A review of machine learning (ML) and explainable artificial intelligence (XAI) methods in additive manufacturing (3D Printing)

Materials Today Communications, Journal Year: 2024, Volume and Issue: 41, P. 110294 - 110294

Published: Sept. 6, 2024

Language: Английский

---

Performance evaluation of machine learning techniques in surface roughness prediction for 3D printed micro-lattice structures

Journal of Manufacturing Processes, Journal Year: 2025, Volume and Issue: 137, P. 320 - 341

Published: Feb. 7, 2025

Language: Английский

---

Accelerated design of high-entropy alloy coatings for high corrosion resistance via machine learning

Surface and Coatings Technology, Journal Year: 2025, Volume and Issue: unknown, P. 131978 - 131978

Published: Feb. 1, 2025

Language: Английский

---

Machine Learning-Assisted Stress and Deformation Prediction for 316 L Stainless Steel Hybrid Lattice Structures Fabricated Through Laser Powder Bed Fusion

Materials Today Communications, Journal Year: 2025, Volume and Issue: unknown, P. 112037 - 112037

Published: Feb. 1, 2025

Language: Английский

---

Machine learning for screw design in single‐screw extrusion

Polymer Engineering and Science, Journal Year: 2025, Volume and Issue: unknown

Published: March 10, 2025

Abstract Artificial intelligence (AI) methods have significantly impacted various areas of technology, particularly in fields where large datasets are available. Screw designs proprietary, and there is very limited information available the open literature. In this study, we generated a dataset 232 using computer simulation software for screw extrusion, involving solids transport, melting, melt pumping. The parameters (features) outputs (targets) were introduced into four powerful machine learning (ML) algorithms. capabilities algorithms assessed by comparing predictions each to corresponding results simulations. Three demonstrated satisfactory performance, with best‐performing one being further tested on an “unseen” dataset, which involved 75 mm another 127 diameter. A machine‐learning technique called Permutation Feature Importance (PFI) was used identify features (parameters) greatest impact predictions. It suggested that same ML methodologies could be applied existing real designs. Highlights Dataset obtained from software. Four employed. Assessment based training testing data. Identification having impact. Satisfactory mass flow rate, exit temperature, melting length, more.

Language: Английский

---

Characterisation and prediction of mechanical properties in laser powder bed fusion-printed parts: a comparative analysis using machine learning

Materials Technology, Journal Year: 2024, Volume and Issue: 39(1)

Published: Oct. 25, 2024

This study investigates the effects of process parameters including scanning strategy, build orientation, and hatching distance on mechanical properties AlSi10Mg parts produced by Laser Powder Bed Fusion (L-PBF). The experiment varied these within defined ranges used statistical analysis to evaluate their impact tensile strength ductility. Results showed that strategy had greatest influence, followed distance, while orientation affected anisotropic properties. Microstructural clear correlation between conditions strength, thereby showing underlying mechanisms govern material behavior. Moreover, Machine learning models, Random Forest Regression (RFR), Support Vector (SVR), Artificial Neural Networks (ANNs), were applied predict ductility characteristics. RFR SVR outperformed ANNs, high predictive accuracy with limited datasets. These findings emphasize importance optimizing L-PBF minimize anisotropy achieve consistent in parts.

Language: Английский

---

Explainable Machine Learning for Predicting Tensile Properties of Aluminum Alloys in the Laser Powder Bed Fusion Process

Published: Jan. 1, 2025

The rapid solidification and unique thermal gradients inherent to the laser powder bed fusion (LPBF) process limit suitability of conventional aluminum (Al) alloys, necessitating optimization existing alloys or development new compositions achieve desired tensile properties while ensuring good processability. Experimental exploration alloy is labor-intensive, costly, time-consuming. Machine learning (ML) offers a cost-effective, flexible approach streamline design accelerate advancements in AM technologies. This study introduces data-driven predictive framework for predicting Al LPBF. To address limited data on LPBF restricted range systems investigated, (including cast wrought alloys) laser-directed energy deposition (LDED) built were also included, alongside data. dataset incorporates comprehensive pool features such as composition, processing parameters, grain size, elemental properties. Pearson correlation coefficient (PCC) with feature importance-based selection was implemented balance model complexity accuracy via reducing dimensionality overfitting. resulting ML demonstrates excellent generalizability, successfully extending its applicability unseen systems. reliable tool optimizing designs, significantly reliance costly experimental trials. inclusion Explainable AI provided detailed interpretability, elucidating influence individual predictions, predictions scientifically grounded.

Language: Английский

---

Predicting material properties in AlSi12Mg alloy additive manufacturing using KNN and ANN machine learning techniques

International Journal on Interactive Design and Manufacturing (IJIDeM), Journal Year: 2025, Volume and Issue: unknown

Published: March 24, 2025

Language: Английский

---

Data augmentation and deep learning model to predict the mechanical properties of AlSi10Mg material fabricated using Laser Powder Bed Fusion additive manufacturing

Materials Today Communications, Journal Year: 2025, Volume and Issue: unknown, P. 112288 - 112288

Published: March 1, 2025

Language: Английский

---

Comprehensive Toughness Dataset of Nuclear Reactor Structural Materials using Charpy V-Notch Impact Testing

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: April 1, 2025

Reactor pressure vessel (RPV) steels are critical for maintaining the structural integrity and safety of nuclear reactors, designed to endure extreme conditions over prolonged operational lifetimes. Evaluating mechanical properties RPV frequently involves tests with sub-sized specimens, due size constraints associated irradiated materials. However, reduced specimen dimensions introduce a effect that alters material behavior requires correlating test results full-sized specimens. Although numerous correlation methods have been previously proposed, they typically applicable specific conditions. To address these challenges, this study introduces public dataset 4,961 Charpy impact records steels. The was compiled through comprehensive literature review incorporates data from 109 peer-reviewed publications. It provides detailed information on composition, manufacturing treatments, dimensions, testing conditions, results. primary objective is advance understanding in testing, support studies validating existing developing data-driven approaches correlation.

Language: Английский

---