Considering the rapid and stable recovery from deep stall in fighter aircraft, a finite-time control strategy based on forced oscillation is proposed. To characterize the dynamics of deep stall state, bifurcation theory is employed for analysis, with the region of attraction boundaries determined through backward-time integration. For generating precise recovery commands in principle, an extended bifurcation analysis is conducted, and forced oscillation commands corresponding to unstable bifurcation points are incorporated into the controller design. To handle timevarying disturbances and aerodynamic parameter perturbations during deep stall, a disturbance observer is designed to estimate lumped uncertainties while neural networks (NNs) compensates for model uncertainties, and the deep stall recovery controller is obtained combining with angle of attack tracking error feedback. The system signals involved in the Lyapunov function are proved to be bounded and the sliding mode surface converges in finite time. Simulation results show that the proposed method can reduce the fighter aircraft’s angle of attack to a safe zone while maintaining stable controllability, achieving rapid and smooth recovery from deep stall conditions.