Fuzzy-Neural Intelligent Control With Fixed-Time Pre-Configured Qualities for Electromechanical Dynamics of Electric Vehicles Motors

The control performance of permanent magnet brush (PMB) DC motors, which are essential components in electric vehicles, is crucial for ensuring the seamless and secure operation of these vehicles. This study investigates discrete-time fuzzy-neural intelligent control with fixed-time prescribed performance for the electromechanical dynamics of PMB DC motors. Unlike existing prescribed performance control (PPC) schemes designed for continuous-time systems, our approach introduces a more practical discrete-time version of PPC that guarantees system outputs with fixed-time preselected behaviors. This advancement addresses the technical limitations faced by current discrete-time PPC methods when managing dynamic systems with time-varying sampling intervals. To achieve this objective, we integrate an enhanced fuzzy-neural approximation technique with the back-stepping design to develop a low-computational discrete-time control protocol. Our method minimizes online learning parameters while circumventing the issue known as “explosion of terms”. Finally, we compare our proposed controller against several existing alternatives to demonstrate its effectiveness and superiority.