A neural network‐enhanced reproducing kernel particle method for modeling strain localization
نویسندگان
چکیده
Abstract Modeling the localized intensive deformation in a damaged solid requires highly refined discretization for accurate prediction, which significantly increases computational cost. Although adaptive model refinement can be employed enhanced effectiveness, it is cumbersome traditional mesh‐based methods to perform while modeling evolving localizations. In this work, neural network‐enhanced reproducing kernel particle method (NN‐RKPM) proposed, where location, orientation, and shape of solution transition near localization automatically captured by NN approximation via block‐level network (NN) optimization. The weights biases blocked parameterization control location orientation localization. designed basic four‐kernel block capable capturing triple junction or quadruple topological pattern, more complicated patters are superposition multiple blocks. standard RK then utilized approximate smooth part solution, permits much coarser than high‐resolution needed capture sharp transitions with conventional methods. A regularization additionally introduced discretization‐independent material responses. effectiveness proposed NN‐RKPM verified series numerical verifications.
منابع مشابه
Reproducing Kernel Space Hilbert Method for Solving Generalized Burgers Equation
In this paper, we present a new method for solving Reproducing Kernel Space (RKS) theory, and iterative algorithm for solving Generalized Burgers Equation (GBE) is presented. The analytical solution is shown in a series in a RKS, and the approximate solution u(x,t) is constructed by truncating the series. The convergence of u(x,t) to the analytical solution is also proved.
متن کاملSome Studies of the Reproducing Kernel Particle Method
Abstract. Interests in meshfree (or meshless) methods have grown rapidly in the recent years in solving boundary value problems arising in mechanics, especially in dealing with difficult problems involving large deformation, moving discontinuities, etc. Rigorous error estimates of a meshfree method, the reproducing kernel particle method (RKPM), have been theoretically derived and experimentall...
متن کاملA New Approach for Solving Volterra Integral Equations Using The Reproducing Kernel Method
This paper is concerned with a technique for solving Volterra integral equations in the reproducing kernel Hilbert space. In contrast with the conventional reproducing kernel method, the Gram-Schmidt process is omitted here and satisfactory results are obtained.The analytical solution is represented in the form of series.An iterative method is given to obtain the approximate solution.The conver...
متن کاملA new reproducing kernel method for solving Volterra integro-dierential equations
This paper is concerned with a technique for solving Volterra integro-dierential equationsin the reproducing kernel Hilbert space. In contrast with the conventional reproducing kernelmethod, the Gram-Schmidt process is omitted here and satisfactory results are obtained.The analytical solution is represented in the form of series. An iterative method is given toobtain the...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: International Journal for Numerical Methods in Engineering
سال: 2022
ISSN: ['0029-5981', '1097-0207']
DOI: https://doi.org/10.1002/nme.7040