This article presents a novel double-loop control structure called FI-NPI (Fuzzy Integral and Neuron Proportional Integral) for improving the performance of brushless DC (BLDC) motor servo control. The traditional PI control method, while robust, has limitations in parameter tuning and achieving optimal performance. The proposed FI-NPI controller combines fuzzy integral control and neuron proportional integral control to enhance the speed and current loop control performance. The fuzzy controller is used for speed loop control, while the neuron PI controller is used for current loop control. The speed error is used as a teacher signal for neuron supervised learning, improving the current loop control. The FI-NPI controller is implemented in C language in the servo-driven lower computer and tested on a BLDC motor. Simulation and experimental results show that the FI-NPI controller has a faster dynamic response speed and better performance in terms of convergence rate and RMSE compared to the traditional dual-PI controller. The controller is more suitable for BLDC servo control due to its improved adaptability to load changes and robustness. The study also discusses the design of the FI-NPI controller, the working principle of field-oriented control (FOC), and the simulation and experimental results. The results demonstrate the effectiveness of the FI-NPI controller in achieving accurate and stable BLDC motor control. The study concludes that the FI-NPI controller is a more advanced and suitable method for BLDC servo control.This article presents a novel double-loop control structure called FI-NPI (Fuzzy Integral and Neuron Proportional Integral) for improving the performance of brushless DC (BLDC) motor servo control. The traditional PI control method, while robust, has limitations in parameter tuning and achieving optimal performance. The proposed FI-NPI controller combines fuzzy integral control and neuron proportional integral control to enhance the speed and current loop control performance. The fuzzy controller is used for speed loop control, while the neuron PI controller is used for current loop control. The speed error is used as a teacher signal for neuron supervised learning, improving the current loop control. The FI-NPI controller is implemented in C language in the servo-driven lower computer and tested on a BLDC motor. Simulation and experimental results show that the FI-NPI controller has a faster dynamic response speed and better performance in terms of convergence rate and RMSE compared to the traditional dual-PI controller. The controller is more suitable for BLDC servo control due to its improved adaptability to load changes and robustness. The study also discusses the design of the FI-NPI controller, the working principle of field-oriented control (FOC), and the simulation and experimental results. The results demonstrate the effectiveness of the FI-NPI controller in achieving accurate and stable BLDC motor control. The study concludes that the FI-NPI controller is a more advanced and suitable method for BLDC servo control.