☆ 4.7 Article

Probabilistic physics-guided transfer learning for material property prediction in extrusion deposition additive manufacturing

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Polymer Science

Deep Transfer Learning Approach for Localization of Damage Area in Composite Laminates Using Acoustic Emission Signal

Jingyu Zhao et al.

Polymers (2023)

添加到收藏夹

Article Engineering, Multidisciplinary

Influence of printing conditions on the extrudate shape and fiber orientation in extrusion deposition additive manufacturing

Pasita Pibulchinda et al.

Summary: A numerical framework was developed to investigate the influence of EDAM processing conditions on the final product. The developed model was validated through simulations and experiments, and the roles of process parameters in determining the microstructure of the product were revealed.

COMPOSITES PART B-ENGINEERING (2023)

添加到收藏夹

Article Materials Science, Composites

Interlayer fusion bonding of semi-crystalline polymer composites in extrusion deposition additive manufacturing

Eduardo Barocio et al.

Summary: This study focuses on the evolution of interlayer fracture toughness properties in fiber-reinforced, semi-crystalline polymers during the additive manufacturing process. A phenomenological model is developed and experiments are conducted to predict the relationship between thermal history and critical strain energy release rate.

COMPOSITES SCIENCE AND TECHNOLOGY (2022)

添加到收藏夹

Article Mechanics

Transfer learning for enhancing the homogenization-theory-based prediction of elasto-plastic response of particle/short fiber-reinforced composites

Jiyoung Jung et al.

Summary: The study introduces a combined theoretical and data-driven approach, utilizing transfer learning to enhance the accuracy of nonlinear mechanical response predictions. By training a deep neural network on a large dataset and fine-tuning it through transfer learning with a relatively small dataset, better predictive performance is achieved across various reinforcement volume fractions and shapes.

COMPOSITE STRUCTURES (2022)

添加到收藏夹

Article Materials Science, Composites

A machine learning approach to determine the elastic properties of printed fiber-reinforced polymers

Akshay J. Thomas et al.

Summary: This study focuses on determining the elastic constants and fiber orientation state of a short fiber-reinforced polymer composite using minimal experimental tests. A methodology is introduced to identify the fiber orientation state and polymer properties by performing tensile tests on the composite coupon level. The proposed approach can be applied to different processing methods of short fiber-reinforced polymer systems.

COMPOSITES SCIENCE AND TECHNOLOGY (2022)

添加到收藏夹

Article Engineering, Industrial

Deep transfer learning of additive manufacturing mechanisms across materials in metal-based laser powder bed fusion process

Vigneashwara Pandiyan et al.

Summary: Defective regimes in metal-based Laser Powder Bed Fusion processes can be minimized by employing in-situ monitoring strategies using Machine Learning algorithms and sensing techniques. This study demonstrates the feasibility of transferring the knowledge learned by Deep Learning networks from one material to another in LPBF processes. The accuracy of the two networks during transfer learning shows the possibility of effectively learning transferable features with minimum training time and dataset collection.

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY (2022)

添加到收藏夹

Article Instruments & Instrumentation

A transfer learning approach for damage diagnosis in composite laminated plate using Lamb waves

Akshay Rai et al.

Summary: This paper presents a study on using transfer learning framework based on 1D-CNN autoencoder and classifier to improve the performance of Lamb wave-based damage diagnosis systems. By utilizing the knowledge learned by a source model and applying it to the training of a target model, the damage diagnosing ability is enhanced. The adopted version of the transfer learning approach achieved an impressive accuracy of 82.64% and emerged as the most robust and computationally more economical classification model based on the test performance.

SMART MATERIALS AND STRUCTURES (2022)

添加到收藏夹

Article Engineering, Mechanical

A Sequential Sampling Approach for Multi-Fidelity Surrogate Modeling-Based Robust Design Optimization

Quan Lin et al.

Summary: This paper proposes a sequential sampling method for robust design optimization based on multi-fidelity modeling, which considers both design variable uncertainty and interpolation uncertainty during the sequential sampling. The extended upper confidence boundary (EUCB) function is developed to determine both the sampling locations and the fidelity levels of the sequential samples.

JOURNAL OF MECHANICAL DESIGN (2022)

添加到收藏夹

Article Chemistry, Physical

Anisotropic thermal and electrical conductivities of individual polyacrylonitrile-based carbon fibers

Xiaoyang Ji et al.

Summary: Understanding the anisotropy of thermal and electrical properties of carbon fibers is crucial for various applications. In this study, time-domain thermoreflectance (TDTR) mapping was used to determine the spatial variations in transverse thermal conductivity for two different PAN-based carbon fibers, IM7 and AS4 fibers. The results showed that the transverse thermal conductivity of IM7 fibers was approximately uniform, while the core of A54 fibers had a higher transverse thermal conductivity than the shell.

CARBON (2022)

添加到收藏夹

Article Materials Science, Composites

Bayesian inference of fiber orientation and polymer properties in short fiber-reinforced polymer composites

Akshay J. Thomas et al.

Summary: This paper presents a Bayesian methodology to infer the elastic modulus of the constituent polymer and the fiber orientation state in a short-fiber reinforced polymer composite (SFRP). The approach provides a reliable framework for composite manufacturing digital twins with minimal experimental tests.

COMPOSITES SCIENCE AND TECHNOLOGY (2022)

添加到收藏夹

Article Engineering, Multidisciplinary

A neural network-aided Bayesian identification framework for multiscale modeling of nanocomposites

Stefanos Pyrialakos et al.

Summary: This study presents a Bayesian framework for determining the mechanical properties of carbon-based nanocomposites by updating prior beliefs using measurements on large-scale structures. A surrogate modeling technique utilizing artificial neural networks is developed to predict the nonlinear stress-strain relationship of representative volume elements. This methodology is validated through numerical examples and can be applied to other physically analogous phenomena related to composite materials modeling.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2021)

添加到收藏夹

Article Engineering, Multidisciplinary

Bayesian inference of non-linear multiscale model parameters accelerated by a Deep Neural Network

Ling Wu et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

添加到收藏夹

Article Materials Science, Multidisciplinary

Computational homogenization of sheet molding compound composites based on high fidelity representative volume elements

Johannes Goerthofer et al.

COMPUTATIONAL MATERIALS SCIENCE (2020)

添加到收藏夹

Article Thermodynamics

Micro-mechanical model for the effective thermal conductivity of the multi-oriented inclusions reinforced composites with imperfect interfaces

Wenlong Tian et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2020)

添加到收藏夹

Article Engineering, Manufacturing

Efficient Distortion Prediction of Additively Manufactured Parts Using Bayesian Model Transfer Between Material Systems

Jack Francis et al.

JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING-TRANSACTIONS OF THE ASME (2020)

添加到收藏夹

Article Materials Science, Multidisciplinary

Predicting the effect of aging and defect size on the stress profiles of skin from advancement, rotation and transposition flap surgeries

Taeksang Lee et al.

JOURNAL OF THE MECHANICS AND PHYSICS OF SOLIDS (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A new image classification method using CNN transfer learning and web data augmentation

Dongmei Han et al.

EXPERT SYSTEMS WITH APPLICATIONS (2018)

添加到收藏夹

Article Chemistry, Multidisciplinary

Machine learning material properties from the periodic table using convolutional neural networks

Xiaolong Zheng et al.

CHEMICAL SCIENCE (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Probabilistic programming in Python using PyMC3

John Salvatier et al.

PEERJ COMPUTER SCIENCE (2016)

添加到收藏夹

Article Mathematics, Applied

Solution of inverse problems with limited forward solver evaluations: a Bayesian perspective

I. Bilionis et al.

INVERSE PROBLEMS (2014)

添加到收藏夹

Article Materials Science, Multidisciplinary

The importance of carbon fiber to polymer additive manufacturing

Lonnie J. Love et al.

JOURNAL OF MATERIALS RESEARCH (2014)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Multi-output separable Gaussian process: Towards an efficient, fully Bayesian paradigm for uncertainty quantification

Ilias Bilionis et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2013)

添加到收藏夹

Article Statistics & Probability

Algorithms for Generating Maximin Latin Hypercube and Orthogonal Designs

Hyejung Moon et al.

JOURNAL OF STATISTICAL THEORY AND PRACTICE (2011)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A Survey on Transfer Learning

Sinno Jialin Pan et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2010)

添加到收藏夹

Article Engineering, Aerospace

Use of kriging models to approximate deterministic computer models

JD Martin et al.

AIAA JOURNAL (2005)

添加到收藏夹

Article Polymer Science

Thermal conductivity of misaligned short-fiber-reinforced polymer composites

SY Fu et al.

JOURNAL OF APPLIED POLYMER SCIENCE (2003)

添加到收藏夹

Article Mathematics, Applied

The Wiener-Askey polynomial chaos for stochastic differential equations

DB Xiu et al.

SIAM JOURNAL ON SCIENTIFIC COMPUTING (2002)

添加到收藏夹

Article Statistics & Probability

Bayesian calibration of computer models

MC Kennedy et al.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY (2001)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.