Design of an Observer for an XY Nano-Positioner using Neural Network

Nowadays, nano-precision positioning stages, have a special position and are used in a variety of applications, such as taking pictures and taking particles of the surface. In this paper,some observers for a nano-precision positioning platform are designed based on three different types of neural networks. The simulated platform was designed at Sharif University of Technology and, based on the system's final requirement for the feedback signal for use in the control rule, neural network observers were designed. In previous studies, the comsol model of the positioning system has been obtained. At this step, the neural network has used the Comsol model and the system has been trained for a sum of a number of sinusoidal functions, and its generalizability has been investigated for ramp input. Neural networks used include, respectively, a multi-layer perceptron network, a radial basis function network and a support vector regression network. By performing simulations, it has been seen that the multi-layer perceptron network and the radial basis function network yielded a good response with low error, but the support vector regression network has a relatively high error.