Abstract: As a new type of actuator mechanism integrating power electronics and permanent magnet synchronous motor(PMSM), motor direct-drive actuator has the advantages of simple transmission structure, high control flexibility and strong digitalization capability. In view of the problem that the load change of the direct-drive actuator leads to the decrease of the speed loop performance in the actual operating conditions, a fuzzy neural network(FNN) and particle swarm optimization(PSO) algorithm based on the optimization of the speed loop control parameters of the motor direct-drive actuator is proposed. The standard PSO algorithm is used to optimize the speed loop PI parameters of the PMSM control system in the direct-drive actuator, while the FNN algorithm is used to optimize the inertia weights in the PSO algorithm. Firstly, the mathematical model of PMSM is established and the design method of speed loop PI controller parameters is analyzed. Secondly, the optimization of the speed loop PI controller parameters of the PMSM control system in the motor direct-drive actuator is analyzed based on the standard PSO algorithm. Subsequently, the inertia weights in the standard PSO algorithm are optimized by combining with the FNN algorithm. Finally, the validity of the proposed method is verified by experiments. The experimental results show that the method can improve the performance of the speed loop of the control system of the motor direct-drive actuator mechanism, which provides an effective solution for the control performance improvement of the motor direct-drive actuator mechanism in the face of the change of system inertia.