A soft sensor for the Bayer process

Journal of Mathematics in Industry - Tập 7 Số 1 - Trang 1-6 - 2017
Cregan, Vincent1,2, Lee, William T2,3, Clune, Louise4
1Centre de Recerca Matemàtica, Barcelona, Spain
2Mathematics Applications Consortium for Science and Industry, University of Limerick, Limerick, Ireland
3Department of Mathematics, University of Portsmouth, Portsmouth , United Kingdom
4RUSAL Aughinish Alumina Ltd., Limerick, Ireland

Tóm tắt

A soft sensor for measuring product quality in the Bayer process has been developed. The soft sensor uses a combination of historical process data recorded from online sensors and laboratory measurements to predict a key quality indicator, namely particle strength. Stepwise linear regression is used to select the relevant variables from a large dataset composed of monitored properties and laboratory data. The developed sensor is employed successfully by RUSAL Aughinish Alumina Ltd to predict product strength five days into the future with R-squared equal to 0.75 and to capture deviations from standard operating conditions.

Tài liệu tham khảo

citation_journal_title=Comput Chem Eng; citation_title=Data-driven soft sensors in the process industry; citation_author=P Kadlec, B Gabrys, S Strandt; citation_volume=33; citation_publication_date=2009; citation_pages=795-814; citation_doi=10.1016/j.compchemeng.2008.12.012; citation_id=CR1 citation_journal_title=Comput Chem Eng; citation_title=A systematic approach for soft sensor development; citation_author=B Lin, B Reck, JKH Knudsen, SB Jørgensen; citation_volume=31; citation_publication_date=2007; citation_pages=419-425; citation_doi=10.1016/j.compchemeng.2006.05.030; citation_id=CR2 citation_journal_title=Braz J Chem Eng; citation_title=Soft sensors with white- and black-box approaches for a wastewater treatment process; citation_author=D Zyngier, OQF Araújo, EL Lima; citation_volume=17; citation_issue=4-7; citation_publication_date=2000; citation_pages=433-440; citation_doi=10.1590/S0104-66322000000400008; citation_id=CR3 citation_journal_title=J Process Control; citation_title=Recursive exponentially weighted PLS and its applications to adaptive control and prediction; citation_author=BS Dayal, JF MacGregor; citation_volume=7; citation_issue=3; citation_publication_date=1997; citation_pages=169-179; citation_doi=10.1016/S0959-1524(97)80001-7; citation_id=CR4 citation_journal_title=Comput Chem Eng; citation_title=ANN-based soft-sensor for real time process monitoring and control of an industrial polymerization process; citation_author=JCB Gonzaga, LAC Meleiro, C Kiang, RM Filho; citation_volume=33; citation_publication_date=2009; citation_pages=43-49; citation_doi=10.1016/j.compchemeng.2008.05.019; citation_id=CR5 citation_journal_title=Comput Chem Eng; citation_title=Soft sensing modeling based on support vector machine and Bayesian model selection; citation_author=W Yan, H Shao, X Wang; citation_volume=28; citation_publication_date=2003; citation_pages=1489-1498; citation_doi=10.1016/j.compchemeng.2003.11.004; citation_id=CR6 citation_journal_title=J Process Control; citation_title=Optimal selection of soft sensor inputs for batch distillation columns using principal component analysis; citation_author=E Zamprogna, M Barolo, DE Seborg; citation_volume=15; citation_publication_date=2005; citation_pages=39-52; citation_doi=10.1016/j.jprocont.2004.04.006; citation_id=CR7 citation_journal_title=Powder Technol; citation_title=Particle size distribution soft-sensor for a grinding circuit; citation_author=A Casali, G Gonzalez, F Torres, G Vallebuona, L Castelli, P Gimenez; citation_volume=99; citation_issue=1; citation_publication_date=1998; citation_pages=15-21; citation_doi=10.1016/S0032-5910(98)00084-9; citation_id=CR8 citation_journal_title=Ind Eng Chem Res; citation_title=Combined quadrature method of moments and method of characteristics approach for efficient solution of population balance models for dynamic modeling and crystal size distribution control of crystallization processes; citation_author=E Aamir, ZK Nagy, CD Rielly, T Kleinert, B Judat; citation_volume=48; citation_issue=18; citation_publication_date=2009; citation_pages=8575-8584; citation_doi=10.1021/ie900430t; citation_id=CR9 citation_journal_title=Sep Purif Technol; citation_title=Multiscale modeling, simulation and validation of batch cooling crystallization; citation_author=A Abbas, J Romagnoli; citation_volume=53; citation_issue=2; citation_publication_date=2007; citation_pages=153-163; citation_doi=10.1016/j.seppur.2006.06.027; citation_id=CR10 citation_journal_title=Control Eng Pract; citation_title=Soft-sensor for industrial sugar crystallization: on-line mass of crystals, concentration and purity measurement; citation_author=C Damour, M Benne, B Grondin-Perez, JP Chabriat; citation_volume=18; citation_issue=8; citation_publication_date=2010; citation_pages=839-844; citation_doi=10.1016/j.conengprac.2010.03.005; citation_id=CR11 citation_journal_title=J Process Control; citation_title=Online dual updating with recursive PLS model and its application in predicting crystal size of purified terephthalic acid (PTA) process; citation_author=S Mu, Y Zeng, R Liu, P Wu, H Su, J Chu; citation_volume=16; citation_issue=6; citation_publication_date=2006; citation_pages=557-566; citation_doi=10.1016/j.jprocont.2005.11.004; citation_id=CR12 GNU Octave. https://www.gnu.org/software/octave/ .