A new transformed input-domain ANFIS for highly nonlinear system modeling and prediction

Abdelrahim, Elsaid Md.; Yahagi, Toru

doi:10.1109/ccece.2001.933761

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 It can be noted that in the original proposal k = 2, but the model has since been extended in the context of real world cases where more regimes were required. This generalisation does not affect any of its properties, and we will assume it here.…”

Section: Regime-switching Autoregressive Modelsmentioning

confidence: 99%

“…This approach is fair, but ignores the special features that distinguish a time series from other sources of data, disregarding at the same time all the scientific knowledge gathered through years for this specific problem. Examples that illustrate this situation are the tests performed with models like ANFIS [10,9,1], EFuNN [12,13] or ANNBFIS [20]. More examples can be found in [8,15,30,22,19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Smooth transition autoregressive models and fuzzy rule-based systems: Functional equivalence and consequences

Aznarte

Benítez

Castro

2007

Fuzzy Sets and Systems

View full text Add to dashboard Cite

Section: Regime-switching Autoregressive Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Smooth transition autoregressive models and fuzzy rule-based systems: Functional equivalence and consequences

Aznarte

Benítez

Castro

2007

Fuzzy Sets and Systems

View full text Add to dashboard Cite

“…It is assumed for simplicity that the fuzzy inference system under consideration has two inputs x and y and one output z. Suppose that the rule base contains two fuzzy if-then rules of Takagi and Sugeno's type [23][24][25][26]. The given concept of ANFIS structure can be explained using a simple example whose rule base is given below.…”

Section: Power System Under Studymentioning

confidence: 99%

Simulation study of a SSSC-based neuro-fuzzy controller for improvement of transient stability in a three-machine power system

Khuntia

2012

2012 IEEE Energytech

View full text Add to dashboard Cite

In this article, computationally simple and accurate expert system, i.e., neuro-fuzzy system based on the artificial neural network (ANN) is applied to design a static synchronous series compensator (SSSC)-based controller for improvement of transient stability in a three-machine power system. The proposed neuro-fuzzy controller combines the advantages of fuzzy controller as well as quick response and adaptability nature of ANN. The neuro-fuzzy structures were trained using the generated database of fuzzy controller for SSSC. The results prove that the proposed SSSC-based neuro-fuzzy controller is found to be robust to fault location and change in operating conditions. A thorough comparison with the conventional leadlag controller is carried out, taking into account the results of previous publications. The SSSC-based neuro-fuzzy controller output provides promising results in terms of accuracy and computation time. Finally, conclusions are duly drawn.

show abstract

“…This adaptive network is functionally equivalent to a fuzzy inference system (FIS). Using a given input/output data set, ANFIS adjusts all the parameters using back propagation gradient descent and the least squares type of method for non-linear and linear parameters, respectively [15][16][17][18]. It is assumed for simplicity that the fuzzy inference system under consideration has two inputs x and y and one output z.…”

Section: Adaptive Neuro-fuzzy Inference System (Anfis) Approachmentioning

confidence: 99%

ANFIS approach for SSSC controller design for the improvement of transient stability performance

Khuntia

Panda

2013

Mathematical and Computer Modelling

View full text Add to dashboard Cite

Adaptive neuro-fuzzy inference system (ANFIS) Flexible ac transmission system (FACTS) Single machine infinite bus (SMIB) Static synchronous series compensator (SSSC) Transient stability a b s t r a c t In this paper, an Adaptive Neuro-Fuzzy Inference System (ANFIS) method based on the Artificial Neural Network (ANN) is applied to design a Static Synchronous Series Compensator (SSSC)-based controller for the improvement of transient stability. The proposed ANFIS controller combines the advantages of a fuzzy controller as well as the quick response and adaptability nature of an ANN. The ANFIS structures were trained using the generated database by the fuzzy controller of the SSSC. It is observed that the proposed SSSC controller improves greatly the voltage profile of the system under severe disturbances. The results prove that the proposed SSSC-based ANFIS controller is found to be robust to fault location and changes in operating conditions. Further, the simulation results obtained are compared with the conventional lead-lag controller under various disturbances, namely three-phase unbalanced faults and other unbalanced faults to show the effectiveness and robustness of the proposed approach for SSSC.

show abstract

A new transformed input-domain ANFIS for highly nonlinear system modeling and prediction

Cited by 7 publications

References 14 publications

Smooth transition autoregressive models and fuzzy rule-based systems: Functional equivalence and consequences

Smooth transition autoregressive models and fuzzy rule-based systems: Functional equivalence and consequences

Simulation study of a SSSC-based neuro-fuzzy controller for improvement of transient stability in a three-machine power system

ANFIS approach for SSSC controller design for the improvement of transient stability performance

Contact Info

Product

Resources

About