Adaptive control of a helicopter system with finite-time performance constraints and input backlash

For a helicopter system exhibiting linear input backlash characteristics, this study proposes an adaptive control framework based on a Radial Basis Function Neural Network (RBFNN) to satisfy prescribed performance constraints and achieve input backlash compensation. First, a Barrier Lyapunov Function (BLF) is employed to ensure that the tracking error remains strictly within the bounds defined by the prescribed performance function. Second, the RBFNN is utilized to approximate unknown nonlinearities in the system dynamics, thereby enhancing the adaptability and robustness of the control scheme. Finally, to compensate for the adverse effects of input backlash, an adaptive inverse model is developed to mitigate signal discontinuities, ultimately improving overall control accuracy. Theoretical analysis confirms that the closed-loop system maintains stability and achieves finite-time convergence. Both simulation and experimental results validate the effectiveness of the proposed method in suppressing backlash, minimizing tracking errors, and ensuring constrained state control.