Real-time control of an inverted pendulum system using complementary neural network and optimal techniques

2005 ◽  
Author(s):  
J. Nelson ◽  
L.G. Kraft
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Inverted Pendulum ◽  
Real Time Control ◽  
Pendulum System ◽  
Time Control ◽  
Inverted Pendulum System

Experiment Platform Design cSPACE-Based for a Permanent Magnet Linear Synchronous Motor Driven Inverted Pendulum

2011 ◽  
Vol 84-85 ◽  
pp. 452-456 ◽  
Author(s):  
Rong Min Cao ◽  
Hui Xing Zhou ◽  
Rong Hua Ma
Keyword(s):  
Permanent Magnet ◽  
Real Time ◽  
Inverted Pendulum ◽  
Synchronous Motor ◽  
Linear Motor ◽  
Real Time Control ◽  
Pendulum System ◽  
Experiment Platform ◽  
Inverted Pendulum System ◽  
Linear Synchronous Motor

Permanent magnet linear synchronous motor (PMLSM) driven inverted pendulum is a new member of present similar devices, various unexpected disturbances such as lag effect of a belt attached to a cart and errors caused by a rotary encoder while detecting the position of a cart can be eliminated or reduced to a small range.In this paper, ironless permanent magnet synchronous linear motor driven inverted pendulum experiment platform is developed. The plant is hardware in the loop real time simulation control development system (Hardware-in-Loop, HIL)based on TMS320F2812DSP and MATLAB, it can use simple and efficient way to achieve linear motor driven inverted pendulum real-time control. Long design time for programming and debugging difficulty are avoided for traditional programming language. Control algorithm can be investigated directly on MATLAB/Simulink, and can be generated automatically control code to control single and double -stage inverted pendulum system. The real performance of the driven inverted pendulum is researched in this paper, the results showed that the controllability of the driven inverted pendulum is fine.

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.

Real-time control and application with self-tuning PID-type fuzzy adaptive controller of an inverted pendulum

2019 ◽  
Vol 46 (1) ◽  
pp. 159-170 ◽  
Author(s):  
Tayfun Abut ◽  
Servet Soyguder
Keyword(s):  
Real Time ◽  
Inverted Pendulum ◽  
Adaptive Controller ◽  
Performance Criteria ◽  
Real Time Control ◽  
Content Type ◽  
Time Control ◽  
Self Tuning ◽  
Fuzzy Adaptive Controller ◽  
Fuzzy Adaptive

PurposeThis paper aims to keep the pendulum on the linear moving car vertically balanced and to bring the car to the equilibrium position with the designed controllers.Design/methodology/approachAs inverted pendulum systems are structurally unstable and nonlinear dynamic systems, they are important mechanisms used in engineering and technological developments to apply control techniques on these systems and to develop control algorithms, thus ensuring that the controllers designed for real-time balancing of these systems have certain performance criteria and the selection of each controller method according to performance criteria in the presence of destructive effects is very helpful in getting information about applying the methods to other systems.FindingsAs a result, the designed controllers are implemented on a real-time and real system, and the performance results of the system are obtained graphically, compared and analyzed.Originality/valueIn this study, motion equations of a linear inverted pendulum system are obtained, and classical and artificial intelligence adaptive control algorithms are designed and implemented for real-time control. Classic proportional-integral-derivative (PID) controller, fuzzy logic controller and PID-type Fuzzy adaptive controller methods are used to control the system. Self-tuning PID-type fuzzy adaptive controller was used first in the literature search and success results have been obtained. In this regard, the authors have the idea that this work is an innovative aspect of real-time with self-tuning PID-type fuzzy adaptive controller.

The Design of Real-Time Control System Based on Single-Inverted Pendulum

2013 ◽  
Vol 850-851 ◽  
pp. 553-556
Author(s):  
Qun Yong Ou
Keyword(s):  
Control System ◽  
Control Problem ◽  
Real Time ◽  
Linear Model ◽  
Inverted Pendulum ◽  
Control Algorithms ◽  
Control Board ◽  
Real Time Control ◽  
Control Software ◽  
Time Control

An inverted pendulum is a classic control problem and is widely used as a benchmark for testing various control algorithms. First, this paper analyse the dynamic and non-linear model of the inverted pendulum, then focus on the real-time control of the inverted pendulum, we developed real-time control software for the single-stage inverted pendulum by using Visual C++ 2010, its mainly operate API functions to control board and implement various control algorithms.

Sign in / Sign up

Export Citation Format

Share Document