Analytical and Bioanalytical Chemistry

, Volume 409, Issue 3, pp 841–857 | Cite as

Improved quantification of important beer quality parameters based on nonlinear calibration methods applied to FT-MIR spectra

  • Carlos Cernuda
  • Edwin Lughofer
  • Helmut Klein
  • Clemens Forster
  • Marcin Pawliczek
  • Markus Brandstetter
Research Paper
Part of the following topical collections:
  1. Process Analytics in Science and Industry


During the production process of beer, it is of utmost importance to guarantee a high consistency of the beer quality. For instance, the bitterness is an essential quality parameter which has to be controlled within the specifications at the beginning of the production process in the unfermented beer (wort) as well as in final products such as beer and beer mix beverages. Nowadays, analytical techniques for quality control in beer production are mainly based on manual supervision, i.e., samples are taken from the process and analyzed in the laboratory. This typically requires significant lab technicians efforts for only a small fraction of samples to be analyzed, which leads to significant costs for beer breweries and companies. Fourier transform mid-infrared (FT-MIR) spectroscopy was used in combination with nonlinear multivariate calibration techniques to overcome (i) the time consuming off-line analyses in beer production and (ii) already known limitations of standard linear chemometric methods, like partial least squares (PLS), for important quality parameters Speers et al. (J I Brewing. 2003;109(3):229–235), Zhang et al. (J I Brewing. 2012;118(4):361–367) such as bitterness, citric acid, total acids, free amino nitrogen, final attenuation, or foam stability. The calibration models are established with enhanced nonlinear techniques based (i) on a new piece-wise linear version of PLS by employing fuzzy rules for local partitioning the latent variable space and (ii) on extensions of support vector regression variants (𝜖-PLSSVR and ν-PLSSVR), for overcoming high computation times in high-dimensional problems and time-intensive and inappropriate settings of the kernel parameters. Furthermore, we introduce a new model selection scheme based on bagged ensembles in order to improve robustness and thus predictive quality of the final models. The approaches are tested on real-world calibration data sets for wort and beer mix beverages, and successfully compared to linear methods, showing a clear out-performance in most cases and being able to meet the model quality requirements defined by the experts at the beer company.


Workflow for calibration of non-Linear model ensembles from FT-MIR spectra in beer production 


Quality control of beer FT-MIR spectroscopy Nonlinear PLS Flexible fuzzy systems Support vector regression variation Bagged model selection 



Financial support was provided by (i) the Austrian research funding association (FFG) under the scope of the COMET programme within the research project Industrial Methods for Process Analytical Chemistry - From Measurement Technologies to Information Systems (imPACts) (contract #843546), (ii) the Basque Government through the ELKARTEK and BERC 2014-2017 programs, and (iii) the Spanish Ministry of Economy and Competitiveness MINECO: BCAM Severo Ochoa accreditation SEV-2013-032. This publication reflects only the authors’ views.

Compliance with Ethical Standards

This paper does not contain any studies with human participants or animals performed by any of the authors.

Conflict of interests

The authors declare that they have no conflict of interest.

Supplementary material

216_2016_9785_MOESM1_ESM.pdf (3.3 mb)
(PDF 3.26 MB)


  1. 1.
    Speers RA, Rogers P, Smith B. Non-linear modelling of industrial brewing fermentations. J I Brewing 2003;109(3):229–235.CrossRefGoogle Scholar
  2. 2.
    Zhang Y, Jia S, Zhang W. Predicting acetic acid content in the final beer using neural networks and support vector machine. J I Brewing 2012;118(4):361–367.CrossRefGoogle Scholar
  3. 3.
    McMurrough M, Lynch V, Murray F, Kearney M. A comparison of alternative high-performance liquid chromatographic systems for measuring bitterness in beer. J Am Soc Brew Chem 1987;45:6–13.Google Scholar
  4. 4.
    de Keukeleire D. Fundamentals of beer and hop chemistry. Quim Nova 2000;23(1):108–112.CrossRefGoogle Scholar
  5. 5.
    Polshin E, Aernouts B, Saeys W, Delvaux F, Delvaux FR, Saison D, Hertog M, Nicolai BM, Lammertyn J. Beer quality screening by FT-IR spectrometry: impact of measurement strategies, data pre-processings and variable selection methods. J Food Eng 2011;106(3):188–198.CrossRefGoogle Scholar
  6. 6.
    Lachenmeier DW. Rapid quality control of spirit drinks and beer using multivariate data analysis of fourier transform infrared spectra. Food Chem 2007;101(2):825–832.CrossRefGoogle Scholar
  7. 7.
    Christensen J, Ladefoged AM, Nrgaard L. Rapid determination of bitterness in beer using fluorescence spectroscopy and chemometrics. J I Brewing 2012;111(1):3–10.CrossRefGoogle Scholar
  8. 8.
    Grassi S, Amigo JM, Lyndgaard CB, Foschino R, Casiraghi E. Beer fermentation: monitoring of process parameters by FT-NIR and multivariate data analysis. Food Chem 2014;155:279–286.CrossRefGoogle Scholar
  9. 9.
    Haenlein M, Kaplan AM. A beginner’s guide to partial least squares (PLS) analysis. Und Stat 2004;3(4): 283–297.Google Scholar
  10. 10.
    Brazdil P, Giraud-Carrier C, Soares C, Vilalta R. Metalearning. Berlin Heidelberg: Springer; 2009.Google Scholar
  11. 11.
    Bleier Z, Brouillette C, Carangelo R. A monolithic interferometer for FT-IR spectroscopy. Spectroscopy 1999;14(10):46–49.Google Scholar
  12. 12.
    Griffiths PR, De Haseth JA. Fourier Transform Infrared Spectrometry, 2nd edn. New Jersey: Wiley; 2007.CrossRefGoogle Scholar
  13. 13.
    Jolliffe IT. Principal Component Analysis. Berlin Heidelberg New York: Springer Verlag; 2002.Google Scholar
  14. 14.
    Brereton RG. Chemometrics: Data Analysis for the Laboratory and Chemical Plant. New Jersey: Wiley; 2003.CrossRefGoogle Scholar
  15. 15.
    Varmuza K, Filzmoser P. Introduction to Multivariate Statistical Analysis in Chemometrics. Boca Raton: CRC Press; 2009.CrossRefGoogle Scholar
  16. 16.
    Otto M. Chemometrics, 2nd edn. New Jersey: Wiley; 2007.Google Scholar
  17. 17.
    Mark H, Workman J. Chemometrics in Spectroscopy. The Netherlands: Academic Press; 2007.Google Scholar
  18. 18.
    Cernuda C, Lughofer E, Hintenaus P, Märzinger W. Enhanced waveband selection in NIR spectra using enhanced genetic operators. J Chemometr 2014;28(3):123–136.CrossRefGoogle Scholar
  19. 19.
    Rosipal R. Kernel partial least squares for nonlinear regression and discrimination. Neural Netw World 2003; 13(3):291–300.Google Scholar
  20. 20.
    Cernuda C, Lughofer E, Hintenaus P, Märzinger W, Reischer T, Pawlicek M, Kasberger J. Hybrid adaptive calibration methods and ensemble strategy for prediction of cloud point in melamine resin production. Chemometr Intell Lab 2013;126:60–75.CrossRefGoogle Scholar
  21. 21.
    Lughofer E. Evolving Fuzzy Systems, —Methodologies, Advanced Concepts and Applications. Berlin Heidelberg: Springer; 2011.CrossRefGoogle Scholar
  22. 22.
    Lughofer E, Cernuda C, Kindermann S, Pratama M. Generalized smart evolving fuzzy systems. Evol Sys 2015;6(4):269–292.CrossRefGoogle Scholar
  23. 23.
    Krishnamoorthy K, Mathew T. Statistical Tolerance Regions: Theory, Applications, and Computation. New Jersey: Wiley; 2009.CrossRefGoogle Scholar
  24. 24.
    Mahalanobis PC. On the generalised distance in statistics; 1936.Google Scholar
  25. 25.
    Gray RM. Vector quantization. IEEE ASSP Mag 1984;1(2):4–29.CrossRefGoogle Scholar
  26. 26.
    Lughofer E, Sayed-Mouchaweh M. Autonomous data stream clustering implementing incremental split-and-merge techniques — towards a plug-and-play approach. Inform Scie 2015;204:54–79.CrossRefGoogle Scholar
  27. 27.
    Angelov PP, Filev D. An approach to online identification of Takagi-Sugeno fuzzy models. IEEE T Syst Man Cy B 2004;34(1):484–498.CrossRefGoogle Scholar
  28. 28.
    Lughofer E. FLEXFIS: A robust incremental learning approach for evolving TS fuzzy models. IEEE T Fuzzy Syst 2008;16(6):1393–1410.CrossRefGoogle Scholar
  29. 29.
    Vapnik V. Statistical Learning Theory. New York: Wiley; 1998.Google Scholar
  30. 30.
    Schölkopf B, Smola AJ. Learning with Kernels—Support Vector Machines, Regularization, Optimization and Beyond. London: MIT Press; 2002.Google Scholar
  31. 31.
    Hofmann T, Scholkopf B, Smola AJ. Kernel methods in machine learning. Ann Stat 2009;36(3):1171–1220.CrossRefGoogle Scholar
  32. 32.
    Smola AJ, Schölkopf B. A tutorial on support vector regression. Stat Comp 2004;14:199–222.CrossRefGoogle Scholar
  33. 33.
    Hsu C-W, Chang C-C, Lin C-J. 2010. A practical guide to support vector classification.Google Scholar
  34. 34.
    Stone M. Cross-validatory choice and assessment of statistical predictions. J R Stat Soc 1974;36(1):111–147.Google Scholar
  35. 35.
    Breiman L. Bagging predictors. Mach Learn 1996;24(2):123–140.Google Scholar
  36. 36.
    Bras LP, Lopes M, Ferreira AP, Menezes JC. A bootstrap-based strategy for spectral interval selection in pls regression. J Chemometr 2008;22(11–12):695–700.CrossRefGoogle Scholar
  37. 37.
    Efron B, Tibshirani R. Improvements on cross-validation: the.632 + bootstrap method. J Am Stat Assoc 1997;92(438):548–560.Google Scholar
  38. 38.
    Breiman L. Random forests. Mach Learn 2001;45(1):5–32.CrossRefGoogle Scholar
  39. 39.
    Centner V, Massart D-L, de Noord OE, de Jong S, Vandeginste BM, Sterna S. Elimination of uninformative variables for multivariate calibration. Anal Chem 1996;68(21):3851–3858.CrossRefGoogle Scholar
  40. 40.
    Cai W, Li Y, Shao X. A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra. Chemometr Intell Lab 2008;90:188–194.CrossRefGoogle Scholar
  41. 41.
    Andersen CR, Bro R. Variable selection in regression—a tutorial. J Chemometr 2010;24(11-12):728–737.CrossRefGoogle Scholar
  42. 42.
    Rinnan A, van den Berg F, Engelsen SB. Review of the most common pre-processing techniques for near-infrared spectra. Trend Anal Chem 2009;28(10):1201–1222.CrossRefGoogle Scholar
  43. 43.
    Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd ed. New York Berlin Heidelberg: Springer; 2009.CrossRefGoogle Scholar
  44. 44.
    Tibshirani R. Regression shrinkage and selection via the lasso. J R Stat Soc 1996;58:267–288.Google Scholar
  45. 45.
    Zou H, Hastie T. Regularization and variable selection via the elastic net. J R Stat Soc 2005;67(2):301–320.CrossRefGoogle Scholar
  46. 46.
    Hastie T, Tibshirani R, Friedman J. Regularized paths for generalized linear models via coordinate descent. J Stat Softw 2010;33(1).Google Scholar
  47. 47.
    Hastie T, Tibshirani R, Friedman J. Pathwise coordinate optimization. Ann Appl Stat 2007;1(2):302–332.CrossRefGoogle Scholar
  48. 48.
    Cernuda C, Lughofer E, Maerzinger W, Kasberger J. NIR-based quantification of process parameters in polyetheracrylat (PEA) production using flexible non-linear fuzzy systems. Chemometr Intell Lab 2011;109(1):22–33.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  • Carlos Cernuda
    • 1
    • 2
  • Edwin Lughofer
    • 2
  • Helmut Klein
    • 3
  • Clemens Forster
    • 3
  • Marcin Pawliczek
    • 4
  • Markus Brandstetter
    • 4
  1. 1.BCAM - Basque Center for Applied MathematicsBilbaoSpain
  2. 2.Department of Knowledge-Based Mathematical SystemsJohannes Kepler University LinzLinzAustria
  3. 3.BrauUnion GmbHLinzAustria
  4. 4.RECENDT GmbH, Science Park 2LinzAustria

Personalised recommendations