Radial basis function implementation of intelligent pressure sensor on field programmable gate array

Abstract

Artificial neural network is a promising area in the development of intelligent sensors. In this paper, we present an implementation of intelligent pressure sensor based on radial basis function (RBF) neural network. The intelligent pressure sensor system is implemented using commercial force and temperature sensors and Celoxica RC203 development board with Xilinx Virtex-II FPGA chip. The RBF neural network is trained to approximate the response characteristics of the pressure sensor for different level of temperatures so as to compensate for the non-linearity. The intelligent sensor system can compensate non-linear response due to its operating conditions over the temperature range of 12 to 80degC. The experimental results show that the system is able to achieve plusmn2.8% maximum full scale error over this temperature range with very fast training.