Compensation control for dead-zone by adaptive dynamic radial basis function network
自适应动态径向基函数网络死区补偿控制

Dead-zone nonlinearity exists in many practical systems, which deteriorates the performance of control system and even causes the instability of the system. In order to compensate the dead-zone nonlinearity in the dynamic system, a dead-zone compensation control algorithm based on adaptive dynamic radial basis function network(DRBF) is presented for eliminating the undesirable effects caused by the unknown dead-zone. A linear controller paralleled with the DRBF network is designed for the compensated dynamic system. The closed-loop system stability is proved by Lyapunov method. The simulation research was performed in a hydraulic system. The results show that this proposed algorithm effectively eliminates the steady-state error, reduces the computation complexity, and makes the control signal less oscillatory.