This paper proposes a double-loop control structure based on fuzzy integral and neuron proportional integral (FI-NPI) for improving the performance of brushless DC (BLDC) servo control in parallel platform systems. The traditional PI control method, while robust, has limitations in parameter tuning and optimal control performance. The FI-NPI controller combines fuzzy control and integrator advantages to enhance speed loop control, and uses neuron supervised learning to improve current loop control. The speed error is used as a teacher signal for the neuron to adjust PI parameters, enhancing dynamic response and control accuracy. Simulation and experimental results show that the FI-NPI controller has a faster dynamic response and better performance in convergence rate and RMSE compared to the traditional dual-PI controller. The controller was implemented in C language on the servo-driven lower computer, and tested under no-load and load conditions. The results demonstrate that the FI-NPI double-loop controller outperforms the dual-PI controller in performance indicators, confirming its superiority in BLDC servo control. The FI-NPI controller is more suitable for BLDC servo control due to its adaptability to load changes and improved control accuracy. Future research will focus on expanding the application of the FI-NPI controller in complex robotic systems and optimizing the fuzzy controller design. The study provides a new and effective method for BLDC motor double-loop control, with experimental verification of its performance superiority.This paper proposes a double-loop control structure based on fuzzy integral and neuron proportional integral (FI-NPI) for improving the performance of brushless DC (BLDC) servo control in parallel platform systems. The traditional PI control method, while robust, has limitations in parameter tuning and optimal control performance. The FI-NPI controller combines fuzzy control and integrator advantages to enhance speed loop control, and uses neuron supervised learning to improve current loop control. The speed error is used as a teacher signal for the neuron to adjust PI parameters, enhancing dynamic response and control accuracy. Simulation and experimental results show that the FI-NPI controller has a faster dynamic response and better performance in convergence rate and RMSE compared to the traditional dual-PI controller. The controller was implemented in C language on the servo-driven lower computer, and tested under no-load and load conditions. The results demonstrate that the FI-NPI double-loop controller outperforms the dual-PI controller in performance indicators, confirming its superiority in BLDC servo control. The FI-NPI controller is more suitable for BLDC servo control due to its adaptability to load changes and improved control accuracy. Future research will focus on expanding the application of the FI-NPI controller in complex robotic systems and optimizing the fuzzy controller design. The study provides a new and effective method for BLDC motor double-loop control, with experimental verification of its performance superiority.