Inverse Identification of Circular Cavity in a 2D Object via Boundary Temperature Measurements Using Artificial Neural Network

Subject Areas : Journal of Simulation and Analysis of Novel Technologies in Mechanical Engineering

محمد امین احمدفرد ¹ , محمد جواد کاظم زاده پارسی ² , علیرضا تهور ³

1 - دانشجوی کارشناسی ارشد مهندسی مکانیک، دانشگاه آزاد اسلامی واحد شیراز، گروه مهندسی مکانیک.
2 - استادیار، دانشگاه آزاد اسلامی، واحد شیراز، گروه مهندسی مکانیک
3 - استادیار، دانشگاه آزاد اسلامی واحد شیراز، گروه مهندسی مکانیک

Received: 2015-09-30 Accepted : 2015-09-30 Published : 2010-06-22

Keywords: Neural network, Finite Element Method, Shape identification, Inverse heat transfer,

Abstract :

In geometric inverse problems, it is assumed that some parts of domain boundaries are not accessible and geometric shape and dimensions of these parts cannot be measured directly. The aim of inverse geometry problems is to approximate the unknown boundary shape by conducting some experimental measurements on accessible surfaces. In the present paper, the artificial neural network is used to solve these kinds of problems in conduction heat transfer in 2D objects. In order to train the neural network, some direct problems are solved by using the finite element method. In order to evaluate the applicability of the proposed method, different cases with different number of measuring points and different error levels are examined. The results show that the ANN can effectively be used in solving inverse geometry problems in heat conduction.

References:

[1] Ferreira M.D.C‏., Venturini W.S., Inverse analysis for two-dimensional structures using the boundary element method, Advances in Engineering Software, 41, 2010, pp. 1061-1072.

[2] Mera N.S., Elliott L., Ingham D.B., , Numerical solution of a boundary detection problem using genetic algorithms, Engineering Analysis with Boundary Elements, 28, 2004, pp. 405-411.

[3] Mehrjoo M., Khaji N., Moharramiand H., Bahreininejad A., Damage detection of truss bridge joints using Artificial Neural Networks, Expert Systems with Applications, 35, 2008, pp. 1122-1131.

[4] Park G., Park S., and Kim J. , Estimating the existence probability of cavities using integrated geophysics and a neural network approach, Computers & Geosciences, 36, 2010,pp. 1161-1167.

[5] Liu S.W., Huang j.h., Sung J.C., Lee. C., , Detection of cracks using neural networks and computational mechanics, Computer Methods in Applied Mechanics and Engineering, 191, 2002, pp. 2831-2845.

[6] Gupta S., Ray A., Keller E., Symbolic time series analysis of ultrasonic data for early detection of fatigue damage , Mechanical Systems and Signal Processing, 21, 2007, pp. 866-884.

[7] Hsieh C. K.,Kassab.  A. J., A general method for the solution of inverse heat conduction problems with partially unknown system geometries, International Journal of Heat and Mass Transfer, 29, 1986, pp. 47-58.

[8] Darabi A., Maldague X., , Neural network based defect detection and depth estimation in TNDE, NDT ,35, 2002, pp. 165-175

[9] Mera N. S.  , Elliott L.  , Ingham D. B., , the use of neural network approximation models to speed up the optimization process in electrical impedance tomography, Computer Methods in Applied Mechanics and Engineering, 197, 2007, pp. 103-114

[10] Mera N.  S., Elliott L.  , Ingham D.  B., Detection of subsurface cavities in IR-CAT by a real coded genetic algorithm, Applied Soft Computing, 2, 2002, pp. 129-139

[11] Rus G., Gallego R., Optimization algorithms for identification inverse problems with the boundary element method, Engineering Analysis with Boundary Elements, 26, 2002, pp. 315-327.

[12] Chamekh A., BelHadjSalah H.  , Hambli R.  , Gahbiche A.  , Inverse identification using the bulge test and artificial neural networks, Journal of Materials Processing Technology, 177, 2006, pp. 307-310.

[13] Hagan M., Demuth H. B., Beale M. , Neural Network Design, PWS. pub. Co., Dec. 1995, pp. 66-79.