Neural Network Based Model Predictive Control. Piche, S., Keeler, J., Martin, G., Boe, G., Johnson, D., & Gerules, M. In Advances in Neural Information Processing Systems, volume 12, 1999. MIT Press. Paper abstract bibtex Model Predictive Control (MPC), a control algorithm which uses an optimizer to solve for the optimal control moves over a future time horizon based upon a model of the process, has become a stan(cid:173) dard control technique in the process industries over the past two decades. In most industrial applications, a linear dynamic model developed using empirical data is used even though the process it(cid:173) self is often nonlinear. Linear models have been used because of the difficulty in developing a generic nonlinear model from empirical data and the computational expense often involved in using non(cid:173) linear models. In this paper, we present a generic neural network based technique for developing nonlinear dynamic models from em(cid:173) pirical data and show that these models can be efficiently used in a model predictive control framework. This nonlinear MPC based approach has been successfully implemented in a number of indus(cid:173) trial applications in the refining, petrochemical, paper and food industries. Performance of the controller on a nonlinear industrial process, a polyethylene reactor, is presented.
@inproceedings{piche_neural_1999,
title = {Neural {Network} {Based} {Model} {Predictive} {Control}},
volume = {12},
url = {https://proceedings.neurips.cc/paper/1999/hash/db957c626a8cd7a27231adfbf51e20eb-Abstract.html},
abstract = {Model Predictive Control (MPC), a control algorithm which uses an optimizer to solve for the optimal control moves over a future time horizon based upon a model of the process, has become a stan(cid:173) dard control technique in the process industries over the past two decades. In most industrial applications, a linear dynamic model developed using empirical data is used even though the process it(cid:173) self is often nonlinear. Linear models have been used because of the difficulty in developing a generic nonlinear model from empirical data and the computational expense often involved in using non(cid:173) linear models. In this paper, we present a generic neural network based technique for developing nonlinear dynamic models from em(cid:173) pirical data and show that these models can be efficiently used in a model predictive control framework. This nonlinear MPC based approach has been successfully implemented in a number of indus(cid:173) trial applications in the refining, petrochemical, paper and food industries. Performance of the controller on a nonlinear industrial process, a polyethylene reactor, is presented.},
urldate = {2022-09-01},
booktitle = {Advances in {Neural} {Information} {Processing} {Systems}},
publisher = {MIT Press},
author = {Piche, Stephen and Keeler, James and Martin, Greg and Boe, Gene and Johnson, Doug and Gerules, Mark},
year = {1999},
keywords = {/unread, ⛔ No DOI found},
}
Downloads: 0
{"_id":"ahro2sEs23CrbAbkk","bibbaseid":"piche-keeler-martin-boe-johnson-gerules-neuralnetworkbasedmodelpredictivecontrol-1999","author_short":["Piche, S.","Keeler, J.","Martin, G.","Boe, G.","Johnson, D.","Gerules, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Neural Network Based Model Predictive Control","volume":"12","url":"https://proceedings.neurips.cc/paper/1999/hash/db957c626a8cd7a27231adfbf51e20eb-Abstract.html","abstract":"Model Predictive Control (MPC), a control algorithm which uses an optimizer to solve for the optimal control moves over a future time horizon based upon a model of the process, has become a stan(cid:173) dard control technique in the process industries over the past two decades. In most industrial applications, a linear dynamic model developed using empirical data is used even though the process it(cid:173) self is often nonlinear. Linear models have been used because of the difficulty in developing a generic nonlinear model from empirical data and the computational expense often involved in using non(cid:173) linear models. In this paper, we present a generic neural network based technique for developing nonlinear dynamic models from em(cid:173) pirical data and show that these models can be efficiently used in a model predictive control framework. This nonlinear MPC based approach has been successfully implemented in a number of indus(cid:173) trial applications in the refining, petrochemical, paper and food industries. Performance of the controller on a nonlinear industrial process, a polyethylene reactor, is presented.","urldate":"2022-09-01","booktitle":"Advances in Neural Information Processing Systems","publisher":"MIT Press","author":[{"propositions":[],"lastnames":["Piche"],"firstnames":["Stephen"],"suffixes":[]},{"propositions":[],"lastnames":["Keeler"],"firstnames":["James"],"suffixes":[]},{"propositions":[],"lastnames":["Martin"],"firstnames":["Greg"],"suffixes":[]},{"propositions":[],"lastnames":["Boe"],"firstnames":["Gene"],"suffixes":[]},{"propositions":[],"lastnames":["Johnson"],"firstnames":["Doug"],"suffixes":[]},{"propositions":[],"lastnames":["Gerules"],"firstnames":["Mark"],"suffixes":[]}],"year":"1999","keywords":"/unread, ⛔ No DOI found","bibtex":"@inproceedings{piche_neural_1999,\n\ttitle = {Neural {Network} {Based} {Model} {Predictive} {Control}},\n\tvolume = {12},\n\turl = {https://proceedings.neurips.cc/paper/1999/hash/db957c626a8cd7a27231adfbf51e20eb-Abstract.html},\n\tabstract = {Model Predictive Control (MPC), a control algorithm which uses an optimizer to solve for the optimal control moves over a future time horizon based upon a model of the process, has become a stan(cid:173) dard control technique in the process industries over the past two decades. In most industrial applications, a linear dynamic model developed using empirical data is used even though the process it(cid:173) self is often nonlinear. Linear models have been used because of the difficulty in developing a generic nonlinear model from empirical data and the computational expense often involved in using non(cid:173) linear models. In this paper, we present a generic neural network based technique for developing nonlinear dynamic models from em(cid:173) pirical data and show that these models can be efficiently used in a model predictive control framework. This nonlinear MPC based approach has been successfully implemented in a number of indus(cid:173) trial applications in the refining, petrochemical, paper and food industries. Performance of the controller on a nonlinear industrial process, a polyethylene reactor, is presented.},\n\turldate = {2022-09-01},\n\tbooktitle = {Advances in {Neural} {Information} {Processing} {Systems}},\n\tpublisher = {MIT Press},\n\tauthor = {Piche, Stephen and Keeler, James and Martin, Greg and Boe, Gene and Johnson, Doug and Gerules, Mark},\n\tyear = {1999},\n\tkeywords = {/unread, ⛔ No DOI found},\n}\n\n","author_short":["Piche, S.","Keeler, J.","Martin, G.","Boe, G.","Johnson, D.","Gerules, M."],"key":"piche_neural_1999","id":"piche_neural_1999","bibbaseid":"piche-keeler-martin-boe-johnson-gerules-neuralnetworkbasedmodelpredictivecontrol-1999","role":"author","urls":{"Paper":"https://proceedings.neurips.cc/paper/1999/hash/db957c626a8cd7a27231adfbf51e20eb-Abstract.html"},"keyword":["/unread","⛔ No DOI found"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/victorjhu","dataSources":["CmHEoydhafhbkXXt5"],"keywords":["/unread","⛔ no doi found"],"search_terms":["neural","network","based","model","predictive","control","piche","keeler","martin","boe","johnson","gerules"],"title":"Neural Network Based Model Predictive Control","year":1999}