Accelerated offline setup of homogenized microscopic model for multi‐scale analyses using neural network with knowledge transfer

نویسندگان

چکیده

The FE 2 $$ {}^2 computational homogenization method is a predictive multi-scale without the need for constitutive assumptions and/or potential function postulates at macro engineering scale. Instead, effective micro-structural responses are extracted directly from representative volume element (RVE) underlying each point. However, still computationally too expensive most practical uses, since micro-macro coupling done loading step/iteration entire domain. To this end, machine learning has been utilized in literature offline training of surrogate model to predict RVE homogenized response general conditions. In contribution, neural network (NN) incorporated into finite framework non-intrusive manner. This termed as FE-NN framework, analogy method. general, online simulations very efficient, with predictions matching closely those obtained reference direct numerical (DNS). A bottleneck however, high cost associated data generation NN setup. paper, focusing on non-linear elastic deformation heterogeneous materials, sequential strategy knowledge transfer proposed, enable an efficient microscopic For given target RVE, we first consider simplified source where can be generated rapidly, pre-training model. pre-trained parameters next downloaded initialize model, followed by fine-tuning process, using only small dataset high-fidelity RVE. efficiency proposed over conventional training, well as, its excellent capability analyses, demonstrated multi-phase composite material. FE-NN-KT approach implemented easily complicated pre-processing procedures, involves standard extraction RVEs, together architecture.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

scour modeling piles of kambuzia industrial city bridge using hec-ras and artificial neural network

today, scouring is one of the important topics in the river and coastal engineering so that the most destruction in the bridges is occurred due to this phenomenon. whereas the bridges are assumed as the most important connecting structures in the communications roads in the country and their importance is doubled while floodwater, thus exact design and maintenance thereof is very crucial. f...

the use of appropriate madm model for ranking the vendors of mci equipments using fuzzy approach

abstract nowadays, the science of decision making has been paid to more attention due to the complexity of the problems of suppliers selection. as known, one of the efficient tools in economic and human resources development is the extension of communication networks in developing countries. so, the proper selection of suppliers of tc equipments is of concern very much. in this study, a ...

15 صفحه اول

Offline Handwritten Character Recognition using Neural Network

The offline character recognition is very useful software in the field of research. Authoritative field of research has made by character recognition due to its need in various fields of research as in banks, post offices to fulfill all recognition requirements. This paper is an exploration on the different scripts including Mathematical digits, Hindi consonants and vowels, Gurumukhi characters...

متن کامل

Offline Handwritten Character Recognition Using Neural Network

This paper is aimed at recognition of offline handwritten characters in a given scanned text document with the help of neural networks. Image preprocessing, segmentation and feature extraction are various phases involved in character recognition. The first step is image acquisition followed by noise filtering, smoothing and image normalization of scanned image. Segmentation decomposes image int...

متن کامل

Offline Signature Verification Using Artificial Neural Network

This review paper off-line signature verification and recognition using a new approach that depends on a artificial neural network which discriminate between two classes (i) forgery and (ii) original signature. The proposed scheme is based on the technique that applies pre-processing on the signature, feature point extraction and neural network training and finally verifies the authenticity of ...

متن کامل

ذخیره 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: 2023

ISSN: ['0029-5981', '1097-0207']

DOI: https://doi.org/10.1002/nme.7239