Self-organization of fuzzy logic controller using fuzzy auto-regressive moving average (FARMA) model

A complete design method is proposed for self-organization of a fuzzy logic controller without using any plant model. Following the human learning process, the control algorithm finds control rules of a system for which little knowledge has been known. In conventional fuzzy logic control, knowledge on the system supplied by an expert is required in developing control rules. However, the proposed new fuzzy logic controller needs no expert in making control rules. Instead, rules are generated using the history of input-output data, and the new inference and defuzzification methods are developed. The generated rules are stored in the fuzzy rule space and updated online by a self-organization procedure. The validity of the proposed fuzzy logic-control method is demonstrated numerically in controlling an inverted pendulum.