Cyber-Physical Hybrid Processing System Digital Twin

2021 ◽  
Vol 1037 ◽  
pp. 119-124
Author(s):  
Dmitrii Shatagin ◽  
Andrei Galkin ◽  
Alexander N. Osmehin ◽  
Natalia Klochkova
Keyword(s):  
3D Printing ◽  
Processing System ◽  
Current Strength ◽  
Electric Arc ◽  
Diagnostic Parameter ◽  
Optimal Parameters ◽  
Digital Twin ◽  
Machine Learning Methods ◽  
The Stability ◽  
Printing Processes

The article proposes a method for obtaining a digital twin of the process of 3D printing by electric arc surfacing using an ensemble of machine learning methods. On the basis of the structural-parametric approach, a set of diagnostic parameters for the signals of current strength, voltage and acoustic emission was determined. Using exploratory analysis, the significance of each diagnostic parameter was assessed. A complex of statistical models has been developed to assess the stability of 3D printing processes using decision trees. Their optimal parameters and efficiency have been determined.

Diagnostics of the 3D printing process on a CNC machine using machine learning approaches

2021 ◽  
pp. 55-59
Author(s):  
Yu.G. Kabaldin ◽  
D.A. Shatagin ◽  
M.S. Anosov ◽  
P.V. Kolchin ◽  
A.V. Kiselev
Keyword(s):  
Nonlinear Dynamics ◽  
Machine Learning ◽  
3D Printing ◽  
Electric Arc ◽  
Cyber Physical System ◽  
Learning Approaches ◽  
Cnc Machine ◽  
Printing Process ◽  
Optimization Of Process Parameters ◽  
The Stability

Diagnostics and optimization of the dynamics of an electric arc during 3D printing on a CNC machine are considered. The application of nonlinear dynamics methods in assessing the stability of the 3D printing process and the use of artificial neural networks in the classification and optimization of process parameters are shown. Keywords: 3D printing, cyber physical system, machine learning, hybrid processing, neuroform controller, diagnostics, digital twin. [email protected]

Cold Resistance and Mechanical Properties of 07Cr25Ni13 (ER309LSI) Stainless Steel Obtained by 3D Printing by Electric Arc Surfacing on a CNC Machine

2021 ◽  
Vol 1037 ◽  
pp. 65-70
Author(s):  
Dmitrii Shatagin ◽  
Maksim S. Anosov ◽  
Pavel Kolchin ◽  
Dmitry A. Ryabov ◽  
Andrey V. Kiselev
Keyword(s):  
Mechanical Properties ◽  
Heat Treatment ◽  
Stainless Steel ◽  
3D Printing ◽  
Dynamic Stability ◽  
Cold Resistance ◽  
Intelligent System ◽  
Electric Arc ◽  
Cnc Machine ◽  
The Stability

The article discusses the mechanical properties and cold resistance of austenitic stainless steel (analogue 07Cr25Ni13) obtained by 3D printing by electric arc surfacing from ER309LSI welding wire on a CNC machine. These properties were investigated in the process of physical tests of samples cut along and across the layers of 3D printing for tensile and impact bending. Using optical microscopy, the microstructures of steel sections were obtained for various temperature conditions of interlayer exposure, as well as the values ​​of the recommended microhardness. In the process of 3D printing, an intelligent system for monitoring the dynamic stability of the electric arc was applied, which made it possible to guarantee the stability of the structure and properties of the obtained samples throughout the entire process of surfacing. Additional heat treatment of experimental samples (austenitization) was considered as a way to improve mechanical properties and cold resistance. It has been established that the dynamic stability of an electric arc, modes of interlayer temperature holding and subsequent heat treatment largely determine the mechanical properties and cold resistance of ER309LSI steel obtained by 3D printing by electric arc surfacing.

scholarly journals A perspective on Using Machine Learning in 3D Bioprinting

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Chunling Yu ◽  
Jingchao Jiang
Keyword(s):  
Machine Learning ◽  
3D Printing ◽  
Three Dimensional ◽  
Dimensional Accuracy ◽  
Accuracy Analysis ◽  
3D Bioprinting ◽  
Daily Lives ◽  
Property Prediction ◽  
Machine Learning Methods ◽  
Printing Processes

Recently, three-dimensional (3D) printing technologies have been widely applied in industry and our daily lives. The term 3D bioprinting has been coined to describe 3D printing at the biomedical level. Machine learning is currently becoming increasingly active and has been used to improve 3D printing processes, such as process optimization, dimensional accuracy analysis, manufacturing defect detection, and material property prediction. However, few studies have been found to use machine learning in 3D bioprinting processes. In this paper, related machine learning methods used in 3D printing are briefly reviewed and a perspective on how machine learning can also benefit 3D bioprinting is discussed. We believe that machine learning can significantly affect the future development of 3D bioprinting and hope this paper can inspire some ideas on how machine learning can be used to improve 3D bioprinting.

Influence of Constructive and Technological Parameters at Generated Spiral Parts with DLP 3D Printing Process

2019 ◽  
Vol 56 (4) ◽  
pp. 801-811
Author(s):  
Mircea Dorin Vasilescu
Keyword(s):  
3D Printing ◽  
Great Influence ◽  
Polymerization Process ◽  
Generation Process ◽  
Technological Parameters ◽  
Printing Process ◽  
The Third ◽  
Solid Models ◽  
Specific Factors ◽  
Printing Processes

This work are made for determine the possibility of generating the specific parts of a threaded assembly. If aspects of CAD generating specific elements was analysed over time in several works, the technological aspects of making components by printing processes 3D through optical polymerization process is less studied. Generating the threaded appeared as a necessity for the reconditioning technology or made components of the processing machines. To determine the technological aspects of 3D printing are arranged to achieve specific factors of the technological process, but also from the specific elements of a trapezoidal thread or spiral for translate granular material in supply process are determined experimentally. In the first part analyses the constructive generation process of a spiral element. In the second part are identified the specific aspects that can generation influence on the process of realization by 3D DLP printing of the two studied elements. The third part is affected to printing and determining the dimensions of the analysed components. We will determine the specific value that can influence the process of making them in rapport with printing process. The last part is affected by the conclusions. It can be noticed that both the orientation and the precision of generating solid models have a great influence on the made parts.

scholarly journals Development of a Decision Support System for 3D Printing Processes based on Cyber Physical Production Systems

Procedia CIRP ◽  
2021 ◽  
Vol 98 ◽  
pp. 348-353
Author(s):  
Rishi Kumar ◽  
Christopher Rogall ◽  
Sebastian Thiede ◽  
Christoph Herrmann ◽  
Kuldip Singh Sangwan
Keyword(s):  
Decision Support ◽  
3D Printing ◽  
Decision Support System ◽  
Support System ◽  
Production Systems ◽  
Cyber Physical Production Systems ◽  
Printing Processes

Human exposure to metals in consumer-focused fused filament fabrication (FFF)/ 3D printing processes

2021 ◽  
pp. 152622
Author(s):  
Getachew Tedla ◽  
Annie M. Jarabek ◽  
Peter Byrley ◽  
William Boyes ◽  
Kim Rogers
Keyword(s):  
3D Printing ◽  
Human Exposure ◽  
Fused Filament Fabrication ◽  
Printing Processes

scholarly journals Embracing 3D Printing

2015 ◽  
Vol 137 (08) ◽  
pp. 42-45
Author(s):  
Mike Vasquez
Keyword(s):  
3D Printing ◽  
Three Dimensional ◽  
Product Line ◽  
Three Dimensional Objects ◽  
Clear Vision ◽  
Materials Used ◽  
Save Energy ◽  
High Level ◽  
Printing Processes ◽  
Lower Material

This article reviews the challenges for companies while adopting three-dimensional (3D) printing technology. A big challenge for companies figuring out whether they need to invest in 3-D printing is the different types of printing systems available in the market. At a high level, there are seven different families of 3-D printing processes. Each of the seven technologies is differentiated by the materials used and how the materials are fused together to create three-dimensional objects. Another barrier is that most companies have not yet found it viable to put the processes in place to incorporate the change in design, engineering, and manufacturing production that is required. Not only capital funds are needed to purchase machines, but to effectively use the technology to create a sellable product, one also needs to have a targeted product line and clear vision of the ways that 3-D printing can help lower material costs, save energy, and simplify manufacturing and assembly.

scholarly journals Synergistic application of continuous granulation and selective laser sintering 3D printing for the development of pharmaceutical dosage forms with enhanced dissolution rates and physical properties

2021 ◽  
Author(s):  
Rishi Thakkar ◽  
Yu Zhang ◽  
Jiaxiang Zhang ◽  
Mohammed Maniruzzaman
Keyword(s):  
Solid State ◽  
3D Printing ◽  
Physical Properties ◽  
Dosage Forms ◽  
Flow Properties ◽  
Printing Process ◽  
Powder Bed ◽  
Printing Processes ◽  
Binder Jetting ◽  
Physical Mixtures

AbstractThis study demonstrated the first case of combining novel continuous granulation with powder-based pharmaceutical 3-dimensional (3D) printing processes to enhance the dissolution rate and physical properties of a poorly water-soluble drug. Powder bed fusion (PBF) and binder jetting 3D printing processes have gained much attention in pharmaceutical dosage form manufacturing in recent times. Although powder bed-based 3D printing platforms have been known to face printing and uniformity problems due to the inherent poor flow properties of the pharmaceutical physical mixtures (feedstock). Moreover, techniques such as binder jetting currently do not provide any solubility benefits to active pharmaceutical ingredients (APIs) with poor aqueous solubility (>40% of marketed drugs). For this study, a hot-melt extrusion-based versatile granulation process equipped with UV-Vis process analytical technology (PAT) tools for the in-line monitoring of critical quality attributes (i.e., solid-state) of indomethacin was developed. The collected granules with enhanced flow properties were mixed with vinylpyrrolidone-vinyl acetate copolymer and a conductive excipient for efficient sintering. These mixtures were further characterized for their bulk properties observing an excellent flow and later subjected to a PBF-3D printing process. The physical mixtures, processed granules, and printed tablets were characterized using conventional as well as advanced solid-state characterization. These characterizations revealed the amorphous nature of the drug in the processed granules and printed tablets. Further, the in vitro release testing of the tablets with produced granules as a reference standard depicted a notable solubility advantage (100% drug released in 5 minutes at >pH 6.8) over the pure drug and the physical mixture. Our developed system known as DosePlus combines innovative continuous granulation and PBF-3D printing process which can potentially improve the physical properties of the bulk drug and formulations in comparison to when used in isolation. This process can further find application in continuous manufacturing of granules and additive manufacturing of pharmaceuticals to produce dosage forms with excellent uniformity and solubility advantage.Abstract Figure

scholarly journals Generating stable molecules using imitation and reinforcement learning

2021 ◽  
Author(s):  
Søren Ager Meldgaard ◽  
Jonas Köhler ◽  
Henrik Lund Mortensen ◽  
Mads-Peter Verner Christiansen ◽  
Frank Noé ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Chemical Space ◽  
Training Data ◽  
Graph Representation ◽  
Imitation Learning ◽  
Training Set ◽  
Machine Learning Methods ◽  
Multiple Copies ◽  
The Stability ◽  
3D Information

Abstract Chemical space is routinely explored by machine learning methods to discover interesting molecules, before time-consuming experimental synthesizing is attempted. However, these methods often rely on a graph representation, ignoring 3D information necessary for determining the stability of the molecules. We propose a reinforcement learning approach for generating molecules in cartesian coordinates allowing for quantum chemical prediction of the stability. To improve sample-efficiency we learn basic chemical rules from imitation learning on the GDB-11 database to create an initial model applicable for all stoichiometries. We then deploy multiple copies of the model conditioned on a specific stoichiometry in a reinforcement learning setting. The models correctly identify low energy molecules in the database and produce novel isomers not found in the training set. Finally, we apply the model to larger molecules to show how reinforcement learning further refines the imitation learning model in domains far from the training data.

Sign in / Sign up

Export Citation Format

Share Document