Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Philip D Loewen"'
Autor:
Qiugang Lu, Guy A. Dumont, R. Bhushan Gopaluni, Philip D. Loewen, Johan U. Backstrom, Michael G. Forbes
Publikováno v:
ISA Transactions. 117:150-159
This paper presents a two-component framework to detect model-plant mismatch (MPM) in cross-directional (CD) processes on paper machines under model-predictive control. First, routine operating data is used for system identification in closed loop; s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::07784e200b0a7ffa90b61f885f39a7c3
https://doi.org/10.1016/j.isatra.2021.01.051
https://doi.org/10.1016/j.isatra.2021.01.051
Autor:
Carl Sheehan, Philip D. Loewen, Travis Reinheimer, Barry Hirtz, Lee D. Rippon, Bhushan Gopaluni
Publikováno v:
Nordic Pulp & Paper Research Journal. 36:549-558
Rotary kilns are large-scale unit operations that are critical to many industrial processes such as cement production, pyrometallurgy, and kraft pulping. As expensive, energy-intensive units, it is imperative from both an economic and environmental p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cdb05eba11afdd8c9164cb0268b90f22
https://doi.org/10.1515/npprj-2021-0048
https://doi.org/10.1515/npprj-2021-0048
Autor:
Johan U. Backstrom, Michael G. Forbes, Philip D. Loewen, R. Bhushan Gopaluni, Gregory E. Stewart, Nathan P. Lawrence
Publikováno v:
IFAC-PapersOnLine. 53:230-235
Reinforcement learning has been successfully applied to the problem of tuning PID controllers in several applications. The existing methods often utilize function approximation, such as neural networks, to update the controller parameters at each tim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c00fc30abc6eeb9da65c47a9c943ff8
https://doi.org/10.1016/j.ifacol.2020.12.127
https://doi.org/10.1016/j.ifacol.2020.12.127
Publikováno v:
Systems modelling and optimization ISBN: 9780203737422
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dcf4eebb6c29ed6273dbeed77e6a54c0
https://doi.org/10.1201/9780203737422-16
https://doi.org/10.1201/9780203737422-16
Autor:
Daniel G. McClement, Nathan P. Lawrence, Johan U. Backström, Philip D. Loewen, Michael G. Forbes, R. Bhushan Gopaluni
Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. In process control, many systems have similar and well-understood dynamics, which suggests i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b6c8b8b5bd378f9a712531b681d766a
Autor:
Nathan P. Lawrence, Michael G. Forbes, Philip D. Loewen, Daniel G. McClement, Johan U. Backström, R. Bhushan Gopaluni
Deep reinforcement learning (RL) is an optimization-driven framework for producing control strategies for general dynamical systems without explicit reliance on process models. Good results have been reported in simulation. Here we demonstrate the ch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cef5d4e9d09804104c7d5b9ceced16f9
http://arxiv.org/abs/2111.07171
http://arxiv.org/abs/2111.07171
Autor:
Johan U. Backstrom, Michael G. Forbes, Guy A. Dumont, R. Bhushan Gopaluni, M.S. Davies, Philip D. Loewen, Qiugang Lu
Publikováno v:
Automatica. 103:515-530
We propose a maximum likelihood estimation approach for the identification of symmetric noncausal models. Such models are used to represent the cross-directional dynamic response of many industrial processes that are generally modeled with a high-dim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a7c315d703e28dc9e75e8880edf34785
https://doi.org/10.1016/j.automatica.2019.01.035
https://doi.org/10.1016/j.automatica.2019.01.035
Autor:
R. Bhushan Gopaluni, Philip D. Loewen, Johan U. Backstrom, Michael G. Forbes, Qiugang Lu, Lee D. Rippon
Publikováno v:
Industrial & Engineering Chemistry Research. 58:11452-11473
Control of industrial sheet and film processes involves separate controllers and actuators for minimizing both temporal variations along the machine direction (MD) and spatial variations along the cross direction (CD). Model-based control methods suc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d8e0d636117ed51c6e1ba63ddf14e880
https://doi.org/10.1021/acs.iecr.8b06067
https://doi.org/10.1021/acs.iecr.8b06067
Autor:
R. Bhushan Gopaluni, Johan U. Backstrom, Michael G. Forbes, Philip D. Loewen, Nathan P. Lawrence, Daniel G. McClement
Meta-learning is a branch of machine learning which aims to quickly adapt models, such as neural networks, to perform new tasks by learning an underlying structure across related tasks. In essence, models are being trained to learn new tasks effectiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f7a791f6ded4e09a8a36bdf2bea313b1
http://arxiv.org/abs/2103.14060
http://arxiv.org/abs/2103.14060
Autor:
R. Bhushan Gopaluni, Philip D. Loewen, Gregory E. Stewart, Johan U. Backstrom, Nathan P. Lawrence, Michael G. Forbes
Deep reinforcement learning (DRL) has seen several successful applications to process control. Common methods rely on a deep neural network structure to model the controller or process. With increasingly complicated control structures, the closed-loo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee4c48efbb3d2b2c5161154a6cae0291
http://arxiv.org/abs/2005.04539
http://arxiv.org/abs/2005.04539