Abstract
This paper addresses a soft computing-based approach to design soft sensors for industrial applications. The goal is to identify second-order Takagi–Sugeno–Kang fuzzy models from available input/output data by means of a coevolutionary genetic algorithm and a neuro-based technique. The proposed approach does not require any prior knowledge on the data-base and rule-base structures. The soft sensor design is carried out in two steps. First, the input variables of the fuzzy model are pre-selected from the secondary variables of a dynamical process by means of correlation coefficients, Kohonen maps and Lipschitz quotients. Such selection procedure considers nonlinear relations among the input and output variables. Second, a hierarchical coevolutionary methodology is used to identify the fuzzy model itself. Membership functions, individual rules, rule-bases and fuzzy inference parameters are encoded into each hierarchical level and a shared fitness evaluation scheme is used to measure the performance of individuals in such levels. The proposed methodology is evaluated by developing soft sensors to infer the product composition in petroleum refining processes. The obtained results are compared with other benchmark approaches, and some conclusions are presented.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
HYSYS 3.0, HYPROTECH Ltd.
Other values did not improved the performance without increasing so hard the computational cost.
Running in a computer AMD-64 3200 2 GHz, 2 GB of RAM
References
Ansari RM, Tadé M (2000) Non-linear model-based process control: applications in petroleum refining. Springer, Heidelberg
Cordón O, Herrera F, Hoffmann F, Magdalena L (eds) (2001) Genetic fuzzy systems. Evolutionary tuning and learning of fuzzy knowledge bases. World Scientific, New York
Delgado MR, Zuben FV (2003) Interpretability issues in fuzzy modeling—studies in fuzziness and soft computing. In: Hierarchical genetic fuzzy systems: accuracy, interpretability and design autonomy. Physica-Verlag, New York, pp 379–405
Delgado MR, Zuben FV, Gomide F (2000) Optimal parameterization of evolutionary Takagi–Sugeno fuzzy systems. In: Proceedings of 8th IPMU00, pp 650–657
Delgado MR, Zuben FV, Gomide F (2004) Coevolutionary genetic fuzzy systems: a hierarchical collaborative approach. Fuzzy Sets Syst 141:89–106
Dote Y, Ovaska SJ (2001) Industrial applications of soft computing: a review. Proc IEEE 89:1243–1265
Espinosa J, Vandewalle J (2000) Constructing fuzzy models with linguistic integrity from numerical data-afreli algorithm. IEEE Trans Fuzzy Syst 8:591–600
Fabro JA, Arruda LVR, Neves-Jr F (2005) Startup of a distillation column using intelligent control techniques. Comput Chem Eng 30:309–320
Fletcher R (1987) Practical methods of optimization. Wiley, New York
Fortuna L, Granziani S, Rizzo A, Xibilia MG (2007) Soft sensors for monitoring and control of industrial processes. Springer, Heidelberg
Gonzales A, Perez R (1998) Completeness and consistency conditions for learning fuzzy rules. Fuzzy Sets Syst 96:37–51
Ishibuchi H, Nakashima T (1999) Genetic-algorithm-based approach to linguistic approximation of nonlinear functions with many input variables. In: Proceedings of FUZZ-IEEE’99, Seoul, Korea, pp 779–784
Jang JSR (1993) Anfis: Adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23:665–684
Jin Y (2000) Fuzzy modeling of high-dimensional systems: complexity reduction and interpretability improvement. IEEE Trans Fuzzy Syst 8:212–221
Kaski S, Lagus K (1996) Comparing self-organizing maps. In: Proceedings of ICANN96, Bochum, Germany, pp 809–814
Klement E, Mesiar R, Pap E (2000) Triangular norms. Kluwer, Dordrecht
Luo JX, Shao HH (2006) Developing soft sensors using hybrid soft computing methodology: a neurofuzzy system based on rough set theory and genetic algorithms. Soft Comput 10:54–60
Michalewicz Z (1996) Genetic algorithms + data structures = evolution programs. Springer, Heidelberg
Moriarty D, Miikkulainen R (1997) Forming neural networks through efficient and adaptive coevolution. Evol Comput 5:373–399
Nagai EY (2006) Automatic identification of inferential fuzzy models (in portuguese). PhD thesis, Federal University of Techonology-Parana
Nagai EY, Arruda LVR (2005) Soft sensor based on fuzzy model identification. In: Proceedings of 16th IFAC World Congress, Prague, Czech Republic
Pedrycz W, Gomide F (1998) An introduction to fuzzy sets: analysis and design. MIT Press, Cambridge
Potter M, Jong KD (2000) Cooperative coevolution: an architecture for evolving coadapted subcomponents. Evol Comput 8:1–29
Prett D, Garcia C (1998) Fundamental process control. Butterworth, London
Qin SJ (1996) Neural networks for control. In: Neural networks for intelligent sensor and control—practical issues and some solutions. Academic Press, New York, pp 215–236
Rallo R, Ferre-Gine J, Arenas A, Giralt F (2002) Neural virtual sensor for the inferential prediction of product quality from process variables. ensor for the inferential prediction of product quality from process variables. Comput Chem Eng 26:1735–1754
Takagi T, Sugeno M (1983) Derivation of fuzzy control rules from human operator’s control actions. In: Proceedings of the IFAC symposium on fuzzy information, knowledge representation and decision analysis, Marseilles, France, pp 55–60
Zadeh L (1965) Fuzzy sets. Inf Control 8:338–352
Acknowledgments
The authors would like to thank Brazilian Petroleum Agency(ANP/FINEP) for grant PRH-ANP/MCT-PRH10-UTFPR.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Delgado, M.R., Nagai, E.Y. & de Arruda, L.V.R. A neuro-coevolutionary genetic fuzzy system to design soft sensors. Soft Comput 13, 481–495 (2009). https://doi.org/10.1007/s00500-008-0363-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-008-0363-3