Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

An online calibration tool for soft sensors: development and experimental tests in a semi-industrial boiler plant

  • 9 Accesses


Soft sensors with real time prediction capabilities appear as a profitable solution for hard-to-measure variables whenever hard sensors are difficult to apply or subjected to high operational costs. Nonetheless, the use of soft sensors within industrial applications is still not widespread because of the systematic accuracy issues that can be introduced with process plant deviations from nominal operation states. Soft sensor models need to be constantly updated to avoid degradation of their prediction potential. This study presents an innovative view on a well-known artificial neural network (ANN) calibration method by developing a generic online calibration tool that can be used in independent data-driven soft sensors based on ANN multi-layer perceptron (MLP) models. The maintenance framework has been fully tested in a semi-industrial boiler plant to predict real time pollutant emission levels, presenting recalibration time responses up to 1 min, overall r2 performance above 80% and an intuitive human–machine-interface.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Change history

  • 06 February 2020

    Due to a typesetting error the second name of the fourth author was wrong.


  1. Andrijić ŽU, Cvetnić M, Bolf N (2018) Soft sensor models for a fractionation reformate plant using small and bootstrapped data sets. Brazilian Journal of Chemical Engineering 35(2):745–756

  2. Beale MH, Hagan MT, Demuth HB (2012) Neural network toolbox—user’s guide. The Mathworks, Natick

  3. Cao P, Luo X (2014) Modeling for soft sensor systems and parameters updating online. Journal of Process Control 24:975–990

  4. Chen K, Castillo I, Chiang LH, Yu J (2015) Soft sensor model maintenance: A case study in industrial processes. IFAC-PapersOnLine 48(8):427–432

  5. De Clercq D, Jalota D, Shang R, Ni K, Zhang Z, Khan A, Wen Z, Caiedo L, Yuan K (2019) Machine learning powered software for accurate prediction of biogas production: A case study on industrial-scale Chinese production data. Journal of Cleaner Production 218:390–399

  6. dos Santos BF, Simiqueli APR, Ponezi AN, Pastore GM, Fileti AMF (2018) Monitoring of biosurfactant production by Bacillus subtilis using beet peel as culture medium via the development of a neural soft-sensor in an electronic spreadsheet. Brazilian Journal of Chemical Engineering 35(4):1355–1367

  7. EPA (1999) Nitrogen oxides (NOx), why and how they are controlled, 57. Clean Air Technology Center, Durham

  8. Foresee FD, Hagan MT (1997) Gauss–Newton approximation to bayesian learning. In: Proceedings of international conference on neural networks (ICNN'97), Houston, 12 June 1997

  9. Fortuna L (2007) Soft sensor for monitoring and control of industrial processes. Springer, Londres

  10. Grbić R, Slisković D, Kadlec P (2013) Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models. Computers & Chemical Engineering 58:84–97

  11. Jin H, Chen X, Yang J, Wang L, Wu L (2015) Online local learning based adaptive soft sensor and its application to an industrial fed-batch chlortetracycline fermentation process. Chemometrics and Intelligent Laboratory Systems 143:58–78

  12. Kadlec P (2009) On robust and adaptive soft sensors, Ph.D. Thesis. Bournemouth University

  13. Kadlec P, Gabrys B (2010) Adaptive on-line prediction soft sensing without historical data. In: The 2010 international joint conference on neural networks (IJCNN 2010), Barcelona, 18–23 July 2010

  14. Kadlec P, Gabrys B, Strandt S (2009) Data-driven soft sensors in the process industry. Computers & Chemical Engineering 33:795–814

  15. Kadlec P, Grbić R, Gabrys B (2011) Review of adaptation mechanisms for data-driven soft sensors. Computers & Chemical Engineering 35:1–245

  16. Kamat S, Madhavan K (2016) Developing ANN based virtual/soft sensors for industrial problems. IFAC-PapersOnLine 49(1):100–105

  17. Kaneko H, Funatsu K (2013) Classification of the degradation of soft sensor models and discussion on adaptive models. AIChE Journal 59:2339–2347

  18. Kano M, Ogawa M (2010) The state of the art in chemical process control in Japan: Good practice and questionnaire survey. Journal of Process Control 20:969–982

  19. Lin B, Recke B, Knudsen JKH, Jørgensen SB (2007) A systematic approach for soft sensor development. Computers & Chemical Engineering 31:419–425

  20. Lu B, Chiang L (2018) Semi-supervised online soft sensor maintenance experiences in the chemical industry. Journal of Process Control 67:23–34

  21. Lu B, Stuber J, Edgar TF (2014) Integrated online virtual metrology and fault detection in plasma etch tools. Industrial Engineering Chemical Research 53:5172–5181

  22. MacKay DJC (1992) A practical bayesian framework for backprop networks. Neural Comput 4:448–472

  23. Maier HR, Dandy GC (1998) The effect of internal parameters and geometry on the performance of back-propagation neural networks: An empirical study. Environmental Modelling and Software 13:193–209

  24. Neuralware (2010) Support: frequently asked questions [Online]. http://www.neuralware.com/support_faq.jsp. Accessed 30 May 2010

  25. Parkinson T, Parkinson A, Dear R (2019) Continuous IEQ monitoring system: Context and development. Building and Environment 149:15–25

  26. Souza FAA, Araújo R, Mendes J (2016) Review of soft sensor methods for regression applications. Chemometrics and Intelligent Laboratory Systems 152:69–79

  27. Tambourghi EB, Fischer GA, Fileti AMF (2006) Neural modeling for cytochrome b5 extraction. Process Biochemistry 41:1272–1275

  28. Tao X, Mao C, Xie F, Liu G, Xu P (2018) Greenhouse gas emission monitoring system for manufacturing prefabricated components. Automation in Construction 93:361–374

  29. Valdman A, Folly R, de Souza Jr MB, Valdman B (2011) A systematic methodology on developing an online soft sensor based on neural networks for monitoring boiler gas emissions. AIDIC Conference Series 10:353–361

  30. Warne K, Prasad G, Rezvani S, Maguire L (2004) Statistical and computational intelligence techniques for inferential model development: A comparative evaluation and a novel proposition for fusion. Engineering Application of Artificial Intelligence 17(8):871–885

  31. Zheng W, Liu Y, Gao Z, Yang J (2018) Just-in-time semi-supervised soft sensor for quality prediction in industrial rubber mixers. Chemometrics and Intelligent Laboratory Systems 180:36–41

Download references


The authors gratefully acknowledge support from the Federal University of Rio de Janeiro for providing software licenses of Matlab® (C Algorithm), Excel® (Electronic Sheet embedded with VBA) and Ifix Proficy® (SCADA).

Author information

Correspondence to Andréa Pereira Parente.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The original version of this article was revised: Due to a typesetting error the second name of the fourth author was wrong.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Parente, A.P., Valdman, A., Folly, R.O.M. et al. An online calibration tool for soft sensors: development and experimental tests in a semi-industrial boiler plant. Braz. J. Chem. Eng. (2020). https://doi.org/10.1007/s43153-019-00005-w

Download citation


  • Model maintenance
  • Soft sensor
  • Gas emission
  • ANN