A genetic-based fuzzy grey prediction model

Three different modeling techniques, i.e., genetic algorithm, fuzzy logic, and grey theory, are integrated to become a practical model for prediction purposes. The grey system is used to predict the next output from an unknown plant. Since the prediction error is inevitable, a fuzzy controller is designed to learn how to compensate for the output from the grey system. The roughly determined fuzzy rule base is then tuned by the genetic algorithms. The results show that the proposed technique outperforms the conventional grey system´s. Also, the proposed model demonstrates its simplicity in modeling, its applicability to real-world prediction problem, and its extension ability for future intelligent control