Research on PID Parameter Self-Tuning Speed Control System Based on Grasshopper Optimazation Algorithm-Optimized BP Neural Network

In response to the limitations associated with conventional PID control strategies, which rely heavily on predetermined design parameters and struggle to provide precise, stable motor speed and current control, particularly in the presence of disturbances, we have developed a novel double closed-loop DC speed regulation system. This system incorporates a self-tuning PID mechanism based on the Grasshopper algorithm optimization neural network. To achieve this, we employed a Back-Propagation (BP) neural network to autonomously fine-tune the parameters of the PID control strategy. Subsequently, during the backpropagation phase of the neural network training, we harnessed the Grasshopper algorithm to optimize these parameters based on a fitness function, leading to the calculation of updated weighting coefficients. Following this iterative process, the output voltage was computed using the incremental PID formula, enabling precise motor control. Remarkably, this approach reduced overshoot by 30%, all without the need for preemptive control parameter adjustments. Moreover, the rise time experienced only a marginal increase of approximately 0.06 seconds. These advancements effectively address the limitations associated with traditional PID control strategies, expanding their utility beyond narrow operational ranges and enhancing performance in complex working conditions. The outcome is a speed regulation system characterized by significantly improved accuracy and robustness, ideally suited to meet the demanding requirements of engineering applications.