Title :
A polynomial fuzzy neural network for identification and control
Author :
Kim, Sungshin ; Vachtsevanos, George J.
Author_Institution :
Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
This paper introduces a new neuro-fuzzy system, an effective optimization method through a genetic algorithm, a performance criterion for model selection, and a numerical example to illustrate the proposed modeling and control approach. The neuro-fuzzy system is based on the polynomial fuzzy neural network architecture. A new performance criterion is defined based on the Group Method of Data Handling; it minimizes the output error while preventing overfitting of the empirical data set. The neuro-fuzzy model is employed to provide optimum set points for low-level control activity
Keywords :
data handling; fuzzy control; fuzzy neural nets; genetic algorithms; identification; modelling; neural net architecture; neurocontrollers; Group Method of Data Handling; data overfitting; genetic algorithm; identification; low-level control; model selection; neurofuzzy control; optimization method; output error minimization; performance criterion; polynomial fuzzy neural network; polynomial fuzzy neural network architecture; Computer networks; Fuzzy control; Fuzzy neural networks; Fuzzy systems; Inference algorithms; Input variables; Least squares approximation; Neural networks; Optimization methods; Polynomials;
Conference_Titel :
Fuzzy Information Processing Society, 1996. NAFIPS., 1996 Biennial Conference of the North American
Conference_Location :
Berkeley, CA
Print_ISBN :
0-7803-3225-3
DOI :
10.1109/NAFIPS.1996.534693
