In order to suppress the vibration of a translational flexible hinged plate system, a vibration suppression scheme based on trajectory planning and piezoelectric active control is proposed. The dynamic model of the system is established by finite element method (FEM), and the experimental parameters are identified by wavelet analysis and simulated annealing (SA) algorithm. After obtaining the accurate system model, an optimized vibration suppression trajectory is designed based on the artificial bee colony (ABC) optimization algorithm to reduce the vibration excited during and after translation. Aiming at piezoelectric active vibration control, an actor-critic with experience replay (ACER) reinforcement learning (RL) algorithm is designed to train the vibration modal controllers in simulation environment. In the simulation environment and experimental environment, piezoelectric active control is carried out under the conditions of fixed base and trajectory motion, compared with pure trajectory motion. The simulation and experimental results show that ABC optimization algorithm can attenuate vibration excitation better than classical trajectory, and ACER RL modal controllers also show better vibration suppression effect than large-gain proportional-derivative (PD) controllers, especially for small amplitude vibration.