A feature based solution to Forward Problem in Electrical Capacitance Tomography

A new feature-based technique is introduced to solve the nonlinear Forward Problem (FP) of the Electrical Capacitance Tomography (ECT) with the target application of monitoring the metal-fill profile in Lost Foam Casting (LFC) process. The new technique to solve the FP is based on key features extracted from the metal distributions and the Correction Factor (CF). The CF is predicted by an Artificial Neural Network (ANN) based on key distribution features. The CF adjusts the linear solution of the FP for nonlinear effects. The data for the ANN training was generated through ANSYS finite element analysis and the codes written in MATLAB. The ANN was implemented using MATLAB Neural Network Toolbox. This approach shows promising results. The ANN was able to learn the effect of these features on the CF with the % RMS error of 2.21 for training data. For the previously unseen test metal distributions, the average RMS error was 2.2%.

[1]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[2]  Q. Marashdeh,et al.  Nonlinear forward problem solution for electrical capacitance tomography using feed-forward neural network , 2006, IEEE Sensors Journal.

[3]  W. Deabes,et al.  A nonlinear fuzzy assisted image reconstruction algorithm for electrical capacitance tomography. , 2010, ISA transactions.

[4]  J. Griffin,et al.  Advanced lost foam casting technology. 1995 summary report , 1996 .

[5]  Steven W. Smith,et al.  The Scientist and Engineer's Guide to Digital Signal Processing , 1997 .

[6]  Daniel Svozil,et al.  Introduction to multi-layer feed-forward neural networks , 1997 .

[7]  F. Teixeira,et al.  Sensitivity matrix calculation for fast 3-D electrical capacitance tomography (ECT) of flow systems , 2004, IEEE Transactions on Magnetics.

[8]  Chih-Chen Chang,et al.  Adaptive neural networks for model updating of structures , 2000 .

[9]  I. L. Freeston,et al.  Analytic solution of the forward problem for induced current electrical impedance tomography systems , 1995 .

[10]  Lihui Peng,et al.  Image reconstruction algorithms for electrical capacitance tomography , 2003 .

[11]  Mohamed Abdelrahman,et al.  Monitoring metal-fill in a lost foam casting process. , 2006, ISA transactions.

[12]  Xin Yao,et al.  A Preliminary Study on Designing Artiicial Neural Networks Using Co-evolution , 1995 .

[13]  Brian S. Hoyle,et al.  Electrical capacitance tomography for flow imaging: system model for development of image reconstruction algorithms and design of primary sensors , 1992 .

[14]  Ø. Isaksen,et al.  A review of reconstruction techniques for capacitance tomography , 1996 .

[15]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[16]  W. A. Deabes,et al.  An Iterative Reconstruction Algorithm for Electrical Capacitive Tomography Using Fuzzy System , 2008 .

[17]  Charles E. Bates,et al.  Advanced Lost Foam Casting Technology , 2000 .

[18]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[19]  Janette B. Bradley,et al.  Neural networks: A comprehensive foundation: S. HAYKIN. New York: Macmillan College (IEEE Press Book) (1994). v + 696 pp. ISBN 0-02-352761-7 , 1995 .

[20]  P.K. Rajan,et al.  Characterization of Capacitive Sensors and Monitoring of Metal Fill in Lost Foam Casting , 2007, 2007 Thirty-Ninth Southeastern Symposium on System Theory.

[21]  Efstratios F. Georgopoulos,et al.  Intelligent Modeling of the Electrical Activity of the Human Heart , 2007 .