Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Reinforcement Learning in Industrial Applications

Kotarsky, Niklas and Bergvall, Eric (2020)
Department of Automatic Control
Abstract
Although reinforcement learning has gained great success in computer games, there are only few yet known implementations in ndustrial applications. This despite the fact that reinforcement learning offers interesting methods to optimise the control of nonlinear processes. In this thesis we have used two model free reinforcement learning algorithms (PPO and DDPG) to control three different simulations of industrial processes, the simplified Tennessee Eastman, original Tennessee Eastman and the Haldex brake valve. Both reinforcement learning algorithms could in almost all cases learn to reach a set point. In addition, hyperparameters were found to have a high impact on training performance. In conclusion, our tests indicate that the model... (More)
Although reinforcement learning has gained great success in computer games, there are only few yet known implementations in ndustrial applications. This despite the fact that reinforcement learning offers interesting methods to optimise the control of nonlinear processes. In this thesis we have used two model free reinforcement learning algorithms (PPO and DDPG) to control three different simulations of industrial processes, the simplified Tennessee Eastman, original Tennessee Eastman and the Haldex brake valve. Both reinforcement learning algorithms could in almost all cases learn to reach a set point. In addition, hyperparameters were found to have a high impact on training performance. In conclusion, our tests indicate that the model free reinforcement learning algorithms are basically capable of controlling industrial processes. Python code for the PPO algorithm applied to the Original
Tennesse Eastman process can be found at Github. 1
1 https://github.com/Heigke/Reinforcement-Learning-In-Industrial-Applications (Less)
Please use this url to cite or link to this publication:
author
Kotarsky, Niklas and Bergvall, Eric
supervisor
organization
year
type
H3 - Professional qualifications (4 Years - )
subject
report number
TFRT-6111
other publication id
0280-5316
language
English
id
9033163
date added to LUP
2020-12-23 11:18:29
date last changed
2020-12-23 11:18:29
@misc{9033163,
  abstract     = {{Although reinforcement learning has gained great success in computer games, there are only few yet known implementations in ndustrial applications. This despite the fact that reinforcement learning offers interesting methods to optimise the control of nonlinear processes. In this thesis we have used two model free reinforcement learning algorithms (PPO and DDPG) to control three different simulations of industrial processes, the simplified Tennessee Eastman, original Tennessee Eastman and the Haldex brake valve. Both reinforcement learning algorithms could in almost all cases learn to reach a set point. In addition, hyperparameters were found to have a high impact on training performance. In conclusion, our tests indicate that the model free reinforcement learning algorithms are basically capable of controlling industrial processes. Python code for the PPO algorithm applied to the Original
Tennesse Eastman process can be found at Github. 1
1 https://github.com/Heigke/Reinforcement-Learning-In-Industrial-Applications}},
  author       = {{Kotarsky, Niklas and Bergvall, Eric}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Reinforcement Learning in Industrial Applications}},
  year         = {{2020}},
}