scholarly journals Prediction of Mechanical Properties of Three-Dimensional Printed Lattice Structures Through Machine Learning

2021 ◽  
Vol 22 (3) ◽  
Author(s):  
Shuai Ma ◽  
Qian Tang ◽  
Ying Liu ◽  
Qixiang Feng
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
3D Printing ◽  
Unit Length ◽  
Three Dimensional ◽  
3D Models ◽  
Design Stage ◽  
Geometric Feature ◽  
Support Vector ◽  
Lattice Structures

Abstract Lattice structures (LS) manufactured by 3D printing are widely applied in many areas, such as aerospace and tissue engineering, due to their lightweight and adjustable mechanical properties. It is necessary to reduce costs by predicting the mechanical properties of LS at the design stage since 3D printing is exorbitant at present. However, predicting mechanical properties quickly and accurately poses a challenge. To address this problem, this study proposes a novel method that is applied to different LS and materials to predict their mechanical properties through machine learning. First, this study voxelized 3D models of the LS units and then calculated the entropy vector of each model as the geometric feature of the LS units. Next, the porosity, material density, elastic modulus, and unit length of the lattice unit are combined with entropy as the inputs of the machine learning model. The sample set includes 57 samples collected from previous studies. Support vector regression (SVR) was used in this study to predict the mechanical properties. The results indicate that the proposed method can predict the mechanical properties of LS effectively and is suitable for different LS and materials. The significance of this work is that it provides a method with great potential to promote the design process of lattice structures by predicting their mechanical properties quickly and effectively.

scholarly journals Predicting Mechanical Properties of 3D Printed Lattice Structures

2021 ◽  
Author(s):  
Shuai Ma ◽  
Qian Tang ◽  
Ying Liu ◽  
Qixiang Feng
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
3D Printing ◽  
Unit Length ◽  
3D Models ◽  
Design Stage ◽  
Geometric Feature ◽  
Support Vector ◽  
Lattice Structures ◽  
Machine Learning Model

Abstract Lattice structures (LS) manufactured by 3D printing are widely applied in many areas, such as aerospace and tissue engineering, due to their lightweight and adjustable mechanical properties. It is necessary to reduce costs by predicting the mechanical properties of LS at the design stage since 3D printing is exorbitant at present. However, predicting mechanical properties quickly and accurately poses a challenge. To address this problem, this study proposes a novel method that is applied to different LS and materials to predict their mechanical properties through machine learning. First, this study voxelised 3D models of the LS units and then calculated the entropy vector of each model as the geometric feature of the LS units. Next, the porosity, material density, elastic modulus, and unit length of the lattice unit are combined with entropy as the inputs of the machine learning model. The sample set includes 57 samples collected from previous studies. Support vector regression was used in this study to predict the mechanical properties. The results indicate that the proposed method can predict the mechanical properties of LS effectively and is suitable for different LS and materials. The significance of this work is that it provides a method with great potential to promote the design process of lattice structures by predicting their mechanical properties quickly and effectively.

scholarly journals An Overview on the Rheology, Mechanical Properties, Durability, 3D Printing, and Microstructural Performance of Nanomaterials in Cementitious Composites

Materials ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 2950
Author(s):  
Hongwei Song ◽  
Xinle Li
Keyword(s):  
Mechanical Properties ◽  
3D Printing ◽  
Three Dimensional ◽  
Cementitious Materials ◽  
Research Area ◽  
Cementitious Composites ◽  
Split Tensile Strength ◽  
Contour Crafting ◽  
Wide Range ◽  
Active Research

The most active research area is nanotechnology in cementitious composites, which has a wide range of applications and has achieved popularity over the last three decades. Nanoparticles (NPs) have emerged as possible materials to be used in the field of civil engineering. Previous research has concentrated on evaluating the effect of different NPs in cementitious materials to alter material characteristics. In order to provide a broad understanding of how nanomaterials (NMs) can be used, this paper critically evaluates previous research on the influence of rheology, mechanical properties, durability, 3D printing, and microstructural performance on cementitious materials. The flow properties of fresh cementitious composites can be measured using rheology and slump. Mechanical properties such as compressive, flexural, and split tensile strength reveal hardened properties. The necessary tests for determining a NM’s durability in concrete are shrinkage, pore structure and porosity, and permeability. The advent of modern 3D printing technologies is suitable for structural printing, such as contour crafting and binder jetting. Three-dimensional (3D) printing has opened up new avenues for the building and construction industry to become more digital. Regardless of the material science, a range of problems must be tackled, including developing smart cementitious composites suitable for 3D structural printing. According to the scanning electron microscopy results, the addition of NMs to cementitious materials results in a denser and improved microstructure with more hydration products. This paper provides valuable information and details about the rheology, mechanical properties, durability, 3D printing, and microstructural performance of cementitious materials with NMs and encourages further research.

scholarly journals Extrusion Based 3D Printing of Sustainable Biocomposites from Biocarbon and Poly(trimethylene terephthalate)

Molecules ◽  
2021 ◽  
Vol 26 (14) ◽  
pp. 4164
Author(s):  
Elizabeth Diederichs ◽  
Maisyn Picard ◽  
Boon Peng Chang ◽  
Manjusri Misra ◽  
Amar Mohanty
Keyword(s):  
Mechanical Properties ◽  
3D Printing ◽  
Surface Finish ◽  
Three Dimensional ◽  
Morphological Properties ◽  
Great Promise ◽  
Structural Components ◽  
Computer Aided ◽  
Trimethylene Terephthalate ◽  
Optimal Quantity

Three-dimensional (3D) printing manufactures intricate computer aided designs without time and resource spent for mold creation. The rapid growth of this industry has led to its extensive use in the automotive, biomedical, and electrical industries. In this work, biobased poly(trimethylene terephthalate) (PTT) blends were combined with pyrolyzed biomass to create sustainable and novel printing materials. The Miscanthus biocarbon (BC), generated from pyrolysis at 650 °C, was combined with an optimized PTT blend at 5 and 10 wt % to generate filaments for extrusion 3D printing. Samples were printed and analyzed according to their thermal, mechanical, and morphological properties. Although there were no significant differences seen in the mechanical properties between the two BC composites, the optimal quantity of BC was 5 wt % based upon dimensional stability, ease of printing, and surface finish. These printable materials show great promise for implementation into customizable, non-structural components in the electrical and automotive industries.

scholarly journals Exceptional Mechanical Properties and Heat Resistance of Photocurable Bismaleimide Ink for 3D Printing

Materials ◽  
2021 ◽  
Vol 14 (7) ◽  
pp. 1708
Author(s):  
Wenqiang Hua ◽  
Qilang Lin ◽  
Bo Qu ◽  
Yanyu Zheng ◽  
Xiaoying Liu ◽  
...  
Keyword(s):  
Mechanical Properties ◽  
3D Printing ◽  
Heat Resistance ◽  
Three Dimensional ◽  
Mechanical And Thermal Properties ◽  
Amino Group ◽  
Building Models ◽  
Fast Processing ◽  
Forming Precision ◽  
Complex Structural

Photosensitive resins used in three-dimensional (3D) printing are characterized by high forming precision and fast processing speed; however, they often possess poor mechanical properties and heat resistance. In this study, we report a photocurable bismaleimide ink with excellent comprehensive performance for stereolithography (SLA) 3D printing. First, the main chain of bismaleimide with an amino group (BDM) was synthesized, and then, the glycidyl methacrylate was grafted to the amino group to obtain the bismaleimide oligomer with an unsaturated double bond. The oligomers were combined with reaction diluents and photo-initiators to form photocurable inks that can be used for SLA 3D printing. The viscosity and curing behavior of the inks were studied, and the mechanical properties and heat resistance were tested. The tensile strength of 3D-printed samples based on BDM inks could reach 72.6 MPa (166% of that of commercial inks), glass transition temperature could reach 155 °C (205% of that of commercial inks), and energy storage modulus was 3625 MPa at 35 °C (327% of that of commercial inks). The maximum values of T-5%, T-50%, and Tmax of the 3D samples printed by BDM inks reached 351.5, 449.6, and 451.9 °C, respectively. These photocured BDM inks can be used to produce complex structural components and models with excellent mechanical and thermal properties, such as car parts, building models, and pipes.

Bioprinting in ophthalmology: current advances and future pathways

2019 ◽  
Vol 25 (3) ◽  
pp. 496-514 ◽  
Author(s):  
Nataraj Poomathi ◽  
Sunpreet Singh ◽  
Chander Prakash ◽  
Rajkumar V. Patil ◽  
P.T. Perumal ◽  
...  
Keyword(s):  
3D Printing ◽  
Cardiac Tissue ◽  
Human Life ◽  
Three Dimensional ◽  
3D Models ◽  
Eye Diseases ◽  
Biological Research ◽  
Content Type ◽  
Almost All ◽  
Time Of Operation

Purpose Bioprinting is a promising technology, which has gained a recent attention, for application in all aspects of human life and has specific advantages in different areas of medicines, especially in ophthalmology. The three-dimensional (3D) printing tools have been widely used in different applications, from surgical planning procedures to 3D models for certain highly delicate organs (such as: eye and heart). The purpose of this paper is to review the dedicated research efforts that so far have been made to highlight applications of 3D printing in the field of ophthalmology. Design/methodology/approach In this paper, the state-of-the-art review has been summarized for bioprinters, biomaterials and methodologies adopted to cure eye diseases. This paper starts with fundamental discussions and gradually leads toward the summary and future trends by covering almost all the research insights. For better understanding of the readers, various tables and figures have also been incorporated. Findings The usages of bioprinted surgical models have shown to be helpful in shortening the time of operation and decreasing the risk of donor, and hence, it could boost certain surgical effects. This demonstrates the wide use of bioprinting to design more precise biological research models for research in broader range of applications such as in generating blood vessels and cardiac tissue. Although bioprinting has not created a significant impact in ophthalmology, in recent times, these technologies could be helpful in treating several ocular disorders in the near future. Originality/value This review work emphasizes the understanding of 3D printing technologies, in the light of which these can be applied in ophthalmology to achieve successful treatment of eye diseases.

scholarly journals Development of Machine Learning Models to Evaluate the Toughness of OPH Alloys

Materials ◽  
2021 ◽  
Vol 14 (21) ◽  
pp. 6713
Author(s):  
Omid Khalaj ◽  
Moslem Ghobadi ◽  
Ehsan Saebnoori ◽  
Alireza Zarezadeh ◽  
Mohammadreza Shishesaz ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Mechanical Alloying ◽  
Fuzzy Inference ◽  
Oxide Dispersion Strengthened ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Anfis Model ◽  
Inference Systems ◽  
The Impact

Oxide Precipitation-Hardened (OPH) alloys are a new generation of Oxide Dispersion-Strengthened (ODS) alloys recently developed by the authors. The mechanical properties of this group of alloys are significantly influenced by the chemical composition and appropriate heat treatment (HT). The main steps in producing OPH alloys consist of mechanical alloying (MA) and consolidation, followed by hot rolling. Toughness was obtained from standard tensile test results for different variants of OPH alloy to understand their mechanical properties. Three machine learning techniques were developed using experimental data to simulate different outcomes. The effectivity of the impact of each parameter on the toughness of OPH alloys is discussed. By using the experimental results performed by the authors, the composition of OPH alloys (Al, Mo, Fe, Cr, Ta, Y, and O), HT conditions, and mechanical alloying (MA) were used to train the models as inputs and toughness was set as the output. The results demonstrated that all three models are suitable for predicting the toughness of OPH alloys, and the models fulfilled all the desired requirements. However, several criteria validated the fact that the adaptive neuro-fuzzy inference systems (ANFIS) model results in better conditions and has a better ability to simulate. The mean square error (MSE) for artificial neural networks (ANN), ANFIS, and support vector regression (SVR) models was 459.22, 0.0418, and 651.68 respectively. After performing the sensitivity analysis (SA) an optimized ANFIS model was achieved with a MSE value of 0.003 and demonstrated that HT temperature is the most significant of these parameters, and this acts as a critical rule in training the data sets.

scholarly journals Computer-Integrated Manufacturing System for Membrane Structures

2019 ◽  
Vol 258 ◽  
pp. 02025
Author(s):  
Kazuo Yokobori ◽  
Tomo Miura
Keyword(s):  
Membrane Structure ◽  
Three Dimensional ◽  
Numerical Data ◽  
3D Models ◽  
Space Structure ◽  
Computer Integrated Manufacturing ◽  
Support Vector ◽  
Membrane Structures ◽  
Structure Estimation ◽  
Steel Panels

A membrane structure is a space structure composed of a membrane material (fabric or film), cables, and steel frames, among others. It reduces the environmental load for transporting materials and constructions; for instance, compared with conventional roofs that have steel panels or tiles, the membrane structure of a roof is lightweight. Computer analysis and three-dimensional (3D) models are required for determining the stable shape of such tensile structures. It is useful to use computer-integrated systems for the design and manufacturing process because these 3D models consist of numerical data. In this study, we developed a system program based on artificial intelligence methods, with a support vector machine instead of human judgment for the membrane structure estimation and for a probabilistic optimization to predict the differences caused by production loss etc. and compare the results after actual production. And we got close predicted results to the person.

scholarly journals 3D Printing Aids Acetabular Reconstruction in Complex Revision Hip Arthroplasty

2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
Andrew J. Hughes ◽  
Cathal DeBuitleir ◽  
Philip Soden ◽  
Brian O’Donnchadha ◽  
Anthony Tansey ◽  
...  
Keyword(s):  
3D Printing ◽  
Hip Arthroplasty ◽  
Surgical Simulation ◽  
Selective Laser Sintering ◽  
Three Dimensional ◽  
3D Models ◽  
Tactile Feedback ◽  
Revision Hip Arthroplasty ◽  
Acetabular Reconstruction ◽  
Acetabular Cup

Revision hip arthroplasty requires comprehensive appreciation of abnormal bony anatomy. Advances in radiology and manufacturing technology have made three-dimensional (3D) representation of osseous anatomy obtainable, which provide visual and tactile feedback. Such life-size 3D models were manufactured from computed tomography scans of three hip joints in two patients. The first patient had undergone multiple previous hip arthroplasties for bilateral hip infections, resulting in right-sided pelvic discontinuity and a severe left-sided posterosuperior acetabular deficiency. The second patient had a first-stage revision for infection and recurrent dislocations. Specific metal reduction protocols were used to reduce artefact. The images were imported into Materialise MIMICS 14.12®. The models were manufactured using selective laser sintering. Accurate templating was performed preoperatively. Acetabular cup, augment, buttress, and cage sizes were trialled using the models, before being adjusted, and resterilised, enhancing the preoperative decision-making process. Screw trajectory simulation was carried out, reducing the risk of neurovascular injury. With 3D printing technology, complex pelvic deformities were better evaluated and treated with improved precision. Life-size models allowed accurate surgical simulation, thus improving anatomical appreciation and preoperative planning. The accuracy and cost-effectiveness of the technique should prove invaluable as a tool to aid clinical practice.

Digital Design and 3D Printing of Aortic Arch Reconstruction in HLHS for Surgical Simulation and Training

2018 ◽  
Vol 9 (4) ◽  
pp. 454-458 ◽  
Author(s):  
Sarah A. Chen ◽  
Chin Siang Ong ◽  
Nagina Malguria ◽  
Luca A. Vricella ◽  
Juan R. Garcia ◽  
...  
Keyword(s):  
3D Printing ◽  
Aortic Arch ◽  
Surgical Simulation ◽  
Three Dimensional ◽  
3D Models ◽  
Digital Design ◽  
Patient Specific ◽  
Aortic Arch Reconstruction ◽  
Arch Reconstruction ◽  
And Training

Purpose: Patients with hypoplastic left heart syndrome (HLHS) present a diverse spectrum of aortic arch morphology. Suboptimal geometry of the reconstructed aortic arch may result from inappropriate size and shape of an implanted patch and may be associated with poor outcomes. Meanwhile, advances in diagnostic imaging, computer-aided design, and three-dimensional (3D) printing technology have enabled the creation of 3D models. The purpose of this study is to create a surgical simulation and training model for aortic arch reconstruction. Description: Specialized segmentation software was used to isolate aortic arch anatomy from HLHS computed tomography scan images to create digital 3D models. Three-dimensional modeling software was used to modify the exported segmented models and digitally design printable customized patches that were optimally sized for arch reconstruction. Evaluation: Life-sized models of HLHS aortic arch anatomy and a digitally derived customized patch were 3D printed to allow simulation of surgical suturing and reconstruction. The patient-specific customized patch was successfully used for surgical simulation. Conclusions: Feasibility of digital design and 3D printing of patient-specific patches for aortic arch reconstruction has been demonstrated. The technology facilitates surgical simulation. Surgical training that leads to an understanding of optimal aortic patch geometry is one element that may potentially influence outcomes for patients with HLHS.

Sign in / Sign up

Export Citation Format

Share Document