Big data, machine learning, and digital twin assisted additive manufacturing: A review

Materials & Design, Journal Year: 2024, Volume and Issue: 244, P. 113086 - 113086

Published: June 25, 2024

Additive manufacturing (AM) has undergone significant development over the past decades, resulting in vast amounts of data that carry valuable information. Numerous research studies have been conducted to extract insights from AM and utilize it for optimizing various aspects such as process, supply chain, real-time monitoring. Data integration into proposed digital twin frameworks application machine learning techniques is expected play pivotal roles advancing future. In this paper, we provide an overview twin-assisted AM. On one hand, discuss domain highlight machine-learning methods utilized field, including material analysis, design optimization, process parameter defect detection monitoring, sustainability. other examine status current technical approach offer future developments perspectives area. This review paper aims present convergence big data, learning, Although there are numerous papers on additive others twins AM, no existing considered how these concepts intrinsically connected interrelated. Our first integrate three propose a cohesive framework they can work together improve efficiency, accuracy, sustainability processes. By exploring latest advancements applications within domains, our objective emphasize potential advantages possibilities associated with technologies

Language: Английский

---

Thermal imaging based non-destructive testing for fault detection in cold spray additive manufacturing

Journal of Manufacturing Processes, Journal Year: 2025, Volume and Issue: 134, P. 1057 - 1068

Published: Jan. 1, 2025

Language: Английский

---

Advancements in additive manufacturing of polymer matrix composites: A systematic review of techniques and properties

Materials Today Communications, Journal Year: 2023, Volume and Issue: 36, P. 106449 - 106449

Published: June 16, 2023

Language: Английский

---

Machine learning for predicting fatigue properties of additively manufactured materials

Chinese Journal of Aeronautics, Journal Year: 2023, Volume and Issue: 37(4), P. 1 - 22

Published: Nov. 7, 2023

Fatigue properties of materials by Additive Manufacturing (AM) depend on many factors such as AM processing parameter, microstructure, residual stress, surface roughness, porosities, post-treatments, etc. Their evaluation inevitably requires these combined possible, thus resulting in low efficiency and high cost. In recent years, their assessment leveraging the power Machine Learning (ML) has gained increasing attentions. A comprehensive overview state-of-the-art progress applying ML strategies to predict fatigue materials, well dependence post-processing parameters laser power, scanning speed, layer height, hatch distance, built direction, post-heat temperature, etc., were presented. few attempts employing Feedforward Neural Network (FNN), Convolutional (CNN), Adaptive Network-Based Fuzzy System (ANFS), Support Vector (SVM) Random Forest (RF) life RF crack growth rate are summarized. The models for predicting materials' found intrinsically similar commonly used ones, but modified involve features. Finally, an outlook challenges (i.e., small dataset, multifarious features, overfitting, interpretability, unable extension from material data structure life) potential solutions prediction is provided.

Language: Английский

---

Computational Modelling and Experimental Challenges of Linear and Nonlinear Analysis of Porous Graded Structure: A Comprehensive Review

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 30(5), P. 3437 - 3452

Published: March 20, 2023

Language: Английский

---

The use of machine learning in process–structure–property modeling for material extrusion additive manufacturing: a state-of-the-art review

Journal of the Brazilian Society of Mechanical Sciences and Engineering, Journal Year: 2024, Volume and Issue: 46(2)

Published: Jan. 11, 2024

Language: Английский

---

Assessment of friction stir spot welding of AA5052 joints via machine learning

Acta Mechanica, Journal Year: 2024, Volume and Issue: 235(4), P. 1945 - 1960

Published: Jan. 4, 2024

Language: Английский

---

Mechanical, Thermal, and Electrical Properties on 3D Printed Short Carbon Fiber Reinforced Polypropylene Composites

ACS Applied Polymer Materials, Journal Year: 2024, Volume and Issue: 6(7), P. 3787 - 3795

Published: March 18, 2024

Carbon fiber-reinforced polymer-matrix composites have been an important research topic due to their high performance and versatility. In this study, we investigated the mechanical, thermal, electrical properties of short carbon polypropylene (SCF/PP) prepared using fused deposition modeling (FDM)-3D printing technique. PP was selected as matrix for 3D printed overcome processing problems caused by content SCFs. The addition SCFs also effectively mitigated warping problem during cooling process. Compared pure PP, tensile strength increased up 35%, bending exhibited approximate 40% enhancement. With increasing SCF content, thermal conductivity a linear growth, reaching 0.266 W/(m · K) at 70 °C PPCF50 sample, simultaneously demonstrating excellent conductivity. material displayed significant potential in electromagnetic protection applications, achieving maximum shielding effectiveness 29.8 dB. texture direction filling density settings proven play roles adjusting composite samples. attempt study is beneficial promoting widespread application polyolefin polymers consumable SCF-reinforced products.

Language: Английский

---

Predicting meltpool depth and primary dendritic arm spacing in laser powder bed fusion additive manufacturing using physics-based machine learning

Materials & Design, Journal Year: 2023, Volume and Issue: 237, P. 112540 - 112540

Published: Dec. 19, 2023

The long-term goal of this work is to predict and control the microstructure evolution in metal additive manufacturing processes. In pursuit goal, we developed applied an approach which combines physics-based thermal modeling with data-driven machine learning two important microstructure-related characteristics, namely, meltpool depth primary dendritic arm spacing Nickel Alloy 718 parts made using laser powder bed fusion (LPBF) process. Microstructure characteristics are critical determinants functional physical properties, e.g., yield strength fatigue life. Currently, LPBF optimized through a cumbersome build-and-characterize empirical approach. Rapid accurate models for predicting therefore valuable reduce process development time achieve consistent properties. However, owing their computational complexity, existing limited few layers, challenging scale practical parts. This paper addresses aforementioned research gap via novel physics data integrated consists steps. First, rapid, part-level model was used temperature distribution cooling rate entire part before it printed. Second, foregoing history quantifiers were as inputs simple (support vector machine) trained based on materials characterization data. As example its efficacy, when tested separate set samples from different build, predicted root mean squared error ≈ 110 nm. thus presents avenue future optimization LPBF.

Language: Английский

---

Application of graphene origami metamaterials to improve nonlinear vibrations of the cars’ hood door under transient loading: Introducing machine learning method for solving the nonlinear problem

Materials Today Communications, Journal Year: 2024, Volume and Issue: 39, P. 109278 - 109278

Published: May 21, 2024

Language: Английский

---