A DRL-Based Adaptive Control Design for a Class of Nonlinear Systems With Mismatched Disturbances: From Algorithm to Application

Focusing on control performance enhancement for a general class of nonlinear systems with mismatched disturbances, an intelligent composite regulator is investigated by integrating disturbance observation, nonrecursive nonsmooth control (NRNSC), and deep reinforcement learning (DRL) techniques in this article. With the help of the self-learning ability delivered by the DRL algorithm, a robust adaptive control scheme is constructed for handling the challenge of parameter configuration difficulty in the traditional NRNSC synthesis approach. A new feature is that the bandwidth factor optimization in both feedforward and feedback loops is simultaneously considered. While ensuring the system maintains certain robustness, the most suitable adaptive bandwidth factors are self-tuned to optimize the control performance. Thereafter, an appropriate tradeoff is promisingly achieved between the two performances. To enhance the persuasiveness of the proposed method in terms of performance improvement, numerical simulations, and experiment tests on a permanent magnet synchronous motor (PMSM) position servo platform are conducted.