A decentralized adaptive neural controller (DANC) for active vehicle suspension systems using singular perturbation method is developed in this paper. In order to reduce the neural network (NN) weight’s number, the DANC is designed based on the decentralized single input single output (SISO) NN. The active suspension system SIMO characteristic is decoupled into two time-scale separated SISO systems via the singular perturbation technique for achieving a compromise between riding comfort and handing performance. The structure of this MIMO model-free controller is derived from the Lyapunov stability theory to monitor the system for tracking a user-defined reference model. The experimental results are discussed and compared with that of the passive suspension.

This content is only available via PDF.
You do not currently have access to this content.