Optimal Type-2 Fuzzy Controller for Anti-lock Braking Systems

Anti-lock Braking System (ABS) is a nonlinear and time varying systemincluding uncertainty, so it cannot be controlled by classic methods. Intelligentmethods such as fuzzy controller are used in this area extensively; howevertraditional fuzzy controller using simple type-1 fuzzy sets may not be robust enoughto overcome uncertainties. For this reason an interval type-2 fuzzy controller isdeveloped to improve the performance of ABS in presence of uncertainty such aschanging road condition. The output membership functions have been optimized byDiscrete Action Reinforcement Learning Automata (DARLA) technique. Simulationresults show the effectiveness of the proposed controller in comparison to type-1fuzzy controller.

کلیدواژه ها:

Anti-lock Braking System (ABS) ، Discrete Action Reinforcement Learning Automata (DARLA) ، Type-2 fuzzy controller