyapunov method from parameter variety. Thus the stability of the fault-suffered system is ensured. Simulation results show
the effectiveness of the proposed algorithm.