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

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.

[1]  Adriaan van den Bos,et al.  An ANN-based smart capacitive pressure sensor in dynamic environment , 2000 .

[2]  C. Xiang,et al.  From multilayer perceptrons to radial basis function networks: a comparative study , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[3]  I. Xilinx,et al.  Virtex-II Platform FPGA User Guide , 2002 .

[4]  Jagdish Chandra Patra,et al.  Neural-Network-Based Smart Sensor Framework Operating in a Harsh Environment , 2005, EURASIP J. Adv. Signal Process..

[5]  Adriaan van den Bos,et al.  Modeling and development of an ANN-based smart pressure sensor in a dynamic environment , 1999 .

[6]  Jagdish Chandra Patra,et al.  Field Programmable Gate Array Implementation of a Neural Network-based Intelligent Sensor System , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[7]  T. Martin McGinnity,et al.  Intrinsic and extrinsic implementation of a bio-inspired hardware system , 2004, Inf. Sci..

[8]  Yang Cai,et al.  Multisensor inversion with high-performance FPGA computation , 2003, Proceedings. 2003 IEEE International Conference on Field-Programmable Technology (FPT) (IEEE Cat. No.03EX798).

[9]  Sheng Chen,et al.  Orthogonal least squares methods and their application to non-linear system identification , 1989 .

[10]  Ganapati Panda,et al.  An intelligent pressure sensor using neural networks , 2000, IEEE Trans. Instrum. Meas..

[11]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[12]  Clive ldMax rd Maxfield,et al.  The design warrior's guide to FPGAs , 2004 .