Abstract

This study shows the latest advances in the application of intelligent control to the inverted-pendulum problem. A complete review regarding intelligent control design is presented in this study in order to show the most important artificial intelligence methods used for controlling an Inverted-Pendulum. Also this study proposed the use of a neural-fuzzy-with-genetic-algorithms controller for the inverted pendulum problem which gives good results. Conventional controllers are presented in order to observe implementation problems. The study goes deeply in the details that have to take into account in order to understand design problems and limitations.

Highlights

  • Nørgaard, 2000a; 2000b; Omatu et al, 1995; Storn and Price, 1997; Mirza and Hussain, 2000; Messner andThe inverted pendulum is a classical example of an instable, nonlinear system that has been solved in many ways but remain a prototypical case study for optimization and the testing of new control techniques

  • This study shows the latest advances in the application of intelligent control to the inverted-pendulum problem

  • One can infer that the ANFIS controller is capable of controlling the system, but more training in the stabilization zone is required

Read more

Summary

INTRODUCTION

2000a; 2000b; Omatu et al, 1995; Storn and Price, 1997; Mirza and Hussain, 2000; Messner and. The control objective is to keep the bar on balance, beginning from nonzero initial conditions, in such a way that the bar remains oriented upwards despite possible perturbations and the system’s intrinsic unstability (Jang, 1992; Lundeberg, 1994; Williams and Matsuoka, 1991; Where: θ = The angle that the bar makes with the vertical (or horizontal) axis θ& = The angular speed of the bar x = The position of the car relative to the tracks and x&& = The linear speed of the car Jacobs and Jordan, 1993; Kitamulra and Saitoh, 1990; Kouda et al, 2002; Sazonov et al, 2003; Mohanlal and Kaimal, 2002; Inoue et al, 2002; Harrison, 2003; Chen and Chen, 2003; Pal and Pal, 2003; Lam et al, 2003; Cho and Jung, 2003; Gao and Er, 2003; Olguín, 2000; Jang, 1992; Ji et al, 1997; DECE, 2003; Omatu and Ide, 1994; As mentioned before, the control objective is to set the car in its central position (x = 0) in such a way that the pendulum remains in its vertical position, with its bob pointing upwards. Pedro Ponce et al / American Journal of Engineering and Applied Sciences 7 (2): 194-240, 2014

Moment of inertia of the pendulum
SYSTEM MODEL
PID Controller
FUZZY LOGIC CONTROLLER
ANFIS CONTROLLER
Sub-Clustering
Grid Partition
Control with 8-Input Time-Sequence State Training
Control with 4-Input State Training
Continuous With Few Training Data
ANFIS CONTROLLER OPTIMIZED BY GENETIC ALGORITHMS
It is Obtained
6.10. It is Obtained
CONTRIBUTIONS TO THE STATE OF THE ART
CONCLUSION
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.