An adaptive control algorithm with rule-bases was developed for cell recycled continuous bioreactor. Ethanol fermentation by Saccharomyces cerevisiae was used as a model system. Since the developed algorithm employed the fermentation model, it was possible to estimate the physical state of the system. Five rule-bases were obtained from the experiments and used to adjust the control input. Good control performance was observed using a rule-based STR (self-tuning regulator) compared to the result using conventional STR. When disturbances were given, rule-based adaptive control scheme showed faster recovery of setpoint. The rule-based STR developed in this study was stable, robust and showed good tracking performance.