Reinforcement learning of ball screw feed drive controllers

Feedback controllers for ball screw feed drives may provide great accuracy in positioning, but have no close analytical solution to derive the desired controller. Reinforcement Learning (RL) is proposed to provide autonomous adaptation and learning of them. The RL paradigm allows different approache...

Full description

Saved in:
Bibliographic Details
Published inEngineering applications of artificial intelligence Vol. 30; pp. 107 - 117
Main Authors Fernandez-Gauna, Borja, Ansoategui, Igor, Etxeberria-Agiriano, Ismael, Graña, Manuel
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.04.2014
Subjects
Algorithms
Ball screw feed drive
Ball screws
Controllers
Feedback control
Learning
Mathematical models
Proportional integral derivative
Reinforcement
Reinforcement learning
Searching
Ball screw feed drive
Reinforcement learning
Feedback control
Online AccessGet full text

Cover

More Information
Summary:Feedback controllers for ball screw feed drives may provide great accuracy in positioning, but have no close analytical solution to derive the desired controller. Reinforcement Learning (RL) is proposed to provide autonomous adaptation and learning of them. The RL paradigm allows different approaches, which are tested in this paper looking for the best suited for the ball screw drivers. Specifically, five algorithms are compared on an accurate simulation model of a commercial device, with and without a noisy disturbance on the state observation values. Benchmark results are provided by a double-loop PID controller, whose parameters have been tuned by a random search optimization. Action-critic methods with continuous action space (Policy-Gradient and CACLA) outperform the PID controller in the computational experiments, encouraging future research.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0952-1976
1873-6769
DOI:10.1016/j.engappai.2014.01.015