Data-driven algorithm for real-time fatigue life prediction of structures with stochastic parameters

Abstract Fatigue crack growth analysis using extended finite element method (XFEM) is an efficient way to predict the residual life of structures; however, when the structure parameters vary stochastically, it will be very hard to make accurate predictions. To bridge this research gap, this work proposed a data-driven learning algorithm to improve the prediction capacity of fatigue life by considering stochastic parameters of structures. In this new algorithm, the XFEM was firstly employed to generate a large amount of datasets that pair the structural responses with remaining fatigue life. Then, the back propagation neural network (BPNN) was employed to construct a fatigue life prediction model based on the XFEM datasets. Real-time prediction for the structural fatigue life was achieved using the constructed BPNN model without knowing the exact distribution functions of stochastic parameters. Several numerical examples were performed to evaluate the performance of the proposed algorithm. The analysis results demonstrate that the proposed data-driven algorithm can accurately predict the fatigue life of the structures with stochastic parameters.

[1]  N. Valizadeh,et al.  Extended isogeometric analysis for simulation of stationary and propagating cracks , 2012 .

[2]  Achchhe Lal,et al.  Stochastic XFEM based fracture behavior and crack growth analysis of a plate with a hole emanating cracks under biaxial loading , 2018 .

[3]  B. K. Mishra,et al.  Numerical simulation of functionally graded cracked plates using NURBS based XIGA under different loads and boundary conditions , 2015 .

[4]  Guozheng Kang,et al.  On the fatigue performance and residual life of intercity railway axles with inside axle boxes , 2018, Engineering Fracture Mechanics.

[5]  Achchhe Lal,et al.  Stochastic fracture analysis of laminated composite plate with arbitrary cracks using X-FEM , 2017 .

[6]  Roger G. Metcalfe,et al.  Fatigue cracking of dragline boom support strands , 2019, Engineering Failure Analysis.

[7]  Ernian Pan,et al.  Fracture mechanics analysis of cracked 2-D anisotropic media with a new formulation of the boundary element method , 1996 .

[8]  H. Nguyen-Dang,et al.  Multiple-cracked fatigue crack growth by BEM , 1995 .

[9]  Yang Zeng,et al.  A Copula-based perturbation stochastic method for fiber-reinforced composite structures with correlations , 2017 .

[10]  Manuel Doblaré,et al.  The perturbation method and the extended finite element method. An application to fracture mechanics problems , 2006 .

[11]  Huy Duong Bui,et al.  An integral equations method for solving the problem of a plane crack of arbitrary shape , 1977 .

[12]  Sohichi Hirose,et al.  An extended consecutive-interpolation quadrilateral element (XCQ4) applied to linear elastic fracture mechanics , 2015 .

[13]  Alokesh Pramanik,et al.  Fracture and fatigue life of Al-based MMCs machined at different conditions , 2018 .

[14]  Rakesh K. Kapania,et al.  Stochastic extended finite element implementation for fracture analysis of laminated composite plate with a central crack , 2017 .

[15]  Yang Li,et al.  Modeling of Constitutive Relationship of Aluminum Alloy Based on BP Neural Network Model , 2015 .

[16]  Sohichi Hirose,et al.  Quasi-static crack propagation simulation by an enhanced nodal gradient finite element with different enrichments , 2017 .

[17]  Guirong Liu,et al.  Extended finite element method with edge-based strain smoothing (ESm-XFEM) for linear elastic crack growth , 2012 .

[18]  Tinh Quoc Bui,et al.  Improved knowledge-based neural network (KBNN) model for predicting spring-back angles in metal sheet bending , 2014, Int. J. Model. Simul. Sci. Comput..

[19]  B. K. Mishra,et al.  A new multiscale XFEM for the elastic properties evaluation of heterogeneous materials , 2017 .

[20]  Timon Rabczuk,et al.  Modeling and simulation of kinked cracks by virtual node XFEM , 2015 .

[21]  E. Pan,et al.  A general Boundary Element Analysis of 2-D Linear Elastic Fracture Mechanics , 1997 .

[22]  Hehua Zhu,et al.  Independent cover meshless method for the simulation of multiple crack growth with arbitrary incremental steps and directions , 2017 .

[23]  Tinh Quoc Bui,et al.  Edge-based smoothed extended finite element method for dynamic fracture analysis , 2016 .

[24]  T. Q. Bui.  Extended isogeometric dynamic and static fracture analysis for cracks in piezoelectric materials using NURBS , 2015 .

[25]  Guangyao Li,et al.  A triangular prism solid and shell interactive mapping element for electromagnetic sheet metal forming process , 2017, J. Comput. Phys..

[26]  Biao Zhao,et al.  BP neural network based flexural strength prediction of open-porous Cu-Sn-Ti composites , 2018, Progress in Natural Science: Materials International.

[27]  S. Z. Feng,et al.  An accurate and efficient algorithm for the simulation of fatigue crack growth based on XFEM and combined approximations , 2018 .

[28]  Sohichi Hirose,et al.  Dynamic stationary crack analysis of isotropic solids and anisotropic composites by enhanced local enriched consecutive-interpolation elements , 2017 .

[29]  Tinh Quoc Bui,et al.  Numerical simulation of 2-D weak and strong discontinuities by a novel approach based on XFEM with local mesh refinement , 2018 .

[30]  Sergej Hloch,et al.  Investigation on Different Type of Defects, Temperature Variation and Mechanical Properties of Friction Stir Welded Lap joint of Aluminum Alloy 6101-T6 , 2018 .

[31]  Fang Fang,et al.  An ATPSO-BP neural network modeling and its application in mechanical property prediction , 2019, Computational Materials Science.

[32]  T.Q. Bui,et al.  Thermal-mechanical crack propagation in orthotropic composite materials by the extended four-node consecutive-interpolation element (XCQ4) , 2019, Engineering Fracture Mechanics.

[33]  Han-Cheng Dan,et al.  Temperature prediction model of asphalt pavement in cold regions based on an improved BP neural network , 2017 .

[34]  Hu Wang,et al.  How to control the crack to propagate along the specified path feasibly? , 2017, Computer Methods in Applied Mechanics and Engineering.

[35]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[36]  T. Belytschko,et al.  Extended finite element method for three-dimensional crack modelling , 2000 .

[37]  Bijay K. Mishra,et al.  The numerical simulation of fatigue crack growth using extended finite element method , 2012 .

[38]  Bijay K. Mishra,et al.  A stochastic XFEM model for the tensile strength prediction of heterogeneous graphite based on microstructural observations , 2017 .

[39]  David Nowell,et al.  Fatigue life prediction for Waspaloy under biaxial loading , 2018, Theoretical and Applied Fracture Mechanics.

[40]  Duc-Kien Thai,et al.  Gradient tree boosting machine learning on predicting the failure modes of the RC panels under impact loads , 2019, Engineering with Computers.

[41]  B. H. Nguyen,et al.  An isogeometric symmetric Galerkin boundary element method for two-dimensional crack problems , 2016 .

[42]  Bijay K. Mishra,et al.  Stochastic fatigue crack growth simulation of interfacial crack in bi-layered FGMs using XIGA , 2015 .

[43]  Tinh Quoc Bui,et al.  On the thermal buckling analysis of functionally graded plates with internal defects using extended isogeometric analysis , 2016 .

[44]  Hehua Zhu,et al.  A mixed cover meshless method for elasticity and fracture problems , 2018, Theoretical and Applied Fracture Mechanics.

[45]  M. Brede,et al.  Efficient critical distance approach to predict the fatigue lifetime of structural adhesive joints , 2019, Engineering Fracture Mechanics.

[46]  Ted Belytschko,et al.  Elastic crack growth in finite elements with minimal remeshing , 1999 .

[47]  Dandan Xu,et al.  Modeling arbitrary crack propagation in coupled shell/solid structures with X‐FEM , 2016 .

[48]  P. Kerfriden,et al.  Isogeometric boundary element methods for three dimensional static fracture and fatigue crack growth , 2017 .

[49]  Stéphane Bordas,et al.  A gradient weighted extended finite element method (GW-XFEM) for fracture mechanics , 2019, Acta Mechanica.

[50]  Achchhe Lal,et al.  Stochastic XFEM fracture and crack propagation behavior of an isotropic plate with hole emanating radial cracks subjected to various in-plane loadings , 2018 .

[51]  T. Rabczuk,et al.  T-spline based XIGA for fracture analysis of orthotropic media , 2015 .

[52]  X. Cui,et al.  A coupling approach of state-based peridynamics with node-based smoothed finite element method , 2018 .

[53]  H. Tran-Ngoc,et al.  Improved ANN technique combined with Jaya algorithm for crack identification in plates using XIGA and experimental analysis , 2020, Theoretical and Applied Fracture Mechanics.

[54]  X. Han,et al.  A novel multi-grid based reanalysis approach for efficient prediction of fatigue crack propagation , 2019, Computer Methods in Applied Mechanics and Engineering.

[55]  Tinh Quoc Bui,et al.  Simulation of dynamic and static thermoelastic fracture problems by extended nodal gradient finite elements , 2017 .