Feedback Control of an Inverted Pendulum by Use of Artificial Intelligence

Webjørn Rekdalsbakken

doi:10.20965/jaciii.2007.p1114

single-jc.php

« previous

JACIII Vol.11 No.9 pp. 1114-1121

doi: 10.20965/jaciii.2007.p1114

(2007)

Paper:

Views over last 60 days: 392

Feedback Control of an Inverted Pendulum by Use of Artificial Intelligence

Webjørn Rekdalsbakken

Institute of Technology and Nautical Science, Aalesund University College, N-6025 Aalesund, Norway

Received:

February 21, 2007

Accepted:

June 14, 2007

Published:

November 20, 2007

Keywords:

Hybrid Artificial Intelligence (AI) controller, Neural Network (NN), Genetic Algorithm (GA), flexible inverted pendulum

Abstract

An inverted pendulum represents an unstable system which is excellent for demonstrating the use of feedback control with different kinds of control strategies. In this work feedback control of the inverted pendulum is examined from the point of view of a state space model of the system. First a pole placement algorithm is thoroughly explored. After this artificial intelligence (AI) methods are investigated to better cope with the nonlinearities of the physical model. The technique used is based on a hybrid system combining a Neural Network (NN) with a Genetic Algorithm (GA). The NN controller is trained by the GA against the behaviour of the physical model. The results of the training process show that the chromosome population tends to stabilize at a suboptimal level, and that changes in the environmental parameters have to take place to reach a new optimal level. The results, however, show that the NN controller gradually adapts to the behaviour of the pendulum.

Cite this article as:

W. Rekdalsbakken, “Feedback Control of an Inverted Pendulum by Use of Artificial Intelligence,” J. Adv. Comput. Intell. Intell. Inform., Vol.11 No.9, pp. 1114-1121, 2007.

Data files:

References

[1] Ø. Undertun and V. Øverås, “Feedback Control of an Inverted Pendulum,” B.Sc. thesis at AUC, 2003.
[2] I. M. Salen and T. A. Voldsund, “Design of a Self-learning Control System for an Inverted Pendulum,” B.Sc. thesis at AUC, 2005.
[3] K. Ogata, “Designing Linear Control Systems with MATLAB,” Matlab Curriculum Series, Prentice Hall, 1994.
[4] W. Rekdalsbakken, “Design and Application of a Motion Platform in Three Degrees of Freedom,” Proc. of SIMS 2005, the 46th Conference on Simulation and Modelling, pp. 269-279, Tapir Academic Press, No-7005, Trondheim.
[5] M. Negnevitsky, “Artificial Intelligence,” Pearson Education Limited, Addison-Wesley, 2002.
[6] The MathWorks, “Neural Network Toolbox,” Matlab Version 7.0.1.24704 (R14) Service pack 1, September 2004.
[7] The MathWorks, “Genetic Algorithm and Direct search Toolbox,” Matlab Version 7.0.1.24704 (R14) Service pack 1, September 2004.

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

[1] [1] Ø. Undertun and V. Øverås, “Feedback Control of an Inverted Pendulum,” B.Sc. thesis at AUC, 2003.

[2] [2] I. M. Salen and T. A. Voldsund, “Design of a Self-learning Control System for an Inverted Pendulum,” B.Sc. thesis at AUC, 2005.

[3] [3] K. Ogata, “Designing Linear Control Systems with MATLAB,” Matlab Curriculum Series, Prentice Hall, 1994.

[4] [4] W. Rekdalsbakken, “Design and Application of a Motion Platform in Three Degrees of Freedom,” Proc. of SIMS 2005, the 46th Conference on Simulation and Modelling, pp. 269-279, Tapir Academic Press, No-7005, Trondheim.

[5] [5] M. Negnevitsky, “Artificial Intelligence,” Pearson Education Limited, Addison-Wesley, 2002.

[6] [6] The MathWorks, “Neural Network Toolbox,” Matlab Version 7.0.1.24704 (R14) Service pack 1, September 2004.

[7] [7] The MathWorks, “Genetic Algorithm and Direct search Toolbox,” Matlab Version 7.0.1.24704 (R14) Service pack 1, September 2004.