T-S cloud model for nonlinear systems control
Zhou Cong · Dianji yu kongzhi xuebao · 2009
The integration of cloud model and T-S fuzzy system was considered.The antecedents of the fuzzy system were replaced by the membership clouds.And a T-S cloud model was proposed.The T-S cloud model balances the trade-off between accuracy and interpretability.The system model can be designed not only through the expert knowledge and experience but also the input/output data.The structure of cloud model system was analyzed.The concept of fuzzy is consistent in cloud model and fuzzy systems.Therefore without considering the hyper-entropy,an iterative gradient-descent algorithm was used to update the antecedent parameters of the T-S cloud model.Then the consequent parameters were calculated by recursive least square method.A controller based on the T-S cloud model was developed to back up the truck.Simulation results show the effectiveness of the proposed method.