Abstract: Aiming at the difficulties that the vibration response signal of the viscoelastic sandwich structure is strongly non-stationary and the change of vibration response signal caused by the change of aging state is weak， this paper proposes an intelligeat identification method for the aging state of the viscoelastic sandwich structure based on sparrow search algorithm （SSA） optimized variational mode decomposition （VMD） and adaptive neuro-fuzzy inference system （ANFIS）. The vibration response signals of different aging states of the viscoelastic sandwich structure are decomposed by the parameter-optimized VMD， and several intrinsic mode functions （IMFs） are obtained； The permutation entropy （PE） features of the obtained IMF components are computed， which are used to reflect the structural aging state change； The obtained permutation entropy features are constructed into feature vectors as inputs of ANFIS to realize the aging state intelligent iclentification of viscoelastic sandwich structure. The effectiveness of the method was verified through experiments， and compared with empirical mode decomposition （EMD） and ANFIS， parameter optimized VMD and radial basis function neural network （RBFNN） methods. The results show that the proposed method in this paper can more accurately identify the aging state of viscoelastic sandwich structure.