Personalized 3D Printing of Artificial Vertebrae: A Predictive Bone Density Modeling Approach for Robotic Cutting Applications DOI Creative Commons
Heqiang Tian, Ying-Chou Sun, J. Zhao

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(20), P. 9479 - 9479

Published: Oct. 17, 2024

Robotic vertebral plate cutting poses significant challenges due to the complex bone structures of lumbar spine, which consist varying densities in cortical and cancellous regions. This study addresses these by developing a predictive model for robotic force quality recognition through fabrication artificial vertebrae with controlled, consistent density. To address variability density between regions, CT data are utilized predict target density, serving as foundation determining optimal 3D printing process parameters. The proposed methodology integrates Response Surface Methodology (RSM), Back Propagation (BP) neural network, genetic algorithm (GA) systematically evaluate effects key parameters, such filling material flow rate, layer thickness, on printed vertebrae’s A one-factor experimental approach RSM-based central composite design applied build an initial prediction model, followed Sobol’s sensitivity analysis quantify influence each parameter. GA-BP network is then employed rapidly accurately identify parameters different densities. resulting optimized models used fabricate personalized vertebrae, subsequently validated experiments. research not only contributes advancement technology but also provides reliable framework patient-specific surgical planning robot-assisted orthopedic surgery.

Language: Английский

Towards defect-free lattice structures in additive manufacturing: A holistic review of machine learning advancements DOI
Numan Khan,

Hamid Asad,

Sikandar Khan

et al.

Journal of Manufacturing Processes, Journal Year: 2025, Volume and Issue: 144, P. 1 - 53

Published: April 15, 2025

Language: Английский

Citations

1
Machine learning-assisted prediction modeling for anisotropic flexural strength variations in fused filament fabrication of graphene reinforced poly-lactic acid composites DOI
Tapish Raj,

Amrit Tiwary,

Akash Jain

et al.

Progress in Additive Manufacturing, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 26, 2024

Language: Английский

Citations

6
Designing Lightweight 3D-Printable Bioinspired Structures for Enhanced Compression and Energy Absorption Properties DOI Open Access

Akhil Harish,

Naser A. Alsaleh, Mahmoud Ahmadein

et al.

Polymers, Journal Year: 2024, Volume and Issue: 16(6), P. 729 - 729

Published: March 7, 2024

Recent progress in additive manufacturing, also known as 3D printing, has offered several benefits, including high geometrical freedom and the ability to create bioinspired structures with intricate details. Mantis shrimp can scrape shells of prey molluscs its hammer-shaped stick, while beetles have highly adapted forewings that are lightweight, tough, strong. This paper introduces a design approach for lattice by mimicking internal microstructures beetle’s forewing, mantis shrimp’s shell, dactyl club, improved mechanical properties. Finite element analysis (FEA) experimental characterisation printed polylactic acid (PLA) samples were performed determine their compression impact The results showed designing unit cells parallel load direction quasi-static compressive performance, among other structures. gyroid honeycomb insect clubs outperformed improvements ultimate strength, Young’s modulus, drop weight impact. On hand, hybrid designs created merging two different reduced bending deformation control collapse during work holds promise development lattices employing properties, which potential implications lightweight high-performance applications.

Language: Английский

Citations

5
Numerical Investigation of Compressive Strength of Structural Steel Material Under Different Loads According to ASTM D695 Standard DOI Open Access
Muhammed Safa KAMER

Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, Journal Year: 2025, Volume and Issue: 40(1), P. 227 - 237

Published: March 26, 2025

In order to determine the mechanical properties of materials according certain standards, numerical analysis methods are frequently used in addition experimental studies. this study, compressive strength test was numerically modeled a computer environment ASTM D695-15 standard. Analyses were carried out by defining structural steel material for plate designed with specified standard dimensions and 1 mm thickness. analysis, two different loading types, force displacement, examined. Numerical analyzes total twelve situations applying 2, 4, 6, 8, 10 12 N forces where load (FL) applied, 1, 3, 5 6 displacements displacement (DL) applied. The effects types intensities on specimen investigated. all analyses FL DL defined, it determined that as intensity increased, stresses deformation also increased.

Language: Английский

Citations

0
A machine learning approach to refining surface quality and material durability in additive manufacturing DOI

Siva Surya Mulugundam,

Santhosh Kumar Gugulothu,

M Varshith

et al.

Progress in Additive Manufacturing, Journal Year: 2025, Volume and Issue: unknown

Published: March 27, 2025

Language: Английский

Citations

0
Effects of key process parameters on tensile properties and interlayer bonding behavior of 3D printed PLA using fused filament fabrication DOI Creative Commons

Tusharbhai Gajjar,

Chunhui Yang,

Lin Ye

et al.

Progress in Additive Manufacturing, Journal Year: 2024, Volume and Issue: unknown

Published: July 11, 2024

Abstract Fused Filament Fabrication (FFF), also known as Deposition Modelling (FDM), is one of the innovative 3D printing technologies for fabricating complex components and products. Mechanical properties 3D-printed mostly depend on intricate process parameters printing. This study experimentally investigates effects four key parameters, including layer thickness, raster angle, feed rate, nozzle temperature, tensile interfacial bonding behaviours FFF printed Polylactic Acid (PLA), their failure mechanisms. The effect surface roughness evaluated, which critical enhancing manufacturing material performance, expecting to provide a potential guide optimisation improving product quality. experimental results demonstrate that strength improves up 10 7% with increasing temperature (200 °C 220 °C) low rate (60 mm/sec 40 mm/sec) during process. increases 12% decreasing thickness (0.4 mm 0.2 mm) 40% angle (90° 0°). findings indicate FFF-printed PLA samples were significantly influenced by an improvement in observed increase reduction rate. Microstructural SEM analysis was conducted investigate ruptured surfaces samples, focusing interlayer quality morphological characteristics void formation, poor adhesion, insufficient fusion between adjacent contact area parameters. found substantially influence two surfaces.

Language: Английский

Citations

3
XGBoost-based prediction of electrical properties for anode aluminium foil DOI
Yue Zhang, Sining Pan

Materials Today Communications, Journal Year: 2024, Volume and Issue: unknown, P. 110400 - 110400

Published: Sept. 1, 2024

Language: Английский

Citations

3
Comparison of Predictive Modeling Concrete Compressive Strength with Machine Learning Approaches DOI Open Access
Gregorius Airlangga

UKaRsT, Journal Year: 2024, Volume and Issue: 8(1), P. 28 - 41

Published: April 30, 2024

Accurately predicting concrete compressive strength is fundamental for optimizing mix designs, ensuring structural integrity, and advancing sustainable construction practices. Increased demands safer, more durable infrastructure necessitate effective predictive models. This research aims to compare the effectiveness of six machine learning models such as Linear Regression, Random Forest, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Gradient Boosting, XGBoost predict strength. Used a dataset 1030 instances with varying mixture compositions, conducted extensive exploratory data analysis, applied feature engineering scaling enhance model performance. Assessments were performed 5-fold cross-validation approach R-squared (R²) metric. In addition, SHAP value used understand influence each on results. The results revealed that significantly outperformed other models, achieving an average R² 0.9178 standard deviation 0.0296. Notably, Forest Boosting also demonstrated robust capabilities. Based our experiment, these effectively predicted strengths close actual measured values, confirming their practical applicability in civil engineering. values provided insights into significant impact age cement quantity outputs. These highlight advanced ensemble methods' prediction underscore importance enhancing accuracy.

Language: Английский

Citations

2
Prediction of Mechanical Properties of Lattice Structures: An Application of Artificial Neural Networks Algorithms DOI Open Access

Jia-Xuan Bai,

Menglong Li, Jianghua Shen

et al.

Materials, Journal Year: 2024, Volume and Issue: 17(17), P. 4222 - 4222

Published: Aug. 27, 2024

The yield strength and Young’s modulus of lattice structures are essential mechanical parameters that influence the utilization materials in aerospace medical fields. Currently, accurately determining often requires conduction a large number experiments for prediction validation purposes. To save time effort to predict material modulus, based on existing experimental data, finite element analysis is employed expand dataset. An artificial neural network algorithm then used establish relationship model between topology structure (the strength), which analyzed verified. Gibson–Ashby indicates different can be classified into two main deformation forms. obtain an deployed BCC-FCC structures, further optimized validated. Concurrently, disparate gives rise certain discrete form their dominant deformation, consequently affects prediction. In conclusion, using networks feasible approach contribute development

Language: Английский

Citations

1
Personalized 3D Printing of Artificial Vertebrae: A Predictive Bone Density Modeling Approach for Robotic Cutting Applications DOI Creative Commons
Heqiang Tian, Ying-Chou Sun, J. Zhao

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(20), P. 9479 - 9479

Published: Oct. 17, 2024

Robotic vertebral plate cutting poses significant challenges due to the complex bone structures of lumbar spine, which consist varying densities in cortical and cancellous regions. This study addresses these by developing a predictive model for robotic force quality recognition through fabrication artificial vertebrae with controlled, consistent density. To address variability density between regions, CT data are utilized predict target density, serving as foundation determining optimal 3D printing process parameters. The proposed methodology integrates Response Surface Methodology (RSM), Back Propagation (BP) neural network, genetic algorithm (GA) systematically evaluate effects key parameters, such filling material flow rate, layer thickness, on printed vertebrae’s A one-factor experimental approach RSM-based central composite design applied build an initial prediction model, followed Sobol’s sensitivity analysis quantify influence each parameter. GA-BP network is then employed rapidly accurately identify parameters different densities. resulting optimized models used fabricate personalized vertebrae, subsequently validated experiments. research not only contributes advancement technology but also provides reliable framework patient-specific surgical planning robot-assisted orthopedic surgery.

Language: Английский

Citations

0