scholarly journals Neural Network Supervision Control Strategy for Inverted Pendulum Tracking Control

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Hongliang Gao ◽  
Xiaoling Li ◽  
Chao Gao ◽  
Jie Wu
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Tracking Control ◽  
Pid Controller ◽  
Inverted Pendulum ◽  
Control Method ◽  
Rbf Neural Network ◽  
Pendulum System ◽  
Inverted Pendulum System ◽  
Tracking Signal

This paper presents several control methods and realizes the stable tracking for the inverted pendulum system. Based on the advantages of RBF and traditional PID, a novel PID controller based on the RBF neural network supervision control method (PID-RBF) is proposed. This method realizes the adaptive adjustment of the stable tracking signal of the system. Furthermore, an improved PID controller based on RBF neural network supervision control strategy (IPID-RBF) is presented. This control strategy adopts the supervision control method of feed-forward and feedback. The response speed of the system is further improved, and the overshoot of the tracking signal is further reduced. The tracking control simulation of the inverted pendulum system under three different signals is given to illustrate the effectiveness of the proposed method.

The Application of PID Based on Optimized RBF in Thickness Control of Strip Steel

2012 ◽  
Vol 466-467 ◽  
pp. 52-56
Author(s):  
Yu Zhen Yu ◽  
Xin Yi Ren ◽  
Chun Yan Deng ◽  
Xiao Hui Wang
Keyword(s):  
Neural Network ◽  
Control System ◽  
Control Strategy ◽  
Pid Controller ◽  
Control Method ◽  
Rbf Neural Network ◽  
Pso Algorithm ◽  
Strip Thickness ◽  
Control Effect ◽  
Thickness Control

The strip thickness control system is difficult to establish an accurate mathematical model, and traditional PID control strategy has a poor adaptive ability, so the effect of control is always not satisfying. According to the problems above, a new control strategy of self-tuning PID controller based on RBF neural network whose parameters are optimized by PSO algorithm is proposed in the paper. The control method integrates advantages of RBF neural network as well as PID controller and good global search capability of PSO algorithm. The simulation results indicate that the method not only improves control performance and dynamic quality, but also has strong self-adapting ability and robustness. It achieved a very good control effect when used in strip thickness control system that proved the correctness and effectiveness of the control method.

Adaptive Neural Network Fuzzy Control Plane Double Inverted Pendulum

2013 ◽  
Vol 765-767 ◽  
pp. 2004-2007
Author(s):  
Su Ying Zhang ◽  
Ying Wang ◽  
Jie Liu ◽  
Xiao Xue Zhao
Keyword(s):  
Neural Network ◽  
Fuzzy Control ◽  
Control Theory ◽  
Inverted Pendulum ◽  
Learning Ability ◽  
Adaptive Neural Network ◽  
Pendulum System ◽  
Inverted Pendulum System ◽  
Self Learning ◽  
Controlled Object

Double inverted pendulum system is nonlinear and unstable. Fuzzy control uses some expert's experience knowledge and learns approximate reasoning algorithm. For it does not depend on the mathematical model of controlled object, it has been widely used for years. In practical engineering applications, most systems are nonlinear time-varying parameter systems. As the fuzzy control theory lacks of on-line self-learning and adaptive ability, it can not control the controlled object effectively. In order to compensate for these defects, it introduced adaptive, self-organizing, self-learning functions of neural network algorithm. We called it adaptive neural network fuzzy inference system (ANFIS). ANFIS not only takes advantage of the fuzzy control theory of abstract ability, the nonlinear processing ability, but also makes use of the autonomous learning ability of neural network, the arbitrary function approximation ability. The controller was applied to double inverted pendulum system and the simulation results showed that this method can effectively control the double inverted pendulum system.

Nonlinear Optimal Control for the Wheeled Inverted Pendulum System

Robotica ◽  
2019 ◽  
Vol 38 (1) ◽  
pp. 29-47 ◽  
Author(s):  
G. Rigatos ◽  
K. Busawon ◽  
J. Pomares ◽  
M. Abbaszadeh
Keyword(s):  
Optimal Control ◽  
Inverted Pendulum ◽  
Control Method ◽  
Taylor Series Expansion ◽  
Nonlinear Optimal Control ◽  
Algebraic Riccati Equation ◽  
Time Step ◽  
Pendulum System ◽  
Inverted Pendulum System ◽  
Wheeled Inverted Pendulum

SummaryThe article proposes a nonlinear optimal control method for the model of the wheeled inverted pendulum (WIP). This is a difficult control and robotics problem due to the system’s strong nonlinearities and due to its underactuation. First, the dynamic model of the WIP undergoes approximate linearization around a temporary operating point which is recomputed at each time step of the control method. The linearization procedure makes use of Taylor series expansion and of the computation of the associated Jacobian matrices. For the linearized model of the wheeled pendulum, an optimal (H-infinity) feedback controller is developed. The controller’s gain is computed through the repetitive solution of an algebraic Riccati equation at each iteration of the control algorithm. The global asymptotic stability properties of the control method are proven through Lyapunov analysis. Finally, by using the H-infinity Kalman Filter as a robust state estimator, the implementation of a state estimation-based control scheme becomes also possible.

Neural Network Trajectory Tracking Control of Compliant Parallel Robot

2015 ◽  
Vol 799-800 ◽  
pp. 1069-1073
Author(s):  
Hao Tian ◽  
Yue Qing Yu
Keyword(s):  
Neural Network ◽  
Trajectory Tracking ◽  
Tracking Control ◽  
Control Method ◽  
Rbf Neural Network ◽  
Control Strategies ◽  
Parallel Robot ◽  
Network Control ◽  
Trajectory Tracking Control ◽  
Compliant Joint

Trajectory tracking control of compliant parallel robot is presented. According to the characteristics of compliant joint, the system model is derived and the dynamic equation is obtained based on the Lagrange method. Radial Basis Function (RBF) neural network control is designed to globally approximate the model uncertainties. Further, an itemized approximate RBF control method is proposed for higher identify precision. The trajectory tracking abilities of two control strategies are compared through simulation.

scholarly journals Model Free Adaptive Control of Switched Reluctance Motor for Electric Vehicle

2021 ◽  
pp. 104-114
Author(s):  
Xifeng Mi , Yuanyuan Fan
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Control Method ◽  
Rbf Neural Network ◽  
Switched Reluctance Motor ◽  
Torque Ripple ◽  
Torque Distribution ◽  
Switched Reluctance ◽  
Model Free ◽  
Reluctance Motor

In this paper, the model free adaptive control method of switched reluctance motor for electric vehicle is studied. Based on the torque distribution control of SRM, a SRM control strategy based on torque current hybrid model based on RBF neural network is proposed in this paper. Based on the deviation between the dynamic average value and instantaneous value of SRM output torque, the online learning of RBF neural network is realized. At the same time, this paper constructs a torque current hybrid model, obtains the current variation law of SRM under low torque ripple operation, and reduces the torque ripple of SRM. The SRM torque distribution control is realized on the SRM experimental platform. Compared with the voltage chopper control method, the experimental results show that the torque ripple of SRM can be reduced by adopting the torque distribution control strategy.

Sign in / Sign up

Export Citation Format

Share Document