Adaptive Neural Fixed‐Time Command Filtered Control for Stochastic Nonlinear Systems With Input Quantization

ABSTRACT In this paper, an adaptive neural network fixed‐time control method based on command filtering is proposed for stochastic nonlinear systems with input quantization. The method utilizes a radial basis function neural network (RBFNN) to approximate the unknown nonlinear terms in the system. The jitter problem is effectively solved in the controller design by configuring the hysteresis quantization inputs as two bounded nonlinear functions. In addition, the fixed‐time control strategy is combined with the command filtering method to probabilistically guarantee the fixed‐time stability of the closed‐loop system, which overcomes the “complexity explosion” and “singularity” problems in the classical backstepping design. Meanwhile, a new error compensation mechanism is designed to effectively compensate for the filtering error. The theoretical analysis proves that the control scheme can ensure that the output tracking error of the closed‐loop system converges to a sufficiently small neighborhood of the origin in a fixed time and that all signals within the closed‐loop system are bounded. Finally, the feasibility and effectiveness of the scheme are verified by two simulation examples.