Integrating Machine Learning into Additive Manufacturing of Metallic Biomaterials: A Comprehensive Review

Journal of Functional Biomaterials, Год журнала: 2025, Номер 16(3), С. 77 - 77

Опубликована: Фев. 21, 2025

The global increase in osteomuscular diseases, particularly bone defects and fractures, has driven the growing demand for metallic implants. Additive manufacturing (AM) emerged as a transformative technology producing high-precision biomaterials with customized properties, offering significant advantages over traditional methods. integration of machine learning (ML) AM shown great promise optimizing fabrication process, enhancing material performance, predicting long-term behavior, development orthopedic implants vascular stents. This review explores application ML biomaterials, focusing on four key areas: (1) component design, where guides optimization multi-component alloys improved mechanical biological properties; (2) structural enabling creation intricate porous architectures tailored to specific functional requirements; (3) process control, facilitating real-time monitoring adjustment parameters; (4) parameter optimization, which reduces costs enhances production efficiency. offers comprehensive overview aspects, presenting relevant research providing an in-depth analysis current state ML-guided techniques biomaterials. It enables readers gain thorough understanding latest advancements this field. Additionally, addresses challenges vivo degradation how models can assist bridging gap between vitro tests clinical outcomes. holds potential accelerate design advanced

Язык: Английский

---

Generative AI in manufacturing: a literature review of recent applications and future prospects

Procedia CIRP, Год журнала: 2025, Номер 132, С. 1 - 6

Опубликована: Янв. 1, 2025

Язык: Английский

---

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

Journal of Manufacturing Processes, Год журнала: 2025, Номер 144, С. 1 - 53

Опубликована: Апрель 15, 2025

Язык: Английский

---

Stress Strain Curve Analysis of Sheet Based TPMS Structures in Quasi Static Compression Test: A Review

Journal of Materials Research and Technology, Год журнала: 2025, Номер unknown

Опубликована: Апрель 1, 2025

Язык: Английский

---

A generalizable framework of solution-guided machine learning with application to nanoindentation of free-standing thin films

Thin-Walled Structures, Год журнала: 2024, Номер 200, С. 111984 - 111984

Опубликована: Май 7, 2024

Язык: Английский

---

Uncertainty quantification for damage detection in 3D-printed auxetic structures using ultrasonic guided waves and a probabilistic neural network

Thin-Walled Structures, Год журнала: 2024, Номер unknown, С. 112466 - 112466

Опубликована: Сен. 1, 2024

Язык: Английский

---

Development and Comparison of Model-Based and Data-Driven Approaches for the Prediction of the Mechanical Properties of Lattice Structures

Journal of Materials Engineering and Performance, Год журнала: 2024, Номер unknown

Опубликована: Окт. 8, 2024

Lattice structures have great potential for several application fields ranging from medical and tissue engineering to aeronautical one. Their development is further speeded up by the continuing advances in additive manufacturing technologies that allow overcome issues typical of standard processes propose tailored designs. However, design lattice still challenging since their properties are considerably affected numerous factors. The present paper aims propose, discuss, compare various modeling approaches describe, understand, predict correlations between mechanical void volume fraction different types fabricated fused deposition 3D printing. Particularly, four proposed: (i) a simplified analytical model; (ii) semi-empirical model combining equations with experimental correction factors; (iii) an artificial neural network trained on data; (iv) numerical simulations finite element analyses. comparison among approaches, data, allows identify performances, advantages, disadvantages each approach, thus giving important guidelines choosing right methodology based needs available data.

Язык: Английский

---

RSM applied to lattice patterns for stiffness optimization

Rapid Prototyping Journal, Год журнала: 2024, Номер 30(11), С. 344 - 355

Опубликована: Окт. 31, 2024

Purpose In this study, response surface methodology (RSM) is applied to a three-point bending stiffness analysis of low-cost material (PLA) specimens printed using FDM technology analyze the performance different internal lattice structures (Octet and IsoTruss principally). The purpose study extend definition from discrete (lattice) model an analytical one for its use in subsequent design phases, capable optimizing type cell be used defining parameters find best stiffness-to-weight ratio. Design/methodology/approach representative function their mechanical behavior extrapolated through two-variable polynomial based on size thickness beam elements characterizing it. obtained thanks several tests performed according scheme RSM. An estimation errors due discontinuities physical also conducted. Physical showed some divergences virtual (ideal) specimens. Findings allowed validate RSM models proposed predict system as size, cells vary. Changes weight follow linear quadratic models, respectively. This generally allows optimal points where ratio at highest. Originality/value Although literature provides numerous references studies parameterizing structures, industrial/practical applications concerning are often still detached theoretical research limited achieving functioning rather than ones. approach here described aimed overcoming limitation. software nTop. Subsequent have validated reliability derived method’s application.

Язык: Английский

---

Neuro-Fuzzy Model Evaluation for Enhanced Prediction of Mechanical Properties in AM Specimens

Applied Sciences, Год журнала: 2024, Номер 15(1), С. 7 - 7

Опубликована: Дек. 24, 2024

This paper explores the integration of adaptive neuro-fuzzy inference systems (ANFIS) with additive manufacturing (AM) to enhance prediction mechanical properties in 3D-printed components. Despite AM’s versatility producing complex geometries, achieving consistent performance remains challenging due various process parameters and anisotropic behavior printed parts. The proposed approach combines learning capabilities neural networks decision-making strengths fuzzy logic, enabling ANFIS refine printing improve part quality. Experimental data collected from AM processes are used train model, allowing it predict outputs such as stress, strain, Young’s modulus under values. predictive model was assessed root mean square error (RMSE) coefficient determination (R2) evaluation metrics. study initially examined impact key on subsequently compared two partitioning techniques—grid subtractive clustering—to identify most effective configuration. experimental results analysis demonstrated that could dynamically adjust parameters, leading significant improvements accuracy modulus, showcasing its potential address inherent complexities processes.

Язык: Английский

---

Rapid Prediction and Parameter Sensitivity Analysis of Damage in Rectangular Welded Plates Under Repeated Blast Loads Based on Deep Neural Network

Опубликована: Янв. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Язык: Английский

---