Precise velocity control is crucial for various systems, such as aircraft, power grids, industrial robots, and electric cars. Traditional control approaches sometimes face challenges such as real time limits, nonlinearities, and complex system dynamics. MPCC-NN, a combination of neural networks and model predictive control (MPC), offers a promising solution to these issues by leveraging the flexibility of neural networks and the predictive capabilities of MPC. This approach ensures enhanced accuracy in speed monitoring. Two types of controllers are compared in this study: proportional-integral (PI) controllers and neural network controllers. The FCSMPCC system is used to control the speed of permanent magnet synchronous motors (PMSMs). Variations in elements such as load and speed can compromise the effectiveness of PI controllers, which typically exhibit satisfactory performance during stable operating conditions. We utilize MATLAB/Simulink to execute the simulation and address these constraints. The results indicate that NN controllers have gained popularity due to their ability to make accurate predictions, reduce overshoot, and allow for rapid responses to changes in speed.