A novel analysis-prediction approach for geometrically nonlinear problems using group method of data handling

Abstract A novel analysis-prediction (ANP) approach for geometrically nonlinear problems of solid mechanics is for the first time proposed in this paper. The key concept of this approach is: (1) A part of equilibrium path is traced by numerical analysis; (2) Data of this part is then used for training predictive network; (3) Applying the trained network, the rest of the equilibrium path is simply traced by pure prediction without using any analysis. As an illustration for ANP approach, the analysis package is in this study established based on isogeometric shell analysis using the first-order shear deformation shell theory (FSDT). As the main advantage of the proposed approach, computational cost is significantly lower than that of the conventional approach based on pure numerical analysis. In addition, the predictive networks are built via group method of data handling (GMDH) known as a self-organizing deep learning method for time series forecasting problems without requirement of big data. Some numerical examples are provided to confirm the high accuracy and efficiency of the proposed approach. The approach not only could be applied to a wide range of computational mechanics problems in which nonlinear response occurs but also to other computational engineering fields.

[1]  Hans Petersson,et al.  On finite element analysis of geometrically nonlinear problems , 1985 .

[2]  Trang Nguyen,et al.  Race Recognition Using Deep Convolutional Neural Networks , 2018, Symmetry.

[3]  Timon Rabczuk,et al.  Learning and Intelligent Optimization for Material Design Innovation , 2017, LION.

[4]  Tan N. Nguyen,et al.  NURBS-based analyses of functionally graded carbon nanotube-reinforced composite shells , 2018, Composite Structures.

[5]  Amy Loutfi,et al.  A review of unsupervised feature learning and deep learning for time-series modeling , 2014, Pattern Recognit. Lett..

[6]  E. Riks.  The Application of Newton's Method to the Problem of Elastic Stability , 1972 .

[7]  Mohammad Rezaiee-Pajand,et al.  Geometrically nonlinear analysis of shells by various dynamic relaxation methods , 2017 .

[8]  Arthur L. Samuel,et al.  Some studies in machine learning using the game of checkers , 2000, IBM J. Res. Dev..

[9]  Huu-Tai Thai,et al.  Nonlinear static and transient isogeometric analysis of functionally graded microplates based on the modified strain gradient theory , 2017 .

[10]  Ngoc Thanh Nguyen,et al.  A fast and accurate approach for bankruptcy forecasting using squared logistics loss with GPU-based extreme gradient boosting , 2019, Inf. Sci..

[11]  H. Nguyen-Xuan,et al.  Isogeometric analysis of large-deformation thin shells using RHT-splines for multiple-patch coupling , 2017 .

[12]  M. Crisfield,et al.  A faster modified newton-raphson iteration , 1979 .

[13]  Hyeonjoon Moon,et al.  Deep Learning Approach for Short-Term Stock Trends Prediction Based on Two-Stream Gated Recurrent Unit Network , 2018, IEEE Access.

[14]  Stéphane Bordas,et al.  A Tutorial on Bayesian Inference to Identify Material Parameters in Solid Mechanics , 2019, Archives of Computational Methods in Engineering.

[15]  G. Garcea,et al.  An efficient isogeometric solid-shell formulation for geometrically nonlinear analysis of elastic shells , 2018 .

[16]  Elena Atroshchenko,et al.  Weakening the tight coupling between geometry and simulation in isogeometric analysis: From sub‐ and super‐geometric analysis to Geometry‐Independent Field approximaTion (GIFT) , 2016, 1706.06371.

[17]  Hyeonjoon Moon,et al.  Utilizing text recognition for the defects extraction in sewers CCTV inspection videos , 2018, Comput. Ind..

[18]  Ali Maghami,et al.  Path following techniques for geometrically nonlinear structures based on Multi-point methods , 2018 .

[19]  Roger A. Sauer,et al.  A NURBS-based Inverse Analysis for Reconstruction of Nonlinear Deformations of Thin Shell Structures , 2018, ArXiv.

[20]  Sung Kyung Hong,et al.  Fault-tolerant Control of Quadcopter UAVs Using Robust Adaptive Sliding Mode Approach , 2018, Energies.

[21]  E. Riks.  An incremental approach to the solution of snapping and buckling problems , 1979 .

[22]  Zhihui Lu,et al.  Automating smart recommendation from natural language API descriptions via representation learning , 2018, Future Gener. Comput. Syst..

[23]  A. Ivakhnenko.  The group method of data handling in long-range forecasting , 1978 .

[24]  Stéphane Bordas,et al.  Simple and extensible plate and shell finite element models through automatic code generation tools , 2018, Computers & Structures.

[25]  Chien H. Thai,et al.  NURBS-based postbuckling analysis of functionally graded carbon nanotube-reinforced composite shells , 2019, Computer Methods in Applied Mechanics and Engineering.

[26]  Sung Wook Baik,et al.  A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced Dataset , 2018, Symmetry.

[27]  Naif Alajlan,et al.  Artificial Neural Network Methods for the Solution of Second Order Boundary Value Problems , 2019, Computers, Materials & Continua.

[28]  Mohammad Rezaiee-Pajand,et al.  An incremental iterative solution procedure without predictor step , 2018 .

[29]  Robert X. Gao,et al.  Deep learning and its applications to machine health monitoring , 2019, Mechanical Systems and Signal Processing.

[30]  Hyeonjoon Moon,et al.  Deep Learning Based Computer Generated Face Identification Using Convolutional Neural Network , 2018, Applied Sciences.

[31]  Annamária R. Várkonyi-Kóczy,et al.  Reviewing the novel machine learning tools for materials design , 2017 .

[32]  K. Y. Sze,et al.  Popular benchmark problems for geometric nonlinear analysis of shells , 2004 .

[33]  H. Rappel,et al.  Identifying elastoplastic parameters with Bayes’ theorem considering output error, input error and model uncertainty , 2019, Probabilistic Engineering Mechanics.

[34]  A. Murat Ozbayoglu,et al.  Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach , 2018, Appl. Soft Comput..

[35]  Mohammad Rezaiee-Pajand,et al.  Using residual areas for geometrically nonlinear structural analysis , 2015 .

[36]  T. Rabczuk,et al.  A meshfree thin shell method for non‐linear dynamic fracture , 2007 .

[37]  Hung Nguyen-Xuan,et al.  Geometrically nonlinear analysis of functionally graded material plates using an improved moving Kriging meshfree method based on a refined plate theory , 2018, Composite Structures.

[38]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[39]  Hossein Estiri,et al.  Finding equilibrium paths by minimizing external work in dynamic relaxation method , 2016 .

[40]  Timon Rabczuk,et al.  Finite strain fracture of plates and shells with configurational forces and edge rotations , 2013 .

[41]  Hung Nguyen-Xuan,et al.  A novel three-variable shear deformation plate formulation: Theory and Isogeometric implementation , 2017 .

[42]  Sanjay Pant,et al.  On improving the numerical convergence of highly nonlinear elasticity problems , 2018, Computer Methods in Applied Mechanics and Engineering.

[43]  N. Nguyen‐Thanh,et al.  Geometrically nonlinear analysis of thin-shell structures based on an isogeometric-meshfree coupling approach , 2018, Computer Methods in Applied Mechanics and Engineering.

[44]  H. Nguyen-Xuan,et al.  An isogeometric approach for size-dependent geometrically nonlinear transient analysis of functionally graded nanoplates , 2017 .

[45]  Mohammad Rezaiee-Pajand,et al.  Geometrical nonlinear analysis based on optimization technique , 2018 .

[46]  Hung Nguyen-Xuan,et al.  A novel computational approach for functionally graded isotropic and sandwich plate structures based on a rotation-free meshfree method , 2016 .

[47]  Sung Wook Baik,et al.  Oversampling Techniques for Bankruptcy Prediction: Novel Features from a Transaction Dataset , 2018, Symmetry.

[48]  J. Reddy.  Mechanics of laminated composite plates and shells : theory and analysis , 1996 .

[49]  Hossein Estiri,et al.  Comparative analysis of three-dimensional frames by dynamic relaxation methods , 2018 .

[50]  Hyeonjoon Moon,et al.  Background Information of Deep Learning for Structural Engineering , 2017 .

[51]  Leandro dos Santos Coelho,et al.  A GMDH polynomial neural network-based method to predict approximate three-dimensional structures of polypeptides , 2012, Expert systems with applications.

[52]  M. Crisfield.  A FAST INCREMENTAL/ITERATIVE SOLUTION PROCEDURE THAT HANDLES "SNAP-THROUGH" , 1981 .

[53]  Duc Truong Pham,et al.  Modelling and prediction using GMDH networks of Adalines with nonlinear preprocessors , 1994 .

[54]  Gianpaolo Francesco Trotta,et al.  Computer vision and deep learning techniques for pedestrian detection and tracking: A survey , 2018, Neurocomputing.

[55]  Hung Nguyen-Xuan,et al.  An improved moving Kriging meshfree method for plate analysis using a refined plate theory , 2016 .

[56]  Hung Nguyen-Xuan,et al.  Geometrically nonlinear isogeometric analysis of functionally graded microplates with the modified couple stress theory , 2017 .

[57]  T. Hughes,et al.  Isogeometric analysis : CAD, finite elements, NURBS, exact geometry and mesh refinement , 2005 .

[58]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[59]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[60]  Stéphane Bordas,et al.  Bayesian inference to identify parameters in viscoelasticity , 2018 .