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.

Detecting Malicious Defects in 3D Printing Process Using Machine Learning and Image Classification

2016 ◽  
Author(s):  
Mingtao Wu ◽  
Vir V. Phoha ◽  
Young B. Moon ◽  
Amith K. Belman
Keyword(s):  
Machine Learning ◽  
3D Printing ◽  
Image Classification ◽  
Decision Trees ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Naive Bayes Classifier ◽  
Bayes Classifier ◽  
Naïve Bayes Classifier ◽  
Printing Process

3D printing, or additive manufacturing, is a key technology for future manufacturing systems. However, 3D printing systems have unique vulnerabilities presented by the ability to affect the infill without affecting the exterior. In order to detect malicious infill defects in 3D printing process, this paper proposes the following: 1) investigate malicious defects in the 3D printing process, 2) extract features based on simulated 3D printing process images, and 3) an experiment of image classification with one group of non-defect infill image and the other group of defect infill training image from 3D printing process. The images are captured layer by layer from the top view of software simulation preview. The data extracted from images is input to two machine learning algorithms, Naive Bayes Classifier and J48 Decision Trees. The result shows Naive Bayes Classifier has an accuracy of 85.26% and J48 Decision Trees has an accuracy of 95.51% for classification.

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.

scholarly journals 3D-Printing and Machine Learning Control of Soft Ionic Polymer-Metal Composite Actuators

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
James D. Carrico ◽  
Tucker Hermans ◽  
Kwang J. Kim ◽  
Kam K. Leang
Keyword(s):  
Machine Learning ◽  
3D Printing ◽  
Bayesian Optimization ◽  
Metal Composite ◽  
Ionic Polymer Metal Composite ◽  
Printing Process ◽  
Ionic Polymer ◽  
Control Paradigm ◽  
Polymer Metal ◽  
And Control

AbstractThis paper presents a new manufacturing and control paradigm for developing soft ionic polymer-metal composite (IPMC) actuators for soft robotics applications. First, an additive manufacturing method that exploits the fused-filament (3D printing) process is described to overcome challenges with existing methods of creating custom-shaped IPMC actuators. By working with ionomeric precursor material, the 3D-printing process enables the creation of 3D monolithic IPMC devices where ultimately integrated sensors and actuators can be achieved. Second, Bayesian optimization is used as a learning-based control approach to help mitigate complex time-varying dynamic effects in 3D-printed actuators. This approach overcomes the challenges with existing methods where complex models or continuous sensor feedback are needed. The manufacturing and control paradigm is applied to create and control the behavior of example actuators, and subsequently the actuator components are combined to create an example modular reconfigurable IPMC soft crawling robot to demonstrate feasibility. Two hypotheses related to the effectiveness of the machine-learning process are tested. Results show enhancement of actuator performance through machine learning, and the proof-of-concepts can be leveraged for continued advancement of more complex IPMC devices. Emerging challenges are also highlighted.

scholarly journals Assessment of Cold Resistance of 09G2S Steel Obtained Using 3D Printing Technology by Electric Arc Surfacing at a CNC Machine

2020 ◽  
Vol 23 (2) ◽  
pp. 16
Author(s):  
Yu. G. Kabaldin ◽  
A. A. Khlybov ◽  
D. A. Shatagin ◽  
M. S. Anosov ◽  
D. A. Ryabov
Keyword(s):  
3D Printing ◽  
Cold Resistance ◽  
Electric Arc ◽  
Cnc Machine ◽  
Printing Technology ◽  
09G2s Steel ◽  
3D Printing Technology

Приводятся результаты исследований образцов из стали 09Г2С при пониженных температурах, полученных с использованием технологии 3D-печати электродуговой наплавкой. Для сравнения приводятся данные исследований на образцах, полученных из проката.Для достижения поставленной цели были изготовлены и испытаны образцы на ударный изгиб из стали 09Г2С. Образцы печатались с использованием технологии 3D-печати на станке с ЧПУ путем послойного нанесения наплавляемого материала из проволоки 09Г2С. Качество и стабильность структуры материала получаемых образцов обеспечивались за счет постоянной диагностики устойчивости динамической системы «источник питания – дуга – материал».Основным диагностическим параметром, характеризующим степень устойчивости, был показатель фрактальной размерности аттрактора динамической системы.Образцы для исследований вырезались в продольном и поперечном направлениих наплавки, аналогично изготавливались образцы из проката. Исследования полученных образцов проводились с использованием испытаний на ударный изгиб в широком диапазоне пониженных температур от –80 до +20 °C. Для выявления особенностей механизма разрушения и температуры вязкохрупкого перехода металлов проводились фрактографические исследования изломов образцов.В ходе исследований установлено, что температура вязкохрупкого перехода стали 09Г2С, полученной с использованием технологии 3D-печати электродуговой наплавкой, составляет порядка –40 °С, что незначительно выше температуры вязкохрупкого перехода стали 09Г2С, полученной из листового проката с последующим отжигом –47 °С. Следует отметить, что образцы, вырезанные вдоль наплавки, имеют более высокие значения ударной вязкости и температуры вязкохрупкого перехода.Для образцов, полученных электродуговой наплавкой, значения ударной вязкости не более чем на 20 % ниже, чем значения ударной вязкости образцов, полученных механической обработкой из листового проката во всем диапазоне исследуемых температур.Приведенная технология электродуговой наплавки, управляемой компьютером, может быть использована как для изготовления сложных изделий, так и для ремонта. Используя сварочные материалы с низкой температурой вязкохрупкого перехода, в частности используя сталь 09Г2С, можно получить высокие эксплуатационные свойства изделия в короткие сроки даже в арктических условиях.

scholarly journals Deep Learning-Based Election Results Prediction Using Twitter Activity

2021 ◽  
Author(s):  
Haider Ali ◽  
Haleem Farman ◽  
Hikmat Yar ◽  
Zahid Khan ◽  
Shabana Habib ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
General Election ◽  
Learning Approaches ◽  
Social Media Platforms ◽  
General Elections ◽  
Election Results ◽  
Twitter Activity ◽  
The Stability

Abstract Nowadays, political parties have widely adopted social media for their party promotions and election campaigns. During the election, Twitter and other social media platforms are used for political coverage to promote the party and its candidates. This research discusses and estimates the stability of many volumetric social media approaches to forecast election results from social media activities. Numerous machine learning approaches are applied to opinions shared on social media for predicting election results. This paper presents a machine learning model based on sentiment analysis to predict Pakistan's general election results. In a general election, voters vote for their favorite party or candidate based on their personal interests. Social media has been extensively used for the campaign in Pakistan general election 2018. Using a machine learning technique, we provide a five-step process to analyze the overall election results, whether fair or unfair. The work is concluded with detailed experimental results and a discussion on the outcomes of sentiment analysis for real-world forecasting and approval for general elections in Pakistan.

Diagnostics of 3D Printing on a CNC Machine by Machine Learning

2021 ◽  
Vol 41 (4) ◽  
pp. 320-324
Author(s):  
Yu. G. Kabaldin ◽  
D. A. Shatagin ◽  
M. S. Anosov ◽  
P. V. Kolchin ◽  
A. V. Kiselev
Keyword(s):  
Machine Learning ◽  
3D Printing ◽  
Cnc Machine

scholarly journals Mitigating Scattering Effects in Light-Based Three-Dimensional Printing Using Machine Learning

2020 ◽  
Vol 142 (8) ◽  
Author(s):  
Shangting You ◽  
Jiaao Guan ◽  
Jeffrey Alido ◽  
Henry H. Hwang ◽  
Ronald Yu ◽  
...  
Keyword(s):  
Machine Learning ◽  
3D Printing ◽  
Light Exposure ◽  
Three Dimensional ◽  
Exposure Dose ◽  
Printing Process ◽  
Three Dimensional Printing ◽  
Scattering Effects ◽  
3D Printed ◽  
Dimensional Printing

Abstract When using light-based three-dimensional (3D) printing methods to fabricate functional micro-devices, unwanted light scattering during the printing process is a significant challenge to achieve high-resolution fabrication. We report the use of a deep neural network (NN)-based machine learning (ML) technique to mitigate the scattering effect, where our NN was employed to study the highly sophisticated relationship between the input digital masks and their corresponding output 3D printed structures. Furthermore, the NN was used to model an inverse 3D printing process, where it took desired printed structures as inputs and subsequently generated grayscale digital masks that optimized the light exposure dose according to the desired structures’ local features. Verification results showed that using NN-generated digital masks yielded significant improvements in printing fidelity when compared with using masks identical to the desired structures.

Sign in / Sign up

Export Citation Format

Share Document