High precision ANN-based adaptive displacement tracking of piezoelectric actuators for MEMS

In this paper, we introduce an artificial neural network (ANN) based motion control methodology of micro actuators for microelectromechanical systems (MEMS). The control strategy is based on a multilayer perception (MLP) trained online using a Lyapunov-based learning technique. The controller achieves high precision tracking under unknown system dynamics including hysteresis and external disturbance. Unlike other ANN control strategies, no a priori offline training or weights initialization is required. Simulation results highlight the performance of the proposed controller in compensating for hysteresis effect. The controller is suitable for very large scale integration (VLSI) implementation and can be used to improve static and dynamic performances of nanopositioning systems.