Broiler Growth Optimization using Norm Optimal Terminal Iterative Learning Control

Simon Vestergaard Johansen, Martin Rishøj Jensen, Bing Chu, Jan Dimon Bendtsen, Jesper Mogensen, Eric Rogers

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

Broiler (chicken for meat production) growth maximization reduces the amount of feed, water and electricity required to produce a mature broiler where temperature control is one of the most influential factors. Iterative learning control provides a potential solution given the repeated nature of the production process, as it has been especially developed for systems that make repeated executions of the same finite duration task. Dynamic neural network models are used given the absence of mathematical models of the growth process. Traditional ILC is modified to maximize the terminal broiler weight and better cope with the uncertain nature of the data driven model. To evaluate the proposed algorithm in simulation, a heuristic broiler growth model based on the knowledge of a broiler application expert is formalized. This paper gives the first results on the application of optimization based iterative learning control.
Original languageEnglish
Title of host publication2018 IEEE Conference on Control Technology and Applications, CCTA 2018
Number of pages7
PublisherIEEE
Publication dateAug 2018
Pages1258-1264
Article number8511464
ISBN (Print)978-1-5386-7699-8
ISBN (Electronic)978-1-5386-7698-1
DOIs
Publication statusPublished - Aug 2018
Event2018 IEEE Conference on Control Technology and Applications (CCTA) - The Scandic Hotel Copenhagen, Copenhagen, Denmark
Duration: 21 Aug 201824 Aug 2018

Conference

Conference2018 IEEE Conference on Control Technology and Applications (CCTA)
LocationThe Scandic Hotel Copenhagen
CountryDenmark
CityCopenhagen
Period21/08/201824/08/2018

Fingerprint

Meats
Temperature control
Electricity
Mathematical models
Neural networks
Water

Keywords

  • Iterative learning control
  • Biosystems
  • Neural networks

Cite this

Johansen, S. V., Jensen, M. R., Chu, B., Bendtsen, J. D., Mogensen, J., & Rogers, E. (2018). Broiler Growth Optimization using Norm Optimal Terminal Iterative Learning Control. In 2018 IEEE Conference on Control Technology and Applications, CCTA 2018 (pp. 1258-1264). [8511464] IEEE. https://doi.org/10.1109/CCTA.2018.8511464
Johansen, Simon Vestergaard ; Jensen, Martin Rishøj ; Chu, Bing ; Bendtsen, Jan Dimon ; Mogensen, Jesper ; Rogers, Eric. / Broiler Growth Optimization using Norm Optimal Terminal Iterative Learning Control. 2018 IEEE Conference on Control Technology and Applications, CCTA 2018. IEEE, 2018. pp. 1258-1264
@inproceedings{ddae06193e464a8ab0c1e6b51e2c9992,
title = "Broiler Growth Optimization using Norm Optimal Terminal Iterative Learning Control",
abstract = "Broiler (chicken for meat production) growth maximization reduces the amount of feed, water and electricity required to produce a mature broiler where temperature control is one of the most influential factors. Iterative learning control provides a potential solution given the repeated nature of the production process, as it has been especially developed for systems that make repeated executions of the same finite duration task. Dynamic neural network models are used given the absence of mathematical models of the growth process. Traditional ILC is modified to maximize the terminal broiler weight and better cope with the uncertain nature of the data driven model. To evaluate the proposed algorithm in simulation, a heuristic broiler growth model based on the knowledge of a broiler application expert is formalized. This paper gives the first results on the application of optimization based iterative learning control.",
keywords = "Iterative learning control, Biosystems, Neural networks",
author = "Johansen, {Simon Vestergaard} and Jensen, {Martin Rish{\o}j} and Bing Chu and Bendtsen, {Jan Dimon} and Jesper Mogensen and Eric Rogers",
year = "2018",
month = "8",
doi = "10.1109/CCTA.2018.8511464",
language = "English",
isbn = "978-1-5386-7699-8",
pages = "1258--1264",
booktitle = "2018 IEEE Conference on Control Technology and Applications, CCTA 2018",
publisher = "IEEE",
address = "United States",

}

Johansen, SV, Jensen, MR, Chu, B, Bendtsen, JD, Mogensen, J & Rogers, E 2018, Broiler Growth Optimization using Norm Optimal Terminal Iterative Learning Control. in 2018 IEEE Conference on Control Technology and Applications, CCTA 2018., 8511464, IEEE, pp. 1258-1264, 2018 IEEE Conference on Control Technology and Applications (CCTA), Copenhagen, Denmark, 21/08/2018. https://doi.org/10.1109/CCTA.2018.8511464

Broiler Growth Optimization using Norm Optimal Terminal Iterative Learning Control. / Johansen, Simon Vestergaard; Jensen, Martin Rishøj; Chu, Bing; Bendtsen, Jan Dimon; Mogensen, Jesper; Rogers, Eric.

2018 IEEE Conference on Control Technology and Applications, CCTA 2018. IEEE, 2018. p. 1258-1264 8511464.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Broiler Growth Optimization using Norm Optimal Terminal Iterative Learning Control

AU - Johansen, Simon Vestergaard

AU - Jensen, Martin Rishøj

AU - Chu, Bing

AU - Bendtsen, Jan Dimon

AU - Mogensen, Jesper

AU - Rogers, Eric

PY - 2018/8

Y1 - 2018/8

N2 - Broiler (chicken for meat production) growth maximization reduces the amount of feed, water and electricity required to produce a mature broiler where temperature control is one of the most influential factors. Iterative learning control provides a potential solution given the repeated nature of the production process, as it has been especially developed for systems that make repeated executions of the same finite duration task. Dynamic neural network models are used given the absence of mathematical models of the growth process. Traditional ILC is modified to maximize the terminal broiler weight and better cope with the uncertain nature of the data driven model. To evaluate the proposed algorithm in simulation, a heuristic broiler growth model based on the knowledge of a broiler application expert is formalized. This paper gives the first results on the application of optimization based iterative learning control.

AB - Broiler (chicken for meat production) growth maximization reduces the amount of feed, water and electricity required to produce a mature broiler where temperature control is one of the most influential factors. Iterative learning control provides a potential solution given the repeated nature of the production process, as it has been especially developed for systems that make repeated executions of the same finite duration task. Dynamic neural network models are used given the absence of mathematical models of the growth process. Traditional ILC is modified to maximize the terminal broiler weight and better cope with the uncertain nature of the data driven model. To evaluate the proposed algorithm in simulation, a heuristic broiler growth model based on the knowledge of a broiler application expert is formalized. This paper gives the first results on the application of optimization based iterative learning control.

KW - Iterative learning control

KW - Biosystems

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=85056842904&partnerID=8YFLogxK

U2 - 10.1109/CCTA.2018.8511464

DO - 10.1109/CCTA.2018.8511464

M3 - Article in proceeding

SN - 978-1-5386-7699-8

SP - 1258

EP - 1264

BT - 2018 IEEE Conference on Control Technology and Applications, CCTA 2018

PB - IEEE

ER -

Johansen SV, Jensen MR, Chu B, Bendtsen JD, Mogensen J, Rogers E. Broiler Growth Optimization using Norm Optimal Terminal Iterative Learning Control. In 2018 IEEE Conference on Control Technology and Applications, CCTA 2018. IEEE. 2018. p. 1258-1264. 8511464 https://doi.org/10.1109/CCTA.2018.8511464