Intelligent backstepping control for linear induction motor drive

The design and properties of an intelligent backstepping control system for a linear induction motor (LIM) drive to track periodic reference trajector ies are studied. First, the dynamic model of a field-oriented control LIM d rive is derived. Then a feedback linearisation controller is designed in th e sense of the backstepping control technique. To relax the requirement for the bound of lumped uncertainty in the feedback linearisation control law, a recurrent fuzzy neural network (RFNN) uncertainty observer is proposed t o estimate the lumped uncertainty in real time. In addition, an online para meter training methodology derived using the Lyapunov stability theorem and the gradient descent method is proposed to increase the learning capabilit y of the RFNN. With the proposed intelligent backstepping control system, t he mover position of the LIM drive possesses the advantages of good transie nt control performance and robustness to uncertainties for the tracking of periodic reference trajectories. The effectiveness of the proposed control scheme is verified by both simulated and experimental results.