Gears are one of the important sources of vibrations and noise in industrial rotating machinery and power transmission systems. In order to design and develop an optimal and quiet geared power transmission system, this paper presents the design of an active vibration control for gear-bearing system. A dynamic model of the geared system is presented, where some undesired parameters in the design such as manufacturing errors, teeth deformations, mounting errors as well as external excitations resulting from distributions of applied torque are included. An active control system is presents in order to control and attenuate the disturbance impress on the system vibrations. The idea behind the design of this control system is to reduce vibration transmissibility by the introduction of the excitation forces in the bearing. The controller is investigated and designed by using feedback control and based on the H-infinity control approach. It can be presented as an optimization problem. To solve this optimization problem, Particle swarm optimization (PSO) algorithm is used, which is one of the optimization methods available among artificial intelligence. The simulation results are performed to investigate performance of the control system.