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.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
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
Beale MH, Hagan MT, Demuth HB (2012) Neural network toolbox—user’s guide. The Mathworks, Natick
Cao P, Luo X (2014) Modeling for soft sensor systems and parameters updating online. Journal of Process Control 24:975–990
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
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
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
EPA (1999) Nitrogen oxides (NOx), why and how they are controlled, 57. Clean Air Technology Center, Durham
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
Fortuna L (2007) Soft sensor for monitoring and control of industrial processes. Springer, Londres
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
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
Kadlec P (2009) On robust and adaptive soft sensors, Ph.D. Thesis. Bournemouth University
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
Kadlec P, Gabrys B, Strandt S (2009) Data-driven soft sensors in the process industry. Computers & Chemical Engineering 33:795–814
Kadlec P, Grbić R, Gabrys B (2011) Review of adaptation mechanisms for data-driven soft sensors. Computers & Chemical Engineering 35:1–245
Kamat S, Madhavan K (2016) Developing ANN based virtual/soft sensors for industrial problems. IFAC-PapersOnLine 49(1):100–105
Kaneko H, Funatsu K (2013) Classification of the degradation of soft sensor models and discussion on adaptive models. AIChE Journal 59:2339–2347
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
Lin B, Recke B, Knudsen JKH, Jørgensen SB (2007) A systematic approach for soft sensor development. Computers & Chemical Engineering 31:419–425
Lu B, Chiang L (2018) Semi-supervised online soft sensor maintenance experiences in the chemical industry. Journal of Process Control 67:23–34
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
MacKay DJC (1992) A practical bayesian framework for backprop networks. Neural Comput 4:448–472
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
Neuralware (2010) Support: frequently asked questions [Online]. http://www.neuralware.com/support_faq.jsp. Accessed 30 May 2010
Parkinson T, Parkinson A, Dear R (2019) Continuous IEQ monitoring system: Context and development. Building and Environment 149:15–25
Souza FAA, Araújo R, Mendes J (2016) Review of soft sensor methods for regression applications. Chemometrics and Intelligent Laboratory Systems 152:69–79
Tambourghi EB, Fischer GA, Fileti AMF (2006) Neural modeling for cytochrome b5 extraction. Process Biochemistry 41:1272–1275
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
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
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
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
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).
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.
About this article
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
- Model maintenance
- Soft sensor
- Gas emission