Design of Rule Adaptive Tuning Grey Prediction Fuzzy Control System

摘要

The paper combines the advantages of the grey prediction theory, fuzzy theory and the technology of online state evaluation tuning algorithm to design a rule adaptive tuning grey prediction fuzzy control system. These different forecasting step sizes are generated by a rule adaptive tuning mechanism in each sampling time. In rule adaptive tuning mechanism, a fuzzy inference system is used to dynamically generate appropriate forecasting step sizes for the grey predictor. A state evaluator is proposed to evaluate a scalar value to indicate the status of the current state, and to provide this value to a parameter modifier to tune the adjustable parameters. An on-line state evaluation tuning algorithm is proposed for a parameter modifier such that the fuzzy inference system has the adaptively tuning ability. The rule adaptive tuning grey prediction fuzzy control system structure is proposed so that the rise time and the overshoot of the controlled system can be maintained simultaneously. Finally, the inverted pendulum control problem is used to illustrate the effectiveness of the proposed control scheme.