☆ 4.7 Article

Prediction of maximum tensile stress in plain-weave composite laminates with interacting holes via stacked machine learning algorithms: A comparative study

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2023)

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 Engineering, Mechanical

Automated fatigue damage detection and classification technique for composite structures using Lamb waves and deep autoencoder

Hyunseong Lee et al.

Summary: This paper introduces a robust automatic damage diagnosis technique that uses ultrasonic Lamb waves and a deep autoencoder (DAE) to detect and classify fatigue damage in composite structures. The technique accurately detects and classifies fatigue damage in composite structures, while eliminating the need for manual or signal processing-based damage sensitive feature extraction.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Sign Stochastic Gradient Descents without bounded gradient assumption for the finite sum minimization

Tao Sun et al.

Summary: This paper presents a convergence framework for sign-based stochastic gradient descents (SGDs) without the bounded gradient assumption. The ergodic convergence rates are provided based on the smooth assumption of the objective functions. Three algorithms, including siGNSGD, majority vote, and zeroth-order version, are developed for different application settings. The bounded gradient assumption used in previous analysis is also removed.

NEURAL NETWORKS (2022)

添加到收藏夹

Article Materials Science, Multidisciplinary

Data-driven compressive strength prediction of steel fiber reinforced concrete (SFRC) subjected to elevated temperatures using stacked machine learning algorithms

Torkan Shafighfard et al.

Summary: This study used a large dataset to construct a data-rich framework and predicted the compressive strength of steel fiber-reinforced concrete subjected to high temperatures using machine learning algorithms. By comparing multiple algorithms, the stacked ML pipeline was found to have the highest accuracy and was compared with an artificial neural network algorithm. The proposed stacked technique is of great importance in accurately predicting the compressive strength of SFRCs in construction applications.

JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T (2022)

添加到收藏夹

Article Chemistry, Physical

Model of the Temperature Influence on Additively Manufactured Carbon Fibre Reinforced Polymer Samples with Embedded Fibre Bragg Grating Sensors

Torkan Shafighfard et al.

Summary: This study investigates the thermo-mechanical behavior of 3D-printed composite structures with embedded FBG sensors under thermal loading. The results show that the numerical simulation is in good agreement with the experimental investigation, demonstrating the capability of the embedded FBG sensors to accurately identify thermo-mechanical strain.

MATERIALS (2022)

添加到收藏夹

Article Mechanics

Comparison of machine learning methods and finite element analysis on the fracture behavior of polymer composites

H. Ersen Balcioglu et al.

Summary: Recent research has used experimental methods, finite element analysis, and machine learning algorithms to analyze the fracture behavior of polymer composites. The results show good agreement between these methods in analyzing fracture behavior.

ARCHIVE OF APPLIED MECHANICS (2021)

添加到收藏夹

Article Mechanics

Machine learning regression approaches for predicting the ultimate buckling load of variable-stiffness composite cylinders

A. Kaveh et al.

Summary: In this study, various machine learning techniques were employed to establish the relationship between fiber angle and buckling capacity of cylinders under bending-induced loads. The numerical results demonstrate that compared with other models such as Random Forest Regressor, Decision Tree algorithm, and Multiple Linear Regression, the Deep Learning model achieved more stable results with smaller errors and higher generalization.

ACTA MECHANICA (2021)

添加到收藏夹

Article Construction & Building Technology

Uniaxial tension damage mechanics of steel fiber reinforced concrete using acoustic emission and machine learning crack mode classification

J. G. Yue et al.

Summary: This paper presents a new scalar plastic damage constitutive model for steel fiber reinforced concrete, which was validated through various experimental methods and shown to reliably predict the mechanical properties of the material.

CEMENT & CONCRETE COMPOSITES (2021)

添加到收藏夹

Article Mechanics

Machine learning and materials informatics approaches for evaluating the interfacial properties of fiber-reinforced composites

B. B. Yin et al.

Summary: The study introduces machine learning-assisted models to predict the interfacial properties of fiber-reinforced composites for the first time, and the effectiveness of the model is verified through comparison between experimental and prediction results. It is found that the interfacial properties are significantly dependent on the fiber's diameter.

COMPOSITE STRUCTURES (2021)

添加到收藏夹

Article Mechanics

Damage mode identification of open hole composite laminates based on acoustic emission and digital image correlation methods

E. Ozaslan et al.

Summary: This paper focuses on damage mode identification of composite laminates using acoustic emission and digital image correlation methods. The study investigates the effect of different fiber/matrix materials and hole orientations on damage progression and mechanisms, selecting the most effective acoustic emission parameter through correlation and Principal Component Analyses. The findings are successfully verified by digital image correlation measurements.

COMPOSITE STRUCTURES (2021)

添加到收藏夹

Article Mechanics

Machine learning assisted characterisation and simulation of compressive damage in composite laminates

Johannes Reiner et al.

Summary: The study proposed a data-rich framework to characterize the macroscopic strain-softening response of laminated composites under compressive loading using machine learning models. By simulating compression tests with an efficient FE model and training two ML methods, the study successfully demonstrated the effectiveness of using ML to reduce experimental efforts for damage characterization in composites subjected to compressive loads.

COMPOSITE STRUCTURES (2021)

添加到收藏夹

Article Mechanics

A methodology to generate design allowables of composite laminates using machine learning

C. Furtado et al.

Summary: This study is the first attempt to apply machine learning techniques in predicting statistical design allowables of composite laminates. By using four machine algorithms, the study successfully predicts notched strength and its statistical distribution, providing a new approach to reduce computational time for obtaining design allowables.

INTERNATIONAL JOURNAL OF SOLIDS AND STRUCTURES (2021)

添加到收藏夹

Article Engineering, Mechanical

An artificial neural network methodology for damage detection: Demonstration on an operating wind turbine blade

Artur Movsessian et al.

Summary: This study presents a novel artificial neural network (ANN) based methodology for robust damage detection within a vibration-based structural health monitoring framework. The method establishes nonlinear relationships between damage sensitive features and novelty indices, using prediction error as a new index. The results demonstrate improved damage detectability in various scenarios, despite the influence of environmental and operational variables.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2021)

添加到收藏夹

Article Engineering, Mechanical

A physics-guided machine learning model for two-dimensional structures based on ordinary state-based peridynamics

Cong Tien Nguyen et al.

Summary: This study introduces a novel physics-guided machine learning model for two-dimensional structures based on ordinary state-based Peridynamics. It establishes linear relationships between material displacements and applied forces using linear regression, and verifies the accuracy of the coupled model in predicting deformations and damage for various structural configurations.

THEORETICAL AND APPLIED FRACTURE MECHANICS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Grid search based multi-population particle swarm optimization algorithm for multimodal multi-objective optimization

Guoqing Li et al.

Summary: This paper proposes a grid search based multi-population particle swarm optimization algorithm (GSMPSO-MM) to handle multimodal multi-objective optimization problems (MMOPs), aiming to balance diversity and convergence by adopting multiple populations and grid search methods. The environmental selection operator updates the non-dominated solution archive to improve solution quality.

SWARM AND EVOLUTIONARY COMPUTATION (2021)

添加到收藏夹

Article Mechanics

A micromechanics and machine learning coupled approach for failure prediction of unidirectional CFRP composites under triaxial loading: A preliminary study

Jiayun Chen et al.

Summary: This study proposes a hybrid method based on ANN and micro-mechanics for predicting the failure of composite lamina under triaxial loading. The ANN algorithm shows robustness in predicting failure with over 97.5% accuracy under different triaxial loading conditions for UD lamina. The approach can be used for modifying existing failure criteria and proposing new ANN-based failure criteria.

COMPOSITE STRUCTURES (2021)

添加到收藏夹

Article Mechanics

A novel hybrid damage monitoring approach to understand the correlation between size effect and failure behavior of twill CFRP laminates

Raja Muhammad Awais Khan et al.

Summary: In this study, a comprehensive experimental approach using multiple structural health monitoring techniques was conducted to elucidate the size effect in twill woven carbon fiber reinforced polymeric composites. It was found that increase in thickness changes the proportion of microdamage related to fiber failures, and a stagnation period in acoustic emission activity was observed before global failure in thick samples. Moreover, the slower damage growth dynamics in thicker laminates compared to thin laminates were highlighted, assisting in understanding the size effect in laminated composites.

COMPOSITE STRUCTURES (2021)

添加到收藏夹

Article Mechanics

Prediction of failure behavior of composite hat-stiffened panels under in-plane shear using artificial neural network

Zhenya Sun et al.

Summary: This study focuses on the development of an analytical and computationally efficient analysis tool using artificial neural networks for predicting the buckling and ultimate loads of composite hat-stiffened panels under in-plane shear. The results show that the trained ANN can accurately and efficiently predict the buckling and ultimate loads of composite hat-stiffened panels under in-plane shear, and will be very useful in the practical engineering design.

COMPOSITE STRUCTURES (2021)

添加到收藏夹

Article Mechanics

Difference-based deep learning framework for stress predictions in heterogeneous media

Haotian Feng et al.

Summary: By developing Difference-based Neural Network (DiNN) frameworks using deep learning and a combination of engineering and statistical knowledge, this study successfully determines stress distribution in heterogeneous media for the first time, with a special focus on discontinuous domains exhibiting high stress concentrations. The DiNN framework consists of three main modules: sample processing, Encoder-Decoder, and stress prediction, and significantly improves the accuracy of stress prediction in composite models, particularly with random volume fraction and localized high stress concentrations compared to existing structures.

COMPOSITE STRUCTURES (2021)

添加到收藏夹

Article Engineering, Multidisciplinary

A parametric study of adhesive bonded joints with composite material using black-box and grey-box machine learning methods: Deep neuron networks and genetic programming

Zewen Gu et al.

Summary: This study presents the development of black-box and grey-box machine learning models for accurately predicting the failure load of adhesive joints, validates the accuracy of the models through experiments, and explores the impact of design variables on the mechanical performance of the joints.

COMPOSITES PART B-ENGINEERING (2021)

添加到收藏夹

Article Engineering, Mechanical

A kNN algorithm for locating and quantifying stiffness loss in a bridge from the forced vibration due to a truck crossing at low speed

Kun Feng et al.

Summary: This paper presents a k-Nearest Neighbours (kNN) algorithm for locating and quantifying bridge damage based on the time-varying forced frequencies due to a moving truck. The algorithm utilizes eigenvalue analysis and a vast sample of patterns generated to determine the location and severity of the damage. Field measurements are simulated using dynamic transient analysis for theoretical testing purposes.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2021)

添加到收藏夹

Article Engineering, Mechanical

Structured machine learning tools for modelling characteristics of guided waves

Marcus Haywood-Alexander et al.

Summary: The use of ultrasonic guided waves for non-destructive evaluation and structural health monitoring is becoming increasingly popular. Understanding the behavior of guided waves in complex materials is crucial, and this paper introduces a novel data-driven method for modeling the feature-space of guided waves, which can lead to more robust models.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2021)

添加到收藏夹

Article Engineering, Civil

Tensile properties and failure mechanism of 3D woven composites containing holes of different geometries

Qiwei Guo et al.

Summary: This study investigated the open-hole tension properties and failure processes of 3D woven composite plates with different hole shapes through experiments and FE modeling. It was found that the hole shape significantly influenced the strain distributions, but had no perceptible effect on the OHT strength. The stress concentration factor of the circular hole was 36% higher than the racetrack and square holes.

THIN-WALLED STRUCTURES (2021)

添加到收藏夹

Article Chemistry, Physical

A Robust Numerical Methodology for Fatigue Damage Evolution Simulation in Composites

Angela Russo et al.

Summary: This study introduces a novel cycle jump strategy called Smart Cycle strategy to avoid simulating every single cycle and save computational resources. The strategy quickly provides a preliminary assessment of the fatigue behavior of composite structures, based on the hypothesis that stress redistribution can be neglected until fiber and/or matrix damage is verified at element/level level.

MATERIALS (2021)

添加到收藏夹

Article Materials Science, Multidisciplinary

An Unconventional Approach for Analyzing the Mechanical Properties of Natural Fiber Composite Using Convolutional Neural Network

Govindaraj Ramkumar et al.

Summary: Natural fiber composites have seen rapid growth in recent years, with computational methods and convolutional neural networks playing a significant role in designing and analyzing their mechanical properties. The incorporation of a genetic algorithm optimizer has helped improve these properties by converging to configurations with highly enhanced performance, particularly in areas adjacent to cracks.

ADVANCES IN MATERIALS SCIENCE AND ENGINEERING (2021)

添加到收藏夹

Article Engineering, Environmental

Comparative study on total nitrogen prediction in wastewater treatment plant and effect of various feature selection methods on machine learning algorithms performance

Faramarz Bagherzadeh et al.

Summary: This study evaluated the effect of seven different Feature Selection methods on enhancing the prediction accuracy for total nitrogen in wastewater treatment plants. The results showed that scenario IV suggested by Mutual Information had the best performance. In addition, Gradient Boosting Machine demonstrated the best performance on unseen data-set, indicating its effectiveness for wastewater components prediction.

JOURNAL OF WATER PROCESS ENGINEERING (2021)

添加到收藏夹

Article Engineering, Multidisciplinary

Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance

Md Manjurul Ahsan et al.

Summary: The study aimed to evaluate the performance of machine learning algorithms on a dataset of patients with heart disease, with the results showing that CART algorithm combined with RS or QT data scaling method outperformed all others.

TECHNOLOGIES (2021)

添加到收藏夹

Article Materials Science, Multidisciplinary

Prediction of Short Fiber Composite Properties by an Artificial Neural Network Trained on an RVE Database

Kevin Breuer et al.

Summary: An artificial neural network was designed and trained to predict the elastic properties of short fiber reinforced plastics, using finite element simulations as the data basis. The network showed good prediction accuracy for a wide range of parameters and outperformed traditional homogenization methods. Training the network on an extended dataset was successful and helped avoid calculation-intensive data points without sacrificing prediction quality.

FIBERS (2021)

添加到收藏夹

Article Mechanics

Experimental characterization, analytical and numerical investigations of metal/polymer/metal sandwich composites - Part 2: Free bending

Mohamed Harhash et al.

COMPOSITE STRUCTURES (2020)

添加到收藏夹

Article Materials Science, Composites

Machine learning predictions on fracture toughness of multiscale bio-nano-composites

Vahid Daghigh et al.

JOURNAL OF REINFORCED PLASTICS AND COMPOSITES (2020)

添加到收藏夹

Article Materials Science, Multidisciplinary

Prediction of composite microstructure stress-strain curves using convolutional neural networks

Charles Yang et al.

MATERIALS & DESIGN (2020)

添加到收藏夹

Article Mechanics

Theory -guided machine learning for damage characterization of composites

Navid Zobeiry et al.

COMPOSITE STRUCTURES (2020)

添加到收藏夹

Article Materials Science, Composites

Damage Detection in Composites By Artificial Neural Networks Trained By Usingin SituDistributed Strains

America Califano et al.

APPLIED COMPOSITE MATERIALS (2020)

添加到收藏夹

Article Engineering, Mechanical

A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications

Onur Avci et al.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2020)

添加到收藏夹

Article Materials Science, Composites

Multi-Scale Analyses of Three Dimensional Woven Composite 3D Shell With a Cut Out Circle

Duc Hai Nguyen et al.

APPLIED COMPOSITE MATERIALS (2019)

添加到收藏夹

Article Materials Science, Multidisciplinary

Machine learning for composite materials

Chun-Teh Chen et al.

MRS COMMUNICATIONS (2019)

添加到收藏夹

Article Engineering, Manufacturing

A machine learning assisted approach for textile formability assessment and design improvement of composite components

Clemens Zimmerling et al.

COMPOSITES PART A-APPLIED SCIENCE AND MANUFACTURING (2019)

添加到收藏夹

Review Mechanics

Decision tree-based machine learning to optimize the laminate stacking of composite cylinders for maximum buckling load and minimum imperfection sensitivity

H. N. R. Wagner et al.

COMPOSITE STRUCTURES (2019)

添加到收藏夹

Article Mechanics

Design of fiber-reinforced variable-stiffness composites for different open-hole geometries with fiber continuity and curvature constraints

Torkan Shafighfard et al.

COMPOSITE STRUCTURES (2019)

添加到收藏夹

Article Chemistry, Multidisciplinary

Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment

Grace X. Gu et al.

MATERIALS HORIZONS (2018)

添加到收藏夹

Review Engineering, Manufacturing

Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering

Dennis M. Dimiduk et al.

INTEGRATING MATERIALS AND MANUFACTURING INNOVATION (2018)

添加到收藏夹

Review Materials Science, Multidisciplinary

Carbon nanotubes as reinforcement in composites: A review of the analytical, numerical and experimental approaches

Sadegh Imani Yengejeh et al.

COMPUTATIONAL MATERIALS SCIENCE (2017)

添加到收藏夹

Article Mechanics

Progressive failure analysis on scaled open-hole tensile composite laminates

Hongchen Bao et al.

COMPOSITE STRUCTURES (2016)

添加到收藏夹

Article Engineering, Multidisciplinary

Progressive failure analysis of three-dimensional woven carbon composites in single-bolt, double-shear bearing

Kyle C. Warren et al.

COMPOSITES PART B-ENGINEERING (2016)

添加到收藏夹

Article Construction & Building Technology

Failure prediction and reliability analysis of ferrocement composite structures by incorporating machine learning into acoustic emission monitoring technique

Arash Behnia et al.

CONSTRUCTION AND BUILDING MATERIALS (2016)

添加到收藏夹

Article Mechanics

A comparative study of metamodeling methods for the design optimization of variable stiffness composites

Mahdi Arian Nik et al.

COMPOSITE STRUCTURES (2014)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Gradient boosting machines, a tutorial

Alexey Natekin et al.

FRONTIERS IN NEUROROBOTICS (2013)

添加到收藏夹

Article Engineering, Mechanical

Decision tree: A very useful tool in analysing flow-induced vibration data

R. Ajith Kumar et al.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2008)

添加到收藏夹

Article Materials Science, Composites

Buckling of composite plates with U-shaped cutouts

M Yazici et al.

JOURNAL OF COMPOSITE MATERIALS (2003)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.