Int. J. Advanced Networking and Applications Volume: 14 Issue: 05 Pages: 5602 - 5608 (2023) ISSN: 0975-0290 5602 PCA based Sugeno Defuzzification Method for Modelling Tacit Knowledge in Power Plants D.S.Kalana Mendis Department of Information Technology, Advanced Technological Institute, Dehiwala, Sri Lanka. Email: kalana@sliate.ac.lk ------------------------------------------------------------------ABSTRACT------------------------------------------------------------------- This paper highlights usability of PCA based Defuzzification for the improvement of Sugeno Defuzzification method for knowledge modeling. Research presents designing and implementation of an intelligent system for knowledge modeling, classification and defuzzification. Knowledge is the key to management of ecological innovations in electric utilities of power plants. However, knowledge in the process of information gathering has not been modeled in a formalized way. The system has been evaluated by a sub field of power systems domain of electricity marketing in power plants. Although Sugeno defuzzification method is considered to be the most computationally effective, there is uncertainty about the defuzzified output, since it generates a singleton fuzzy values objectively and not well evaluated. A methodology for PCA based Defuzzification for Sugeno type inference systems has been used directly integrated with the principal component analyzer, fuzzy inference engine, knowledge base and user interface. The PCA based defuzzification system has been tested for modelling tacit knowledge for electric utilities in power plants as per renewable energy. The electric utility assessment tool based on a questionnaire to classify electric utilities (wind, biomass, and hydro) in percentages and identify electric utility performance index in power plants. The project highlights usability of fuzzy logic for designing and implementation of an intelligent system by principal component analysis for renewable energy modeling, classification and defuzzification. The experiment was conducted to investigate performance of PCA based approach with the Sugeno type inference systems. The accuracy of the PCA defuzzification approach is 98 %. Keywords – Sugeno Defuzzification, Principal Component Analysis, Tacit Knowledge, Fuzzy logic, Power plants ------------------------------------------------------------------------------------------------------------------------------------------------------- Date of Submission: January 15, 2023 Date of Acceptance: February 06, 2023 ----------------------------------------------------------------------------------------------------------------------------------------------------- I. INTRODUCTION The most popular defuzzification methods are the center of gravity method and the mean of maxima method, which are computationally inexpensive and easy to implement within fuzzy hardware chips although a full scientific reasoning has not been established. Many researchers have attempted to understand the logic of the defuzzification process. Yager and Filev contributed to the process of defuzzification from the perspective of invariant transformation between different uncertainty paradigms, including basic defuzzification distribution (Filev, etal., 1991; Yager, et al., 1994), semi- linear defuzzification (Yager, et al., 1993) and generalized level set defuzzification (Filev, et al., 1993). They all can be seen as an extension of the center of gravity method. Research has been also carried on the fast computation of the center of gravity defuzzification method (Wang, et al., 2000; Broekhoven, et al., 2006). It should be noted that with the developments of intelligent technologies, some adaptive and parameterized defuzzification methods that can include human knowledge have been proposed. (Saneifard Saneifard 2010) used neural networks for defuzzification. Since it is a more compact and computationally efficient representation than a Mamdani type fuzzy inference system, the Sugeno system lends itself to the use of adaptive techniques for constructing fuzzy models This is further explained as development of intelligent electric utility assessment system for power plants. It is mainly concerned with the development of electric utility assessment, model refinement, classification and defuzzification as features of the system for renewable electricity generation. 1.2 Problem statement Although so many defuzzification methods have been proposed so far, no one method gives a right effective defuzzified output for commonsense knowledge modeling. The computational results of defuzzification methods often conflict, and they don’t have a uniform framework in theoretical view.Most of the existing defuzzification methods attempt to make the estimation of a fuzzy set in an objective way. However, an important aspect of the fuzzy set application is that it can represent the subjective knowledge of the decision maker; different decision makers may have different perception for the defuzzification results. Although Sugeno type inference system is considered as the most computationally effective, there is uncertainty about defuzzified output, because it generates singleton fuzzy values objectively and not well evaluated. 2.0 REVIEW OF LITERATURE Zhang [1] propose a novel approach to using an improved genetic algorithm (IGA) combined with the dynamic autoregressive with outside input (ARX) Takagi-Sugeno (T- S) fuzzy model. The IGA algorithm automatically generates the input variable, the appropriate fuzzy if-then rules, and the