Citation: Wang, J.; Li, M.; Jiang, W.;
Huang, Y.; Lin, R. A Design of
FPGA-Based Neural Network PID
Controller for Motion Control System.
Sensors 2022, 22, 889. https://
doi.org/10.3390/s22030889
Academic Editors: Yuansong Qiao
and Seamus Gordon
Received: 3 January 2022
Accepted: 20 January 2022
Published: 24 January 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Design of FPGA-Based Neural Network PID Controller for
Motion Control System
Jun Wang, Moudao Li, Weibin Jiang, Yanwei Huang * and Ruiquan Lin
College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350116, China;
wangjunfzu@fzu.edu.cn (J.W.); N190127108@fzu.edu.cn (M.L.); 210110008@fzu.edu.cn (W.J.); rqlin@fzu.edu.cn (R.L.)
* Correspondence: sjtu_huanghao@fzu.edu.cn
Abstract:
In the actual industrial production process, the method of adaptively tuning proportional–
integral–derivative (PID) parameters online by neural network can adapt to different characteristics
of different controlled objects better than the controller with PID. However, the commonly used
microcontroller unit (MCU) cannot meet the application scenarios of real time and high reliability.
Therefore, in this paper, a closed-loop motion control system based on BP neural network (BPNN)
PID controller by using a Xilinx field programmable gate array (FPGA) solution is proposed. In
the design of the controller, it is divided into several sub-modules according to the modular design
idea. The forward propagation module is used to complete the forward propagation operation from
the input layer to the output layer. The PID module implements the mapping of PID arithmetic to
register transfer level (RTL) and is responsible for completing the output of control amount. The
main state machine module generates enable signals that control the sequential execution of each
sub-module. The error backpropagation and weight update module completes the update of the
weights of each layer of the network. The peripheral modules of the control system are divided
into two main parts. The speed measurement module completes the acquisition of the output pulse
signal of the encoder and the measurement of the motor speed. The pulse width modulation (PWM)
signal generation module generates PWM waves with different duty cycles to control the rotation
speed of the motor. A co-simulation of Modelsim and Simulink is used to simulate and verify the
system, and a test analysis is also performed on the development platform. The results show that the
proposed system can realize the self-tuning of PID control parameters, and also has the characteristics
of reliable performance, high real-time performance, and strong anti-interference. Compared with
MCU, the convergence speed is far more than three orders of magnitude, which proves its superiority.
Keywords: BPNN; PID; adaptive control; PWM; co-simulation; speed measurement; DC motor; FPGA
1. Introduction
The PID control algorithm is widely used in practical engineering [
1
], but when facing
the nonlinear and time-varying characteristics of the controlled object, it has the problems of
tedious parameter adjustment and poor nonlinear adaptability. Therefore, the limitations of
conventional PID in engineering applications are becoming more and more
obvious [2–4]
.
The boom in artificial intelligence has led to an increasing focus on neural network control.
Neural network has the characteristics of self-learning, self-adaptive and good robustness,
etc. Combining PID controller with neural network can meet the actual demand for
response speed and stability in the control process. Therefore, it plays an increasingly
important role in the field of practical intelligent control [5–8].
The traditional method of implementing control algorithms in MCU has been suf-
fering from slow convergence and poor real-time performance. In [
9
], a DC motor speed
regulation system based on incremental PID algorithm is proposed with the microcontroller
AT89S52 as the control core to achieve stable speed regulation of the DC motor. In [
10
],
the parameters of the fuzzy controller are adjusted using a particle swarm optimization
Sensors 2022, 22, 889. https://doi.org/10.3390/s22030889 https://www.mdpi.com/journal/sensors
