Vibration frequency fuzzy adaptive control of the flexible lunar regolith sampler based on the dynamic prediction by using the RBFNN

The drilling efficiency can be improved effectively by controlling the lunar regolith sampler always in the resonance state. But the dynamical modeling of the sampler-regolith system is difficult to obtain and time varies when the sampler is in different depth in the lunar regolith. For the nonlinear time-varying system of the dynamic modeling of the sampler in drilling, we present a method of the vibration frequency fuzzy adaptive control based on the dynamic prediction by using the RBFNN. The Radial Basis Function (RBF) neural network with a FIR filter in series is used to predict the resonant frequency dynamically and decrease the overshoot. And the fuzzy adaptive control is used to calculate the sweeping frequency bandwidth with the input of the amplitude and variation. The simulation results have verified the effectiveness of the control strategy. The experimental results show that the control algorithm can improve the drilling depth, drilling efficiency and the discarding efficiency effectively.