No abstract

Currently, the proportional integral derivative (PID) control algorithm is most commonly used in the field of industrial control. People are not satisfied with the existing basic theory of control theory and have started to integrate it with other disciplines. Therefore, most scholars combine control theory with a neural network, which is the product of integrating biology and computer by forming a new control theory. Similar to the above, this research work combines the neural BP network with a PID controller by making the PID control parameters of electrical equipment of rural electric drainage and irrigation stations in the experimental environment. This work first briefly introduces the structure and principle of the PID controller. After that, it analyzes the incremental PID by introducing the Z-N method of rectifying PID parameters. Finally, it selects the neural network implicit layer, activation function, network initial weights, and learning rate, and then it drives the BP neural network PID algorithm. The experiment demonstrates that the system employing the BP neural network speed PID regulator has low overshoot, quick dynamic response, high immunity, and fast regulation speed.

No abstract