China
Africa
Explore chapters and articles related to this topic
Fuzzy Logic and AGC Systems
Published in Hassan Bevrani, Takashi Hiyama, Intellyigent Automatic Generation Control, 2017
Hassan Bevrani, Takashi Hiyama
Fuzzy rule is the basis of fuzzy logic operation to map the input space to the output space. Here, a rule base including forty-nine fuzzy rules is considered (Table 9.5). The rule base works on vectors composed of ACE and its gradient ΔACE. Using Table 9.5, fuzzy rules can be expressed in the form of if-then statements, such as: IfACE is SN and ΔACE is MP,then output is SN.
Strategies-challenges of engineering education
Published in J. P. Mohsen, Mohamed Y. Ismail, Hamid R. Parsaei, Waldemar Karwowski, Global Advances in Engineering Education, 2019
Fuzzy If-Then rules are constituted from two parts: antecedent parts and consequence part. A typical fuzzy rule in a fuzzy model has the form presented above where fuzzy terms are fuzzy linguistic values defining the linguistic variables. Quiz exam is poor and Final exam is good are antecedent part of a rule. Similarly, Student learning level is average is a conclusion or consequent part of a rule set.
Fuzzy Control for Food Processes
Published in Gauri S. Mittal, Computerized Control Systems in the Food Industry, 2018
A fuzzy rule set is a set of conditional statements relating fuzzy inputs/observations to control outputs. Actual process observations are not necessarily exact matches for rule antecedents (i.e., there can be partial belonging to more than one fuzzy input value). The inference procedure to determine the appropriate control output is a process of interpolation within the granules of the fuzzy graph.
Adaptive neuro-fuzzy inference systems (ANFIS) and artificial neural networks (ANNs) for optimizing electrospun PVA/TIO2 fiber diameter
Published in The Journal of The Textile Institute, 2022
Valentinus Galih Vidia Putra, Juliany Ningsih Mohamad
Where, is the membership function (MF) of x in C. The MF maps each W element to a membership value between 1 and 0. A Takagi Sugeno fuzzy inference systems (FIS) model was selected to train the network with 100 epochs. The model of 2-4-3 generalized bell membership functions was chosen for the FIS. The parameters associated with the membership functions vary through the learning process until optimum ones are obtained. A gradient vector method stimulates the computation of these parameters as in artificial neural networks. A gradient vector measures how well the FIS models the input and output data for a given set of parameters. Figure 4 shows the adaptive neuro-fuzzy inference systems (ANFIS) model plot. In this study, parameters of fiber diameter, such as solution concentration (x1), applied voltage (x2), and spinning distance (x3), were used as inputs to predict the fiber diameter (d), the output. After selecting the fuzzy set and the related membership functions, linguistic terms are used to develop the fuzzy rule. For 2-4-3 generalized bell membership functions, the following linguistic terms were used (Table 2).
Prediction of the unconfined compressive strength of stabilised soil by Adaptive Neuro Fuzzy Inference System (ANFIS) and Non-Linear Regression (NLR)
Published in Geomechanics and Geoengineering, 2022
Adaptive Neuro Fuzzy Inference System (ANFIS) is an integration of Artificial Neural Network (ANN) and fuzzy logic developed by Jang et al. (1997). Learning capabilities of ANN are employed in ANFIS efficiently so that simulation of system behaviour is possible. On the other hand, incorporation of fuzzy logic makes it possible to mimic complex behaviours, smoothly. Smoothness of response (output) is a major advantage of fuzzy models meaning that abrupt and high fluctuation in response due to input variation is not taken place. Smoothness is due to applying a concept called ‘membership function’. A membership function indicates the degree of belonging any numerical value to a specific level (for example: low, medium or high) of a variable. Further explanation of fuzzy concepts can be found in Jang et al. (1997). Fuzzy modelling also employs knowledge of experts in the form of fuzzy rules, efficiently. Each fuzzy rule explains an existing physical relationship among different levels of input and output variables in a model. In summary, ANFIS can be assumed as an estimator mapping the model inputs to corresponding outputs having advantages such as adaptive framework, smooth response and employing expert experiences.
Estimation of saturated hydraulic conductivity using fuzzy neural network in a semi-arid basin scale for murum soils of India
Published in ISH Journal of Hydraulic Engineering, 2018
Sathish Bahurao More, Paresh Chandra Deka
A fuzzy logic system is commonly defined as a system which emulates a human expert. A fuzzy controller consists of three operations: fuzzification, inference, and defuzzification. In the fuzzy logic system, the knowledge of the human is put in the form of a set of fuzzy linguistic rules. These rules would produce approximate decisions, just as a human would. The human expert observes quantities by observing the inputs, and leads to a decision or output using his judgment. The human expert can be replaced by a combination of a fuzzy rule-based system (FRBS) and a block called as defuzzifier. The inputs are fed into the fuzzy rule-based system, where physical quantities are represented into linguistic variables with appropriate membership functions. These linguistic variables are then used in a set of fuzzy rules within an inference engine, resulting in a new set of fuzzy linguistic variables. In the defuzzification stage, the variables are combined and changed to a crisp output which represents an approximation to actual output. For more details refer Cox (1994).