International Journal of Fuzzy Computation and Modelling (9 papers in press)
A new computational method for solving fully fuzzy nonlinear matrix equations
by Raheleh Jafari, Ahmad Jafarian
Abstract: Since the uncertainty in parameters can be transformed into fuzzy set theory, fuzzy set and fuzzy system theory are good tools to deal with uncertainty systems. The popularity related to fuzzy nonlinear systems has always shown an upward trend, and also incorporated with wide spread applications in industries. The solutions of them are applied to analyze many engineering problems. Multi formulations and computational methodologies have been suggested to extract solution related to fuzzy nonlinear programming problems. However, In some cases the methods which have been utilized in order to find the solution of these problems involve greater complexity. On the basis of the mentioned reason, the current research work is intended towards introduction of a simple method for finding the fuzzy optimal solution related to fuzzy nonlinear issues. The main idea is on the basis of employing nonlinear system with equality constraints in order to find nonnegative fuzzy number matrixes X ̃,X ̃^2,,X ̃^n which satisfies A ̃X ̃+C ̃X ̃^2+⋯+E ̃X ̃^n=B ̃ where A ̃,C ̃,,E ̃ and B ̃ are n
Keywords: Fuzzy solution; Fuzzy numbers; Fully fuzzy nonlinear system; Fully fuzzy matrix equations.
Implementation of Fuzzy-PID controller with Demand Response control to LFC Model in Real Time using Lab VIEW
by Vijaya Santhi Rajamahanthi, Srividya Devi P
Abstract: This paper presents real time simulation for single area power system with Demand Response (DR) to evaluate the performance of controller using LabVIEW. Here the mathematical model of LFC-DR for explorations is considered with external load disturbance are given in real time. In this, controller is checked non real time simulation environmental platform and transformed the controller into a real-time model controller, which is used for testing in real operating conditions. This simulation in real time provides a rapid solution for prototyping novel functions in different types of industrial processes and devices which are to be controlled in complex system. With the controller, simulation is carried out to monitor the results, i.e. the change in Frequency deviation, the response plots are obtained for 1% to 100% load disturbance. It shows better performance and superiority by using Fuzzy -PID Controller based LFC-DR single-area power system have over a classical controller under different operating scenarios
Keywords: Load Frequency Control; Demand Response; Fuzzy Logic Control; Pad.
Application of fuzzy inference techniques in the production of Eco-friendly Aminoplast based modied resins for plywood panel industries
by Sanghamitra Dey, Dipak Kumar Jana, Pijush K. Khatua, Anupam Mukherjee
Abstract: Aminoplast based resins are the important and most widely used adhesive in plywoodrnpanel industries. Environmental concerns and higher cost of petroleum based resins have resulted inrnthe development of technologies to replace melamine partially by biomaterials for the manufacturingrnof resin adhesive. This paper presents the development of melamine, animal glue formaldehydernresin as exterior grade binder. About 25% to 30% melamine was substituted by animal glue andrnoptimized. Input variables included pressure, temperature, pH, percentage of melamine, animalrnglue and formalin of the polymerisation reactors. Different strength properties (tensile strength,rnglue shear strength, internal bond strength) are considered as output variables. Statistical datarnanalysis is performed with some sensitivity analyses via neural network. This technique for thernproduction of bio based wood adhesive is cost effective, eco-friendly and could be an ideal solutionrnof petroleum based non-biodegradable resin adhesives.
Keywords: Adhesive; Fuzzy-logic; Fuzzy Inference System; Neural Network; Natural bio-based materials.
Availability of a Two-Unit Warm Standby System with Different Fuzzy Rayleigh Failure Rates
by Neama Temraz
Abstract: In the present paper, analysis of a two-unit warm standby system is introduced where the life and repair times are assumed to be fuzzy variables follow fuzzy Rayleigh distribution. Markov models are used to construct the mathematical model of the system. Analysis of the availability function of the model is introduced. A general expression for steady state availability is discussed. A numerical example is introduced for illustration.
Keywords: Availability; steady state availability; warm standby system; Markov models; Rayleigh distribution; different failure rates; fuzzy numbers.
Optimization by dual simplex approach in neutrosophic environment.
by TUHIN BERA, Nirmal Kumar Mahapatra
Abstract: In the present study, the coefficients of the objective function, technical coefficients, the right hand side coefficients and the decision variables in a crisp linear programming problem are considered as single valued neutrosophic numbers. Such type of linear programming problem is hereafter called a neutrosophic linear programming problem. The basic goal of this paper is to solve a neutrosophic linear programming problem by applying dual simplex method following the sense in crisp environment. In order to that, some necessary results are brought first and then an algorithm is developed. Finally, a classical problem has been solved to measure the efficiency of the proposed algorithm.
Keywords: Neutrosophic set; Single valued neutrosophic number; Neutrosophic linear programming problem; Dual simplex method.
INTERESTINGNESS MEASURES FOR QUANTIFIED AND ORDERED CATEGORICAL ATTRIBUTES USING FUZZY APPROACH
by Swati Ramdasi, Shailaja Shirwaikar, Vilas Kharat
Abstract: Fuzzy Association rules with its linguistic annotations and human interpretable form, hasrnnot only provided a convenient extension of association concepts to quantified attributesrnbut further broadened their applicability by combining extraction of both positive andrnnegative association rules. Interestingness measures are usedrnto filter out the right set of actionable association rules from the rules minedrnby association rule mining algorithms. This paper presents Support matrix using Fuzzy partitions, as a natural extension of contingency table for quantified and ordered categorical attributes so that the different interestingness measures can be defined in a uniform and consistent manner. It uses thernexisting interestingness measures defined in new form using fuzzy support to characterizerncomplimentary and substitute attributes and some new interestingness measures that measure the irrelevance of attribute data. Theoretical evaluation of various properties for interestingnessrnmeasures is carried out which helps in identifying representative set of eight measures.
Keywords: Interestingness measures; Association Rules mining; Fuzzy sets; support.
Development of Fuzzy Based Autoregressive Integrated Moving Average Exogenous Input(FARIMAX)Model for Filtration Process
by Dauda Araromi, Olajide Ajala, Aminah Sulayman
Abstract: Development of black-box model for filtration process has been carried out in this work. Data needed for the model development was obtained through experimental study on filtration unit using aqueous calcium carbonate (CaCO3) slurry. The input and output data generated from the experiment consisted of one manipulated variable (feed pressure, Pr), one disturbance variable (concentration of the solute in the feed, CA0) and one controlled variable (suspension concentration, CA). The data were used to develop a fuzzy model based on autoregressive integrated moving average exogenous input (FARIMAX) structure. Model order selection was carried out based on trial and error while optimal model order was determined using factorial technique. The performance of the developed model was determined using root mean square error (RMSE), coefficient of determination (R2) and model fit. The model gave optimal order [3 3 3 3 1], RMSE (1.855
Keywords: Fuzzy model;FARIMAX model; Black-box model; MATLAB; Modelling; ARIMAX; Filtration process.
Prediction of flood hazard map based on hybrid fuzzy geographic information system and its application for Ayamama Watershed
by Hussein BIZIMANA, Abdusselam Altunkaynak
Abstract: This research aims to bring a new methodology to early flood management and warning. It proposes modeling one of Istanbul watersheds, the Ayamama watershed in Istanbul, Turkey for possible flood hazard using a new fuzzy-Geographical Information System hybrid approach. It expands the domain of flood hazard early warning and management that usually uses conventional hydraulic and hydrology approaches to a newly developing area of artificial intelligence in flood early warning and management. The research opted for a more technical study using both GIS and MATLAB softwares to model the flood hazard levels in Ayamama watershed. The methodology takes into account three factors to model the flood hazard map. Elevation, Euclidian distance from Ayamama creek and local urbanization degree are the chosen factors. Results on how to identify flood hazard were demonstrated by providing a map of flood hazard zones with their respective negative levels of impacts.
Keywords: Fuzzy-GIS; Flood; hazard; prediction; Geographic Information System; Modelling.
Takagi-Sugeno Fuzzy PID Controllers: Mathematical Models and Stability Analysis with Multiple Fuzzy Sets
by Ritu Raj, Murali M. Bosukonda
Abstract: This paper deals with nonlinear Takagi-Sugeno (TS) fuzzy PID controllers with multiple fuzzy sets. Two models of fuzzy PID controllers are proposed using Algebraic Product (AP) triangular norm, Bounded Sum (BS)/Maximum (Max) triangular co-norm and Center of Gravity (CoG) defuzzifier. The inputs are fuzzified by three or more fuzzy sets with trapezoidal/triangular type membership functions. A new rule base is proposed consisting of four rules which reduce the number of tunable parameters. The models of the fuzzy PID controllers reveal that they are (nonlinear) variable gain/structure controllers, i.e. the gains are a function of input variables and the structure of the controller changes in the input space. The variations of gain and the properties of the controllers are investigated. The Bounded-Input Bounded-Output (BIBO) stability of the closed loop system with one of the proposed models in the loop is studied. The applicability of the controllers is demonstrated with the help of two examples.
Keywords: Fuzzy control; Takagi-Sugeno controller; Variable gain controller; Mathematical model; BIBO stability.