scholarly journals Predicting the Printability in Selective Laser Melting with a Supervised Machine Learning Method

Materials ◽  
2020 ◽  
Vol 13 (22) ◽  
pp. 5063
Author(s):  
Yingyan Chen ◽  
Hongze Wang ◽  
Yi Wu ◽  
Haowei Wang
Keyword(s):  
Machine Learning ◽  
Selective Laser Melting ◽  
Process Parameter ◽  
Supervised Machine Learning ◽  
Laser Melting ◽  
Metallographic Examination ◽  
Free Process ◽  
Input Variables ◽  
Surface Morphologies

Though selective laser melting (SLM) has a rapidly increasing market these years, the quality of the SLM-fabricated part is extremely dependent on the process parameters. However, the current metallographic examination method to find the parameter window is time-consuming and involves subjective assessments of the experimenters. Here, we proposed a supervised machine learning (ML) method to detect the track defect and predict the printability of material in SLM intelligently. The printed tracks were classified into five types based on the measured surface morphologies and characteristics. The classification results were used as the target output of the ML model. Four indicators had been calculated to evaluate the quality of the tracks quantitatively, serving as input variables of the model. The data-driven model can determine the defect-free process parameter combination, which significantly improves the efficiency in searching the process parameter window and has great potential for the application in the unmanned factory in the future.

scholarly journals Automatic Fault Detection for Selective Laser Melting Using Semi-Supervised Machine Learning

2018 ◽  
Author(s):  
Ikenna A. Okaro ◽  
Sarini Jayasinghe ◽  
Chris Sutcliffe ◽  
Kate Black ◽  
Paolo Paoletti ◽  
...  
Keyword(s):  
Machine Learning ◽  
Selective Laser Melting ◽  
Learning Algorithm ◽  
Supervised Machine Learning ◽  
Value Chains ◽  
Risk Averse ◽  
Laser Melting ◽  
Large Sets ◽  
The Cost

Risk-averse areas such as the medical, aerospace and energy sectors have been somewhat slow towards accepting and applying Additive Manufacturing (AM) in many of their value chains. This is partly because there are still signicant uncertainties concerning the quality of AM builds. This paper introduces a machine learning algorithm for the automatic detection of faults in AM products. The approach is semi-supervised in that, during training, it is able to use data from both builds where the resulting components were certied and builds where the quality of the resulting components is unknown. This makes the approach cost ecient, particularly in scenarios where part certication is costly and time consuming. The study specically analyses Selective Laser Melting (SLM) builds. Key features are extracted from large sets of photodiode data, obtained during the building of 49 tensile test bars. Ultimate tensile strength (UTS) tests were then used to categorise each bar as `faulty' or `acceptable'. A fully supervised approach identied faulty specimens with a 77% success rate while the semi-supervised approach was able to consistently achieve similar results, despite being trained on a fraction of the available certication data. The results show that semi-supervised learning is a promising approach for the automatic certication of AM builds that can be implemented at a fraction of the cost currently required.

scholarly journals Leveraging Road Characteristics and Contributor Behaviour for Assessing Road Type Quality in OSM

2021 ◽  
Vol 10 (7) ◽  
pp. 436
Author(s):  
Amerah Alghanim ◽  
Musfira Jilani ◽  
Michela Bertolotto ◽  
Gavin McArdle
Keyword(s):  
Machine Learning ◽  
Spatial Data ◽  
Classification Accuracy ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Data Set ◽  
Semantic Inference ◽  
Road Type ◽  
The Impact

Volunteered Geographic Information (VGI) is often collected by non-expert users. This raises concerns about the quality and veracity of such data. There has been much effort to understand and quantify the quality of VGI. Extrinsic measures which compare VGI to authoritative data sources such as National Mapping Agencies are common but the cost and slow update frequency of such data hinder the task. On the other hand, intrinsic measures which compare the data to heuristics or models built from the VGI data are becoming increasingly popular. Supervised machine learning techniques are particularly suitable for intrinsic measures of quality where they can infer and predict the properties of spatial data. In this article we are interested in assessing the quality of semantic information, such as the road type, associated with data in OpenStreetMap (OSM). We have developed a machine learning approach which utilises new intrinsic input features collected from the VGI dataset. Specifically, using our proposed novel approach we obtained an average classification accuracy of 84.12%. This result outperforms existing techniques on the same semantic inference task. The trustworthiness of the data used for developing and training machine learning models is important. To address this issue we have also developed a new measure for this using direct and indirect characteristics of OSM data such as its edit history along with an assessment of the users who contributed the data. An evaluation of the impact of data determined to be trustworthy within the machine learning model shows that the trusted data collected with the new approach improves the prediction accuracy of our machine learning technique. Specifically, our results demonstrate that the classification accuracy of our developed model is 87.75% when applied to a trusted dataset and 57.98% when applied to an untrusted dataset. Consequently, such results can be used to assess the quality of OSM and suggest improvements to the data set.

Effect of laser rescanning on Ti6Al4V microstructure during selective laser melting

2020 ◽  
pp. 095440542097609
Author(s):  
Weipeng Duan ◽  
Meiping Wu ◽  
Jitai Han
Keyword(s):  
Wear Resistance ◽  
Titanium Alloy ◽  
Selective Laser Melting ◽  
Human Body ◽  
High Impact ◽  
Laser Melting ◽  
Heat Treated ◽  
Volume Porosity ◽  
Biomedical Field

TC4, which is one of the most widely used titanium alloy, is frequently used in biomedical field due to its biocompatible. In this work, selective laser melting (SLM) was used to manufacture TC4 parts and the printed parts were heat-treated using laser rescanning technology. The experimental results showed that laser rescanning had a high impact on the quality of SLMed part, and a different performance on wear resistance can be found on the basis. It can be seen that the volume porosity of the sample was 7.6 ± 0.5% without using any further processing technology. The volume porosity of the sample processed using laser rescanning strategy was decreased and the square-framed rescanning strategy had a relative optimal volume porosity (1.5 ± 0.3%) in all these five samples. With the further decreasing of volume porosity, the wear resistance decreased at the same time. As its excellent bio-tribological properties, the square-framed rescanning may be a potential suitable strategy to forming TC4 which used in human body.

Liquation and Crystallization Cracks in Aluminum Alloy AA2024 during Selective Laser Melting

2021 ◽  
Vol 410 ◽  
pp. 203-208
Author(s):  
I.S. Loginova ◽  
N.A. Popov ◽  
A.N. Solonin
Keyword(s):  
Aluminum Alloy ◽  
Selective Laser Melting ◽  
Laser Scanning ◽  
Scanning Speed ◽  
Melting Zone ◽  
Alloying Elements ◽  
Laser Melting ◽  
Laser Scanning Speed ◽  
Positive Effect

In this work we studied the microstructure and microhardness of standard AA2024 alloy and AA2024 alloy with the addition of 1.5% Y after pulsed laser melting (PLM) and selective laser melting (SLM). The SLM process was carried out with a 300 W power and 0.1 m/s laser scanning speed. A dispersed microstructure without the formation of crystallization cracks and low liquation of alloying elements was obtained in Y-modified AA2024 aluminum alloy. Eutectic Al3Y and Al8Cu4Y phases were detected in Y-modified AA2024 aluminum alloy. It is led to a decrease in the formation of crystallization cracks The uniform distribution of alloying elements in the yttrium-modified alloy had a positive effect on the quality of the laser melting zone (LMZ) and microhardness.

Development of 3D Finite Element Model for Predicting Process-Induced Defects in Additive Manufacturing by Selective Laser Melting (SLM)

2016 ◽  
Author(s):  
Bilal Hussain ◽  
A. Sherif El-Gizawy
Keyword(s):  
Additive Manufacturing ◽  
Laser Beam ◽  
Selective Laser Melting ◽  
Thermal Stresses ◽  
Cost Effective ◽  
Element Model ◽  
Laser Melting ◽  
Two Phase ◽  
Free Process ◽  
Manufacturing Techniques

Selective Laser Melting (SLM) is one of the important Additive Manufacturing techniques for building functional products. Nevertheless, the absence of accurate models for predicting the SLM process behavior, delays development of cost effective and defects free process. This work presents a coupled thermo-mechanical numerical model to capture the two phase (solid-liquid) solidification melting phenomena that occur in the process. The proposed model will also predict the evolvement of process-induced properties and defects particularly residual stresses caused by temperature gradient and thermal stresses. CO2 or Nd:YAG laser beam can be used as a heat source with a Gaussian distribution for the laser beam energy.

scholarly journals Enlisting Supervised Machine Learning in Mapping Scientific Uncertainty Expressed in Food Risk Analysis

2017 ◽  
Vol 48 (3) ◽  
pp. 608-641 ◽  
Author(s):  
Akos Rona-Tas ◽  
Antoine Cornuéjols ◽  
Sandrine Blanchemanche ◽  
Antonin Duroy ◽  
Christine Martin
Keyword(s):  
Machine Learning ◽  
Food Safety ◽  
Supervised Machine Learning ◽  
Risk Assessments ◽  
Scientific Uncertainty ◽  
Empirical Measure ◽  
Taxonomic Structure ◽  
Safety Risk ◽  
Food Safety Risk

Recently, both sociology of science and policy research have shown increased interest in scientific uncertainty. To contribute to these debates and create an empirical measure of scientific uncertainty, we inductively devised two systems of classification or ontologies to describe scientific uncertainty in a large corpus of food safety risk assessments with the help of machine learning (ML). We ask three questions: (1) Can we use ML to assist with coding complex documents such as food safety risk assessments on a difficult topic like scientific uncertainty? (2) Can we assess using ML the quality of the ontologies we devised? (3) And, finally, does the quality of our ontologies depend on social factors? We found that ML can do surprisingly well in its simplest form identifying complex meanings, and it does not benefit from adding certain types of complexity to the analysis. Our ML experiments show that in one ontology which is a simple typology, against expectations, semantic opposites attract each other and support the taxonomic structure of the other. And finally, we found some evidence that institutional factors do influence how well our taxonomy of uncertainty performs, but its ability to capture meaning does not vary greatly across the time, institutional context, and cultures we investigated.

scholarly journals Effect of Alloying Mn by Selective Laser Melting on the Microstructure and Biodegradation Properties of Pure Mg

Metals ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. 1527
Author(s):  
Bin Xie ◽  
Ming-Chun Zhao ◽  
Ying-Chao Zhao ◽  
Yan Tian ◽  
Dengfeng Yin ◽  
...  
Keyword(s):  
Manganese Oxide ◽  
Selective Laser Melting ◽  
Immersion Test ◽  
Biodegradation Rate ◽  
Laser Melting ◽  
Xps Spectra ◽  
Average Grain Size ◽  
Mn Content ◽  
Surface Morphologies ◽  
Effect Of Alloying

This work studied the effect of alloying Mn by selective laser melting on the microstructure and biodegradation properties of pure Mg. The grains in the microstructure were quasi-polygon in shape. The average grain size was similar (~10 μm) for the SLMed Mg-xMn with different Mn contents. The XPS spectra of the corrosion surface showed that alloying Mn into Mg by SLM produced a relatively protective manganese oxide film, which contributed to decreasing the biodegradation rate. All the results of the electrochemistry test, immersion test and the corrosion surface morphologies coincided well. The SLMed Mg-0.8Mn had the lowest biodegradation rate. When Mn content was more than 0.8 wt.%, the influence of the undissolved Mn phase on the decrease of the biodegradation resistance counteracted the influence of the relatively protective manganese oxide layer on the increase of the biodegradation resistance.

Sign in / Sign up

Export Citation Format

Share Document