J. Today’s Ideas - Tomorrow’s Technol.

Application of Artificial Neural Network to Analyze Hexagonal Plate with Hole Considering Different Geometrical and Loading Parameters

Saket Rusia, K. K. Pathak

  • Download PDF
  • DOI Number
    https://doi.org/10.15415/jotitt.2016.41001
KEYWORDS

Artificial Neural Networks; Finite Element Analysis; Hexagonal Plate; ANSYS

PUBLISHED DATE December 2015
PUBLISHER The Author(s) 2016. This article is published with open access at www.chitkara.edu.in/publications
ABSTRACT

In the competitive nature of structural engineering, industry and its heuristic problem-solving needs, among other reasons, have contributed to the development of some advanced decision making tools. A step ahead from soft computing techniques, now artificial intelligence has proved itself as an efficient tool for solving the problem in construction industry over old tedious analytical methods. In this study, Artificial Neural Network is compared with finite element techniques in order to find the stress, strain and deflection in plates with holes. For approaching the complexity of the problem, hexagonal plates with holes and different geometrical and loading parameters have been taken as specimens. Finite element analysis for 81 cases are carried out using the software based on finite element method (FEM), ANSYS Workbench 15.0 software. Using these data of FEM analysis an Artificial Neural Network has been trained. The successfully trained network is further used for analysis of four new cases which are also validated by using FEM based software. It was found that most of the results were quite close to the FEM results. Such a technique can be used to reduce the computation time and labour.

INTRODUCTION

Regardless of the powerful analysis software now available, the development of methods of approximate solution is very important. Although, these analysis software allow us to find out the numerical solution of various problems, including the problems of structural analysis. The need of approximate methods which would provide solutions in the form of simple analytic expressions is there. One of the method is artificial neural network also known as ANN. These are a functional abstraction of the biologic neural structures of the central nervous system.

ANNs are powerful pattern recognizers and classifiers. Garrett [1] has given an interesting engineering definition of the ANN as: “a computational mechanism able to acquire, represent, and compute mapping from one multivariate space of information to another, given a set of data representing that mapping.” Their computing abilities have been proven in the fields of prediction and estimation, pattern recognition, and optimization. Neural networks have been used for various structural analysis like fully stressed design of trusses, buckling behaviour of plates, stress concentration factor analysis for membranes etc.

In Figure 1, artificial neural network consisting of an input layer with four nodes, one hidden layers with five nodes, and an output layer with three nodes is shown. State function is summation function. Among transfer functions like sigmoid, modified sigmoid, hyperbolic tangent, Gaussian and modified Gaussian, hyperbolic tan-gent function has been used. Then, a training algorithm is needed that is back- propagation algorithm over here. Neurons are the processing elements of network. Neuron consists of a set of weighted input connections, a bias input, a state function, a nonlinear transfer function, an output. Figure 2 shows the structure of a neuron.

Further, Initialization method of threshold and initialization method of weight factor are to be chosen between zero or random, in our research, we have chose random.

P. Emmanuel Nicholas et al. [2] proposed a novel approach to study neural network based buckling strength prediction of laminated composite plate with central cut-out, The laminated composite plates with holes analyzed using finite element analysis by optimizing the parameters like thickness, orientation, material and the stacking sequence to obtain the desired characteristics for these structures. They showed that using finite element analysis makes the process more tedious job and thus proposed to construct the artificial neural network to predict the buckling behaviour of the composite plate. Hojjat Adeli [3] presented the first journal article on neural network application in civil/ structural engineering in 1989

In many previous research papers, membrane with holes or cutouts analysed using finite element software like ANSYS [4], ABAQUS etc., also the stress field around circular holes in plates with arbitrary thickness has been studied but most of the researches only plane loading is considered. However, it seems difficult to locate a work that quantifies the use of ANNs for analysis of equivalent stress, strain and directional deformation in a hexagonal plate subjected to vertical surface pressure without performing finite element analysis. The artificial neural network is used as an alternative analysis tool to analysis plates with hole since it can handle uncertainty through the probability method.

While comparing the artificial neural networking method with finite element method we have taken hexagonal plate with hole, it is to make problem much complex and to increase the number of variables. Different shaped plates with different shaped holes are used in industry to match the needs. Thus, it becomes necessary to use the method which excels in dealing with arbitrary shapes in less time and computational cost.

In some of the following research papers finite element analysis have been performed for plates and membranes with cut-outs. Zuxing Pan et al. [5], dealt with a complex variable method and proposed stress functions to obtain the solution for stress distribution around rectangular hole in finite plate subjected to uniaxial tension. They analyzed effect of hole sizes, hole orientation and plate’s aspect ratio on stress distribution. Jeom Kee Paik [6] examined the ultimate strength of metallic plates with central circular cut-out under shear loading. The influence of boundary conditions on the buckling load for rectangular plates of various cut-out shape, length/thickness ratio, and ply orientation was examined by Buket Okutan Baba [7]. Boundary conditions considered were clamped, pinned and their various combinations. The plates were subjected to in-plane compression load. The results of experimentation were validated using numerical analysis by ANSYS. A.V Singh [8], presented the results of their study which was based on generalized work–energy method for rectangular plates with circular cut-out. Optimum design of holes and notches by considering fatigue life were presented by Hwai Chung Wu et al. [9]. V.G. Ukadgaonker et al. [10] gave a general solution for bending of symmetric laminates with holes considering any shape of hole in symmetric laminates subjected to remotely apply bending or twisting moments. Moments around circular, elliptical, Triangular, square, rectangular and several irregular shaped holes in cross-ply and angle ply symmetric laminates are obtained.

In this study, artificial neural network has been employed for analysis of maximum equivalent von Mises stress, strain and directional deformation in equilateral Hexagonal plate with different geometrical and loading patterns. Plates, having different size concentric holes are analyzed. Finite element analysis for 81 cases are carried out using ANSYS Workbench 15.0 software. Using these data of FEM analysis an artificial neural network has been trained. The successfully trained network is further used for analysis of five new cases which are also validated using ANSYS Workbench 15.0 software.

Page(s) 1–13
URL http://dspace.chitkara.edu.in/jspui/bitstream/1/740/3/001_JOTITT_Saket%20Rusia.pdf
ISSN Print : 2321-3906, Online : 2321-7146
DOI https://doi.org/10.15415/jotitt.2016.41001
CONCLUSION

In this study, linear elastic analysis of steel plates is performed, and results have been predicted using artificial neural network. The differences calculated between the maximum equivalent von Mises stress, strain and directional deformation by ANN and ANSYS are quite low. The average variation for all type of outcomes is about 5%. This could be further reduced if hidden layers used in higher numbers in neural network but that would in-crease the computation time a little so here, in this study a balance is made between the accuracy and time of computation. We have found that Artificial Neural Network (ANN) is a very powerful tool for linear elastic analysis of steel plates even with concentric cut-outs. Artificial neural network approach is easier and faster than approach adopted by software based on finite element method. It takes lesser time to compute the results. Using ANN, dependency upon costly analysis and design packages can be avoided.

REFERENCES
  • Adeli, H. Neural Networks in Civil Engineering. 1989–2000 Comput. Civ. Infrastruct. Eng. 16, 126-142. http://dx.doi.org/10.1111/0885-9507.00219
  • ANSYS. Workbench User’ s Guide. ANSYS Work. 15.0 15317, 724–746 (2013). Figure 9: Regression Analyses for Max Directional Deformation in -Z Direction between ANN and ANSYS for New Models.
  • Baba, B. O. Buckling Behavior of Laminated Composite Plates. J. Reinf. Plast. Compos. 26, 1637–1655 (2007). http://dx.doi.org/10.1177/0731684407079515
  • Garrett, J. H. Where and why artificial neural networks are applicable in civil engineering. J. Comput. Civ. Eng. ASCE 8, 129–130 (1994). http://dx.doi.org/10.1061/(ASCE)0887-3801(1994)8:2(129)
  • Nicholas, P. Emmanuel Padmanaban, K. P., Vasudevan, D. & Selvaraj, I. J. Neural network based buckling strength prediction of laminated composite plate with central cutout. Appl. Mech. Mater. 560 (2014).
  • Paik, Jeom Kee, Ultimate strength of perforated steel plates under combined biaxial compression and edge shear loads. Thin-Walled Struct. 46, 207–213 (2008). http://dx.doi.org/10.1016/j.tws.2007.07.010
  • Pan, Z., Cheng, Y. & Liu, J. Stress analysis of a finite plate with a rectangular hole subjected to uniaxial tension using modified stress functions. Int. J. Mech. Sci. 75, 265–277 (2013). http://dx.doi.org/10.1016/j.ijmecsci.2013.06.014
  • Rusia, S. & Pathak, K. K. “Application of artificial neural network for analysis of triangular plate with hole considering different geometrical and loading parameters,” Open J. Civ. Eng., 06, 01, 31–41(2016). http://dx.doi.org/10.4236/ojce.2016.61004
  • Singh, A. . & Paul, U. . Finite displacement static analysis of thin plate with an opening––a variational approach. Int. J. Solids Struct. 40, 4135–4151 (2003). http://dx.doi.org/10.1016/S0020-7683(03)00204-X
  • Ukadgaonker, V. G. & Rao, D. K. N. A general solution for moments around holes in symmetric laminates. Compos. Struct. 49, 41–54 (2000). http://dx.doi.org/10.1016/S0263-8223(99)00123-3
  • Wu, H. C. & Mu, B. On stress concentrations for isotropic/orthotropic plates and cylinders with a circular hole. Compos. Part B Eng. 34, 127–134 (2003). http://dx.doi.org/10.1016/S1359-8368(02)00097-5