Mass-balance based soft sensor for monitoring ash content at two-ply paperboard manufacturing
Source abstract
Abstract
Abstract Continuous and robust measurements are needed for the high end-product quality and efficient and eco-friendly process in paperboard manufacturing. As the online measurements enable the optimization of the manufacturing process making it more cost effective and environmentally friendly, these measurements must be validated carefully and continuously. This paper presents the development of a mass-balance based soft sensor for online estimation of a two-ply paperboard ash content. The developed soft sensor considers the basis weight, moisture and fiber measurements to derive the ash content of the paperboard at the reel. The development of the soft sensor was success (Mean Absolute Percentage Error was 11.80) and during the long-term simulation with measured data, this robust online estimator showed the level and changes in ash content accurately, enabling also the continuous validation of the hardware sensor.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Mineral Processing and Grinding · Spectroscopy and Chemometric Analyses · Electrical and Bioimpedance Tomography
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Environmental and Chemical Engineering Research Unit, Control Engineering , 6370 University of Oulu , P.O. Box 8000 , University of Oulu , Finland
Automation Technology and Mechanical Engineering, Faculty of Technical Sciences , 7840 Tampere University , P.O. Box 692 , Tampere , Finland
Valmet Automation Inc. , P.O. Box 237 , Tampere , Finland
Funding
Business Finland
References (21)
Show source-provided references
1. Alonso, A., Negro, C., Blanco, A., San Pío, I. (2009) Application of advanced data treatment to predict paper properties. Math. Comput. Model. Dyn. Syst. 15(5):453–462. 10.1080/13873950903375445.10.1080/13873950903375445 ↗
2. Avelin, A., Jansson, J., Dotzauer, E., Dahlquist, E. (2009) Use of combined physical and statistical models for online applications in the pulp and paper industry. Math. Comput. Model. Dyn. Syst. 15(5):425–434. 10.1080/13873950903375403.10.1080/13873950903375403 ↗
3. Chiang, L., Lu, B., Castillo, I. (2017) Big Data Analytics in Chemical Engineering. Annu. Rev. Chem. Biomol. Eng. 8:63–85. 10.1146/annurev-chembioeng-060816-101555.10.1146/annurev-chembioeng-060816-101555 ↗
4. Dijkstra, B.K. (2011) Development of a predictive model for the moisture content in a paper mill. Master Thesis, University of Groningen. 89 p. Available: https://fse.studenttheses.ub.rug.nl/9771/1/Development_of_a_predictive_mo_1.pdf.
5. Fu, J., Hart, P. (2016) Leveraging mill-wide big data sets for process and quality improvement in paperboard production. Tappi J. 15(5):309–319.10.32964/TJ15.5.309 ↗
6. Harding, G. (2020) Big data opportunities in pulp and paper: A case study of what can be achieved from a recent energy audit. Appita J. 1:44–46.
7. Holik, H. Handbook of Paper and Board. Wiley-VCH Verlag GmbH & Co. KGaA, 2006. 10.1002/3527608257.
8. Hu, L., Lu, X., Ma, J. (2020) Research review on devices and methods for rapid measurement of paper ash. BioResources 15(1):2096–2110. 10.15376/biores.15.1.2096-2110.10.15376/biores.15.1.2096-2110 ↗
9. Karlsson, E. (2020) Evaluation of sodium salt scaling in black liquor evaporators using existing process data. Nord. Pulp Pap. Res. J. 35(4):516–532. 10.1515/npprj-2020-0038.10.1515/npprj-2020-0038 ↗
10. Karlström, A., Johansson, L., Hill, J. (2019) On the modeling of tensile index from larger data sets. Nord. Pulp Pap. Res. J. 34(3):289–303. 10.1515/npprj-2018-0019.10.1515/npprj-2018-0019 ↗
11. Lu, B., Chiang, L. (2018) Semi-supervised online soft sensor maintenance experiences in the chemical industry. J. Process Control 67:23–34. 10.1016/j.jprocont.2017.03.013.10.1016/j.jprocont.2017.03.013 ↗
12. Mäntylä, M. (2017) Sheet measurement, US9574994B2, Feb. 21, 2017. Available: https://patents.google.com/patent/US9574994B2/en?inventor=mantyla+markku&scholar&oq=mantyla+markku&sort=new. Accessed: November 2021.
13. Narasimhan, S., Jordache, C. Data reconciliation & gross error detection – An intelligent use of process data. Gulf Publishing Company, Houston Texas, 2000. 405 p.10.1016/B978-088415255-2/50002-1 ↗
14. NIST/SEMATECH e-Handbook of Statistical Methods. Available: http://www.itl.nist.gov/div898/handbook/. Accessed: October 2021.
15. Nobakhti, A., Wang, H. (2010) Minimization of Wet End disturbances during web breaks using online LAV estimation. Control Eng. Pract. 18(4):433–447. 10.1016/j.conengprac.2010.01.003.10.1016/j.conengprac.2010.01.003 ↗
16. Raffaele, D., Ondruch, T. (2020) Data-driven soft sensor for continuous production monitoring: an application to paper strength. In: 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), 2020. IEEE. pp. 1335–1338. 10.1109/ETFA46521.2020.9212113.10.1109/ETFA46521.2020.9212113 ↗
17. Skoglund, A., Brundin, A., Mandenius, C. (2018) A multivariate process model for grade change in a paperboard machine. Nord. Pulp Pap. Res. J. 15(3):183–188. 10.3183/npprj-2000-15-03-p183-188.10.3183/npprj-2000-15-03-p183-188 ↗
18. Souza, F., Araujo, R., Mendes, J. (2016) Review of Soft Sensor Methods for Regression Applications. Chemom. Intell. Lab. Syst. 152:69–79.10.1016/j.chemolab.2015.12.011 ↗
19. Viitamäki, M., Ritala, R. (2018) Soft sensor for compression and burst strength: identification and uncertainty analysis. J. Sci. Technol. For. Prod. Process. 7(1):38–47.
20. Weidl, G., Dahlquist, E. (2002) Root cause analysis for pulp and paper applications. In: Proc. of 10th Control Systems Conference, June 3–5, 2002, Stockholm, Sweden. pp. 343–347.
21. Wilson, D. (2008) Applying data reconciliation and the diagnostic model processor to a paper machine. In: Proc. of the 27th IASTED International Conference on Modelling, Identification and Control (MIC’08), February 11–13, 2008, Innsbruck, Austria. pp. 376–380.