Summary
As a consequence of the continually increasing complexity of technical systems and processes, the requirement for high-performing modeling techniques is increasing. The methods of Computational Intelligence (CI), such as fuzzy modeling or artificial neural networks, are specifically designed to deal with imprecise, incomplete, and partially incorrect information in dynamically changing environments and large variable spaces. Fuzzy modeling has the additional advantage that, with certain restrictions, interpretable models are obtained. However, especially for data-based approaches, there are still difficulties in generating efficiently interpretable rule bases with the required accuracy. Moreover, particularly with regard to complex applications, efficiency, interpretability, and accuracy are often partly contradictory modeling objectives. The main focus of this contribution is on determining an adequate compromise in this conflict area. The applicability of the concepts presented is demonstrated by means of complex real-world applications in the domains of power management control, classification in quality control, and prediction in financial service.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
J. Albrecht. Vorausschauende optimale Steuer-und Regelstrategien zur Verbesserung der Kraftwerksführung. Fortschritt-Berichte VDI, Reihe 8, Nr. 616. VDI Verlag, Düsseldorf, 1997.
J. Albrecht, K. Albers, and P. Stelzner. Sequentielle vorausschauende Vorsteuerung eines Kraftwerksparks durch ein Führungssystem. at-Automatisierungstechnik, 44 (8): 381–390, 1996.
J. Albrecht, H. Kiendl, A. Michalske, K. Albers, and P. Stelzner. Verfahren zum Regeln der Leistung eines Kraftwerksparks, 1995. Patent, DE 195 10 342.
Th. Bäck, U. Hammel, and H.-P. Schwefel. Evolutionary computation: Comments on the history and current state. IEEE Transactions on Evolutionary Computation, 1:1-15, 1997.
J.C. Bezdek. Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New York, 1981.
S. Blochwitz and J Eigermann. Creation and application of fuzzy rules to access the creditworthiness of enterprises. In Proceedings of the Fourth European Congress on Intelligent Techniques and Soft Computing (EUFIT `99), volume CD-ROM. Verlag Mainz, Aachen, 1999.
O. Cordon, A. Gonzalez, F. Herrera, and R. Perez. Encouraging cooperation in the genetic iterative rule learning approach for qualitative modeling. In Computing with Words in Information/Intelligent Systems, pages 95–117. Physica-Verlag, Heidelberg, 1999.
K. Honczarenko, A. Jardzioch, A. Piegat, and J Honczarenko. Application of soft computing method to Parkinson’s disease therapy. In Proceedings of the Fourth European Congress on Intelligent Techniques and Soft Computing (EUFIT `99), volume CD-ROM. Verlag Mainz, Aachen, 1999.
H. Jessen. Test-und Bewertungsverfahren zur regelbasierten Modellierung und Anwendung in der Lastprognose. Fortschritt-Berichte VDI, Reihe 8, Nr. 836. VDI Verlag, Düsseldorf, 2000.
H. Jessen. Test and rating strategies for automatic fuzzy rule generation and application to load prediction. In M. Mohammadian, editor, New Frontiers in Computational Intelligence and its Applications, pages 11–21. IOS Press, Amsterdam, 2000.
H. Jessen and T Slawinski. Mittelwertbasierter Regeltest und Bewertung für das Fuzzy-ROSA-Verfahren und Anwendung zur Lastprognose. In Tagungsband des 8. Workshops Fuzzy Control, number 0298, pages 67–81. VDI/VDE GMA-FA 5. 22, Faculty of Electrical Engineering and Information Technology, University of Dortmund, 1998.
H. Jessen and T. Slawinski. Test and rating strategies for data-based rule generation. Technical Report CI-39/98, Collaborative Research Center 531, University of Dortmund, 1998.
E. Juuso, D. Schauten, T. Slawinski, and H. Kiendl. Combination of linguistic equations and the fuzzy-ROSA method in dynamic simulation of a solar collector field. In Proceedings of TOOLMET2000 Symposium–Tool Environments and Development Methods for Intelligent Systems, pages 63–77. Oulun Yliopistopaino, Oulu, Finland, 2000.
H. Kiendl. Implizite Modellierung, inkrementeller Relevanzindex und Rauigkeitsmaß: neue Strategieelemente für die datenbasierte Modellierung. In Tagungsband des 10. Workshop Fuzzy Control des GMA-FA 5.22, pages 114. VDI/VDE GMA-FA 5.22, Research Reports Forschungszentrum Karlsruhe (FZKA 6509), Karlsruhe, 2000.
H. Kiendl. Verfahren zur Erzeugung von Stellgrößen am Ausgang eines Fuzzy-Reglers und Fuzzy-Regler hierfür. Technical report, 1994. Patent, DE 43 08 083.
H. Kiendl. System of controlling or monitoring processes or industrial plants employing a dual-line fuzzy unit. Technical report, 1998. Patent, U.S. 5,826, 251.
H. Kiendl. Decision analysis by advanced fuzzy systems. In J. Kacprzyk L. Zadeh, editor, Computing with Words in Information/Intelligent Systems, pages 223–242. Physica-Verlag, Heidelberg, 1999.
H. Kiendl and J. Albrecht. Verfahren zur sequentiellen Vorsteuerung eines Prozesses, 1997. Patent, DE 195 10 343.
H. Kiendl and W. Hansen. Quadratische Optimierung unter Nebenbedingungen und Anwendung in der Kraftwerksführung. Technical Report CI-119/02, Collaborative Research Center 531, University of Dortmund, 2002.
R. Klinkenberg and T. Slawinski. Wissensmanagement in der Computational Intelligence: Systematisierung der Beschreibung von Problemen, Methoden und Methodeneinsätzen. In Proceedings 11. Workshop Fuzzy Control des GMAFA 5.22, Dortmund, pages 78–99. VDI/VDE GMA-FA 5.22, Research Reports Forschungszentrum Karlsruhe (FZKA 6660), Karlsruhe, 2001.
P. Krause. Generierung von Takagi-Sugeno-Fuzzy-Systemen aus relevanten Fuzzy-Regeln. In Proceedings 10. Workshop Fuzzy Control des GMA-FA 5.22, Dortmund, pages 84–97. VDI/VDE GMA-FA 5.22, Research Reports Forschungszentrum Karlsruhe (FZKA 6509), Karlsruhe, 2000.
P. Krause. Datenbasierte Generierung von transparenten und genauen Fuzzy-Modellen für mehrdeutige Daten und komplexe Systeme. Fortschritt-Berichte VDI, Reihe 10, Nr. 691. VDI Verlag, Düsseldorf, 2001.
P. Krause, A. Krone, and T. Slawinski. Fuzzy System Identification by Generating and Evolutionary Optimizing Fuzzy Rule Bases Consisting of Relevant Fuzzy Rules. Technical Report CI-84/00, Collaborative Research Center 531, University of Dortmund, 2000.
P. Krause and T. Slawinski. Das Fuzzy-ROSA-Verfahren: Von der regelorientierten statistischen Analyse zur datenbasierten Generierung von interpretierbaren Takagi-Sugeno-Systemen. at-Automatisierungstechnik, 9 (49): 391–399, 2001.
P Krause, D. Wiesmann, and T. Slawinski. Parallel evolutionary algorithms for optimizing data-based generated fuzzy systems. Technical Report CI-101/00, Collaborative Research Center 531, University of Dortmund, 2000.
T. Kretschmer, T. Born, C Gierend, and M. Born. Automatische Generierung von Fuzzy-Systemen in Verbrennungsprozessen. In Tagungsband 5tes Nationales DataAnalysis Symposium, pages 45–50. MIT GmbH, Aachen, 1999.
A. Krone. Advanced rule reduction concepts for optimizing efficiency of knowledge extraction. In Proceedings of the Fourth European Congress on Intelligent Techniques and Soft Computing (EUFIT `96), volume 2, pages 919–923. Verlag Mainz, Aachen, 1996.
A. Krone. Datenbasierte Generierung von relevanten Fuzzy-Regeln zur Modellierung von Prozesszusammenhängen und Bedienstrategien. Fortschritt-Berichte VDI, Reihe 10, Nr. 615. VDI Verlag, Düsseldorf, 1999.
A. Krone, T. Bäck, and P. Teuber. Evolutionäres Suchkonzept zum Aufstellen signifikanter Fuzzy-Regeln. at-Automatisierungstechnik, 44 (8): 405–411, 1996.
A. Krone, C. Frenck, and O. Russak. Design of a fuzzy controller for an alkoxylation process using the ROSA method for automatic rule generation. In Proceedings of the Third European Congress on Intelligent Techniques and Soft Computing (EUFIT ‘85), volume 2, pages 760–764. Verlag Mainz, Aachen, 1995.
A. Krone and H. Kiendl. Automatic generation of positive and negative rules for two-way fuzzy controllers. In Proceedings of the Second European Congress on Intelligent Techniques and Soft Computing (EUFIT ‘84), volume 1, pages 438–447. Verlag Mainz, Aachen, 1994.
A. Krone and H. Kiendl. WINROSA von Daten zu Regeln. MIT-Managment Intelligenter Technologien GmbH, Aachen, 1st edition, 1997. Manual.
A. Krone, P. Krause, and T. Slawinski. A new rule reduction method for finding interpretable and small rule bases in high dimensional search spaces. In Proceedings of the Ninth IEEE International Conference on Fuzzy Systems, (FUZZ-IEEE ‘00), San Antonio, TX, volume 2, pages 696–699. IEEE Press, Piscataway, NJ, 2000.
A. Krone, P. Krause, T. Slawinski, and R. Knicker. WINROSA 2.0 and DORA for Windows 6.2. In Symposium on System Identification (SYSID 2000), Santa Barbara, CA, pages 521–526. Elsevier Science, Amsterdam, 2000.
A. Krone and U. Schwane. Generating fuzzy rules from contradictory data of different control strategies and control performances. In Proceedings of the Fifth IEEE International Conference on Fuzzy Systems (FUZZ-IEEE ‘86), New Orleans, volume 1, pages 492–497. IEEE Press, Piscataway, NJ, 1996.
A. Krone and T. Slawinski. Data-based extraction of unidimensional fuzzy sets for fuzzy rule generation. In Proceedings of the Seventh IEEE International Conference on Fuzzy Systems (FUZZ-IEEE ‘88), Anchorage, AK, volume 2, pages 1032–1037. IEEE Press, Piscataway, NJ, 1998.
A. Krone and T. Slawinski. A distance measure for the mutation of fuzzy-rules. Technical Report CI-83/00, Collaborative Research Center 531, University of Dortmund, 2000.
A. Krone and H. Taeger. Relevance test for fuzzy rules. Technical Report CI-40/98, Collaborative Research Center 531, University of Dortmund, 1998.
A. Krone and H. Taeger. Data-based fuzzy rule test for fuzzy modelling. Fuzzy Sets and Systems, 126: 343–358, 2001.
K. Linke. Kraftwerksführungssystem der Verbundebene - Struktur, Entwicklungsstand, neue Konzepte. In FGE-Tagung 1996, pages 618–624. Energiewirtschaft und Technik Verlagsgesellschaft mbH, Essen, Energiewirtschaftliche Tagesfragen, Heft 10/1996, 1996.
W. Pedrycz. Fuzzy Control and Fuzzy Systems. Research Studies LTD, Taunton, UK, 1993.
B. M. Pfeiffer, J. Jäkel, A. Kroll, C. Kuhn, H. B. Kuntze, B. Lehmann, T. Slawinski, and V. Tews. Tutorial: Erfolgreiche Anwendungen Fuzzy Control. In Proceedings 11. Workshop Fuzzy Control des GMA-FA 5.22, Dortmund, pages 1–27. VDI/VDE GMA-FA 5.22, Research Reports Forschungszentrum Karlsruhe (FZKA 6660), Karlsruhe, 2001.
J. Praczyk. Entwurf von Fuzzy-Gütemaßen zur Prozeßbewertung. Fortschritt-Berichte VDI, Reihe 8, Nr. 796. VDI Verlag, Düsseldorf, 1999.
J. Praczyk, H. Kiendl, and T. Slawinski. Finding relevant process characteristics with a method for data-based complexity reduction. In B. Reusch, editor, Computational Intelligence: Theory and Applications (Proceedings of 6th Fuzzy-Days), pages 548–555. Springer, Berlin, 1999.
D. Schauten, B. Nicolaus, and H. Kiendl. Evolutionäres Verfahren zur Selektion relevanter Merkmalssätze für die datenbasierte Fuzzy-Modellierung. In Proceedings 11. Workshop Fuzzy Control des GMA-FA 5.22, Dortmund, pages 133147. VDI/VDE GMA-FA 5.22, Research Reports Forschungszentrum Karlsruhe (FZKA 6660), Karlsruhe, 2001.
D. Schauten, B. Nicolaus, and H. Kiendl. An evolutionary concept for selecting relevant sets of input variables for data-based fuzzy modeling. In Proceedings of the European Symposium on Intelligent Technologies, Hybrid Systems and their Implementation on Smart Adaptive Systems (E UNITE `01), volume CD-ROM. Verlag Mainz, Aachen, 2001.
D. Schauten, T. Slawinski, and H. Kiendl. Datenbasierte Generierung von situationsbezogenen Entscheidungsregeln für die Kraftwerksführung. Technical Report CI-110/01, Collaborative Research Center 531, University of Dortmund, 2001.
U. Schwane. Datenbasierte Generierung von Adaptionsregeln und Anwendung zur Erhöhung der Bahngenauigkeit eines Industrieroboters. Fortschritt-Berichte VDI, Reihe 8, Nr. 748. VDI Verlag, Düsseldorf, 1999.
T. Slawinski. Analyse und effiziente Generierung von relevanten Fuzzy Regeln in hochdimensionalen Suchräumen. Fortschritt-Berichte VDI, Reihe 10, Nr. 686. VDI Verlag, Düsseldorf, 2001.
T. Slawinski, H. Jessen, J. Praczyk, P. Krause, A. Krone, and H. Kiendl. Einsatz der datenbasierten Fuzzy-Modellierungen für komplexe Anwendungen. In Computational Intelligence im industriellen Einsatz, Tagung Baden-Baden, VDI-Berichte, Nr. 1526, pages 119–124. VDI/VDE GMA und GI, VDI-Verlag, Düsseldorf, 2000.
T. Slawinski, P. Krause, and H. Kiendl. Using individually tested rules for the data-based generation of interpretable rule bases with high accuracy. In J. Casillas, O. Cordon, F. Herrera, and L. Magdalena, editors, Trade-off Between Acuracy and Interpretability in Fuzzy Rule-Based Modeling, page (Accepted). Physica-Verlag, Heidelberg, 2002.
T. Slawinski, P. Krause, A. Krone, U. Hammel, and D. Wiesmann. Fuzzy Adaption der evolutionären Regelsuche im Fuzzy-ROSA-Verfahren. In Tagungsband des 9. Workshops Fuzzy Control des GMA-FA 5.22, Dortmund, number 0499, pages 14–39. VDI/VDE GMA-FA 5. 22, Faculty of Electrical Engineering and Information Technology, University of Dortmund, 1999.
T. Slawinski, A. Krone, U. Hammel, D. Wiesmann, and P. Krause. A hybrid evolutionary search concept for data-based generation of relevant fuzzy rules in high dimensional spaces. In Proceedings of IEEE International Conference on Fuzzy Systems (FUZZ-IEEE ‘89) Seoul, volume 3, pages 1432–1437. IEEE Press, Piscataway, NJ, 1999.
T. Slawinski, A. Krone, U. Hammel, D. Wiesmann, and M. Lindenblatt. A hybrid evolutionary search concept for data-based generation of relevant fuzzy rules in high dimensional spaces (extended version). Technical Report CI-50/98, Collaborative Research Center 531, University of Dortmund, 1998.
T. Slawinski, A. Krone, and H. Kiendl. Automatisierung durch datenbasierte Fuzzy-Modellierung von Prozessbedienern. In Computational Intelligence: neuronale Netze, evolutionäre Algorithmen, Fuzzy-Control im industriellen Einsatz, Tagung Berlin, 1998, VDI-Berichte, Nr. 1381, pages 203–219. VDI/VDE GMA, VDI-Verlag, Düsseldorf, 1998.
T. Slawinski, A. Krone, and P. Krause. Efficient design of a complete rule search in sparsely populated search spaces. Technical Report CI-77/99, Collaborative Research Center 531, University of Dortmund, 1999.
T. Slawinski, A. Krone, P. Krause, and H. Kiendl. The fuzzy-ROSA method: A statistically motivated fuzzy approach for data-based generation of small interpretable rule bases in high-dimensional search spaces. In M. Last, A. Kandel, and H. Bunke, editors, Data Mining and Computational Intelligence, pages 141–166. Physica-Verlag, Heidelberg, 2001.
T. Slawinski, J. Praczyk, U. Schwane, A. Krone, and H. Kiendl. Data-based generation of fuzzy rules for classification, prediction and control with the fuzzy-ROSA method. In European Control Congress (ECC ‘89), Karlsruhe, volume CD-ROM. Karlsruhe, 1999.
N. Thomaidis, G. Dounias, and Tselentis. Stock exchange market analysis using data engine and WINROSA. In Proceedings of the Fourth European Congress on Intelligent Techniques and Soft Computing (EUFIT `99), volume CD-ROM. Verlag Mainz, Aachen, 1999.
G. Vachkov. Fuzzy modeling examples by WINROSA. In Proceedings of the 2nd DataAnalysis Symposium. MIT GmbH, Aachen, 1998. Artikel Nr. 25299.
N. Xion. Designing Compact and Comprehensible Fuzzy Controllers Using Genetic Algorithms (Entwurf kompakter und interpretierbarer Fuzzy Controller mittels Genetischer Algorithmen). Berichte aus der Automatisierungstechnik. Shaker Verlag, Aachen, 2001.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kiendl, H., Krause, P., Schauten, D., Slawinski, T. (2003). Data-Based Fuzzy Modeling for Complex Applications. In: Schwefel, HP., Wegener, I., Weinert, K. (eds) Advances in Computational Intelligence. Natural Computing Series. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-05609-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-662-05609-7_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-07758-6
Online ISBN: 978-3-662-05609-7
eBook Packages: Springer Book Archive