Generating fuzzy rules from contradictory data of different control strategies and control performances

Krone, A.; Schwane, U.

doi:10.1109/fuzzy.1996.551790

Cited by 16 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Each fact has a degree of membership.The systems can handle contradictory data, i.e. some consequents may define forbidden areas for the outputs [28,29].…”

Section: Rule-based Fuzzy Set Systemsmentioning

confidence: 99%

Expertise and Uncertainty Processing with Nonlinear Scaling and Fuzzy Systems for Automation

Juuso

2020

Open Engineering

View full text Add to dashboard Cite

Integration of domain expertise and uncertainty processing is increasingly important in automation solutions which rely on data analytics and artificial intelligence. We need a level to assess what is approximately correct. Uncertainties of the inputs are taken into account by using fuzzy numbers as the inputs of different fuzzy and parametric systems. Nonlinear scaling functions (NSFs) integrate these solutions and make them easier to tune. Fuzzy rule-based systems are represented with scaled fuzzy inputs. Membership functions (MFs) can be developed from NSFs and existing MFs can be used in developing NSFs. Fuzzy set systems and linguistic equation (LE) systems become consistent within the limits of detail. In recursive analysis, both meanings and interactions on all levels can be tuned together with genetic algorithms. In applications, the modular overall system consists of similar subsystems, which are normally used, with extensions to fuzzy. The compact fuzzy modules can be developed for specific tasks which are combined within Cyber Physical Systems (CPS). Uncertainty processing is embedded in the recursive analysis. The fuzzy extensions provide a feasible way for the sensitivity analysis of the solution.

show abstract

“…Each fact has a degree of membership.The systems can handle contradictory data, i.e. some consequents may define forbidden areas for the outputs [28,29].…”

Section: Rule-based Fuzzy Set Systemsmentioning

confidence: 99%

Expertise and Uncertainty Processing with Nonlinear Scaling and Fuzzy Systems for Automation

Juuso

2020

Open Engineering

View full text Add to dashboard Cite

show abstract

“…• Regleradaption für einen Industrieroboter [20] • Reglerentwurf für einen chemischen Prozess [16] • Automatisierung der Trennung von Bildröhren [16] • Prognose der elektrischen Last [10] • Qualitätskontrolle von Automatikgetrieben [27] • Vorhersage der Versicherungsvertragsdauer [27] • Analyse des griechischen Aktienindex [29] • Kreditwürdigkeit von Unternehmen [1] • Medikamentendosierung [8] …”

Section: Anwendungenunclassified

Das Fuzzy-ROSA-Verfahren: Von der regelorientierten statistischen Analyse zur datenbasierten Generierung von interpretierbaren Takagi-Sugeno-Systemen (The Fuzzy–ROSA Method: From the Rule–Oriented Statistical Analysis to Data–Based Generation of Interpretable Takagi–Sugeno Systems)

Krause¹,

Slawinski²

2001

Auto

View full text Add to dashboard Cite

Data-Minings und insbesondere der datenbasierten Modellierung hat im Bereich der Automatisierungstechnik in den letzten Jahren einen regelrechten Boom erfahren. Die Gründe hierfür sind zum einen das Bedürfnis der Anwender nach Modellen für immer komplexere Systeme. Zum anderen ergeben sich aufgrund leistungsfähigerer Rechnersysteme und der Entwicklung neuer Methoden, besonders aus dem Bereich der Computational Intelligence, vielfältige Möglichkeiten, auch solche Probleme zu lösen, für die herkömmliche Lösungsansätze bisher nicht erfolgreich waren. Aus Akzeptanzgründen werden in der industriellen Praxis häufig interpretierbare Modelle gefordert. Zudem weisen sie den Vorteil auf, dass mit ihnen vorhandenes Wissen integriert und in datenbasierten Ansätzen neues Wissen extrahiert werden kann. Ein Verfahren zur datenbasierten Fuzzy-Modellierung, das sich insbesondere dann bewährt hat, wenn kompakte interpretierbare Regelsätze für komplexe Problemstellungen automatisch generiert werden sollen, ist das Fuzzy-ROSAVerfahren. In diesem Beitrag wird das Fuzzy-ROSA-Verfahren zunächst in seiner jetzigen Form vorgestellt. Dann wird genauer auf jüngste Weiterentwicklungen eingegangen, die zu einem sehr viel breiteren Anwendungsfeld geführt haben. Es wird gezeigt, wie mit neuen Regeltestund Bewertungsstrategien unterschiedliche Modellierungsziele berücksichtigt und welche Suchraumgrößen aufgrund der Effizienzsteigerung der Regelsuche bearbeitet werden kön-nen. Des Weiteren wird die insbesondere aus methodischer Sicht interessante Erweiterung des Fuzzy-ROSA-Verfahrens zur Generierung interpretierbarer Takagi-Sugeno-Systeme mit hoher Modellierungsgüte ausführlich vorgestellt.The use of data mining methods, especially data-based modeling, in the field of automation has experienced a boom over the last years. On the one hand the users are in need of models for systems with growing complexity. On the other hand there are new possibilities of solving problems, where common solving strategies failed, because of the increasing capacity of computer systems and the availability of new methods, especially in the field of computational intelligence. In many cases interpretable models are required to be accepted in industry. Moreover, interpretable models have the advantage that available knowledge can be easily integrated and with data-based methods new information can be gained. A method which has proven to be very efficient when it comes to generate automatically compact and interpretable small fuzzy rule bases is the Fuzzy-ROSA method. In this paper we show the present state of the Fuzzy-ROSA method and then we present in detail current research activities, which led to a far wider area of applications. We demonstrate how new test and rating strategies consider different modeling objectives and how the efficiency of the rule search is increased by new search methods. At last we present in detail an extension to the Fuzzy-ROSA method which generates interpretable Takagi-Sugeno systems with high modeling accuracy.

show abstract

“…Most systems based on interval type-2 fuzzy sets are reduced to an interval-valued type-1 fuzzy set. Fuzzy set systems can also handle contradictory data (Krone and Kiendl, 1994;Krone and Schwane, 1996). Takagi-Sugeno (TS) fuzzy models (Takagi and Sugeno, 1985) combine fuzzy rules and local lineal models.…”

Section: Introductionmentioning

confidence: 99%

Recursive Data Analysis in Large Scale Complex Systems

Juuso¹

2018

Linköping Electronic Conference Proceedings

View full text Add to dashboard Cite

Advanced data analysis is needed in practical applications in large scale complex systems. Variable specific datadriven solutions provide consistent levels, which can be used in compact model structures. In changing operating conditions, the recursive analysis extends the applicability of these structures in building and tuning dynamic and case-based models for complex systems since the meanings change more frequently than the interactions. The methodology provides information about uncertainty, fluctuations and confidence in results. The scaling approach brings temporal analysis to all measurements and features: trend indices are calculated by comparing the averages in the long and short time windows, a weighted sum of the trend index and its derivative detects the trend episodes and severity of the trend is estimated by including also the variable level in the sum. The trend episodes and temporal adaptation of the scaling functions with time are used in the early detection of changes in the operating conditions. The levels are understood as fuzzy labels and the decision making is based on fuzzy calculus. The solution is highly compact: all variables, features and indices are transformed to the range [-2, 2] and represented in natural language which is important in integrating datadriven solutions with domain expertise.

show abstract

Generating fuzzy rules from contradictory data of different control strategies and control performances

Cited by 16 publications

References 1 publication

Expertise and Uncertainty Processing with Nonlinear Scaling and Fuzzy Systems for Automation

Expertise and Uncertainty Processing with Nonlinear Scaling and Fuzzy Systems for Automation

Das Fuzzy-ROSA-Verfahren: Von der regelorientierten statistischen Analyse zur datenbasierten Generierung von interpretierbaren Takagi-Sugeno-Systemen (The Fuzzy–ROSA Method: From the Rule–Oriented Statistical Analysis to Data–Based Generation of Interpretable Takagi–Sugeno Systems)

Recursive Data Analysis in Large Scale Complex Systems

Contact Info

Product

Resources

About