Soft Sensors to Monitoring a Multivariate Nonlinear Process Using Neural Networks
- 54 Downloads
In general, industrial processes have a multivariable nature, with multiple inputs and multiple outputs. Such systems are more difficult to monitor and control due to interactions between the input and output variables. Focusing on these issues, the development of soft sensors to monitor multivariate nonlinear processes using neural networks is proposed. Experiments were performed to monitor the pressure and flow values on an experimental platform (fluid transport system) using developed soft sensors. With the monitoring using soft sensor, it is possible to make processes more reliable, with better performance and with less difficulty in detecting and solving possible failures.
KeywordsMonitoring Modeling Neural networks Soft sensor System identification
The authors would like to thank CNPq and Copele-DEE for financial support.
- Buondonno, G. & Luca, A. D. (2016), Combining real and virtual sensors for measuring interaction forces and moments acting on a robot. In International conference on intelligent robots and systems (IROS). Google Scholar
- Ell, S. M., & Trabachini, A. (2011). Loss of charge in forced conduits. Retrieved January 18, 2018 from http://pt.scribd.com/doc/72710149/Perda-de-Carga-Tubulacao-Singular-Ida-Des.
- Haykin, S. (2009). Neural networks and learning machines (3rd ed.). Ontario: Prentice Hall.Google Scholar
- Liu, L., Chen, J. & Xu, L. (2008). Realization and application research of BP neural network based on MATLAB. In International seminar on future biomedical information engineering.Google Scholar
- Lopes, A. M., Lapa, J. P. & Oliveira, L. A. (2006). Turbulent laminar regime transition unit—practical workbook. Retrieved January 18, 2018 from https://woc.uc.pt/dem/getFile.do?tipo=6&id=362.
- Mansoori, G. (2001), Deposition and fouling of heavy organic oils and other compounds. In 9th International conference on properties an phases equilibria for product and process design.Google Scholar
- Marques, J. A. A. S. & Sousa, J. J. O. (1997). Formula of colebrook—white: old but current. explicit solutions. In 3rd Symposium on hydraulics and water re-sources in Portuguese-speaking Countries (Silusba).Google Scholar
- Ortega, E. (2012). Calculation of the friction energy. http://www.unicamp.br/fea/ortega/aulas/aula05\_fator\_atrito.ppt.
- Palcios, R. H. C., da Silva, I. N., Goedtel, A., Godoy, W. F., & Oleskovicz, M. (2014). A robust neural method to estimate torque in three-phase induction motor. Journal of Control, Automation and Electrical Systems, 25, 493–502.Google Scholar
- Saptoro, A. (2014). State of the art in the develop-ment of adaptive soft sensors based on just-in-time models’. International Conference and Workshop on Chemical Engineering, 9, 226–234.Google Scholar
- Severson, K., Chaiwatanodom, P., & Braatz, R. D. (2015). Perspectives on process monitoring of industrial systems’. International Federation of Automatic Control (IFAC), 48, 931–939.Google Scholar