scholarly journals Prediction of Inclusion Types From BSE Images: RF vs. CNN

2021 ◽  
Vol 8 ◽  
Author(s):  
Mohammad Abdulsalam ◽  
Nan Gao ◽  
Bryan A. Webler ◽  
Elizabeth A. Holm
Keyword(s):  
Prediction Models ◽  
Complex Calcium ◽  
Class Model ◽  
Eds Analysis ◽  
Binary Model ◽  
Metallic Inclusions ◽  
Calcium Aluminates ◽  
Steel Properties ◽  
Class Models ◽  
Scanning Electron

The analysis of non-metallic inclusions is crucial for the assessment of steel properties. Scanning electron microscopy (SEM) coupled with energy dispersive spectroscopy (EDS) is one of the most prominent methods for inclusion analysis. This study utilizes the output generated from SEM/EDS analysis to predict inclusion types from BSE images. Prediction models were generated using two different algorithms, Random Forest (RF) and convolutional neural networks (CNN), for comparison. For each method, three separate models were developed. Starting with a simple binary model to differentiate between inclusions and non-inclusions, then developing to more complex four and five class models. For the 4-class model, inclusions were split into oxides, sulfides, and oxy-sulfides, in addition to the non-inclusion class. The 5-class model included specific types of inclusions only, namely alumina, calcium aluminates, calcium sulfides, complex calcium-manganese sulfides, and oxy-sulfide inclusions. CNN achieved better accuracy for the binary (92%) and 4-class (78%) models, compared to RF (binary 87%, 4-class 75%). For the 5-class model, the results were similar, 60% accuracy for RF and 59% for CNN.

scholarly journals A tool for finding inclusion clusters in steel SEM specimens

2020 ◽  
Vol 10 (1) ◽  
pp. 642-648
Author(s):  
Anna-Mari Wartiainen ◽  
Markus Harju ◽  
Satu Tamminen ◽  
Leena Määttä ◽  
Tuomas Alatarvas ◽  
...  
Keyword(s):  
Prediction Models ◽  
Microscopic Analysis ◽  
Steel Specimen ◽  
Sem Analysis ◽  
Quality Prediction ◽  
Automatic Production ◽  
Automatic Interpretation ◽  
Metallic Inclusions ◽  
Purity Analysis ◽  
Inclusions In Steel

AbstractNon-metallic inclusions, especially large or clustered inclusions, in steel are usually harmful. Thus, the microscopic analysis of test specimens is an important part of the quality control. This steel purity analysis produces a large amount of individual inclusion information for each test specimen. The interpretation of the results is laborious and the comparison of larger product groups practically impossible. The purpose of this study was to develop an easy-to-use tool for automatic interpretation of the SEM analysis to differentiate clustered and large inclusions information from the manifold individual inclusion information. Because of the large variety of the potential users, the tool needs to be applicable for any steel grade and application, both for liquid and final product specimen, to analyse automatically steel specimen inclusions, especially inclusion clusters, based on the INCA Feature program produced data from SEM/EDS. The developed tool can be used to improve the controlling of the steel purity or for automatic production of new inclusion cluster features that can be utilised further in quality prediction models, for example.

Scanning Electron Microscopy Coupled with Energy Dispersive Spectrometric Analysis Reveals for the First Time Weddellite and Sylvite Crystals on the Surface of Involucral Bracts and Petals of two Xeranthemum L. (Compositae) Species

2017 ◽  
Vol 23 (3) ◽  
pp. 679-686 ◽  
Author(s):  
Milan Gavrilović ◽  
Suzana Erić ◽  
Petar D. Marin ◽  
Núria Garcia-Jacas ◽  
Alfonso Susanna ◽  
...  
Keyword(s):  
Electron Microscopy ◽  
Scanning Electron Microscopy ◽  
Glandular Trichomes ◽  
Energy Dispersive ◽  
Spectrometric Analysis ◽  
Eds Analysis ◽  
Taxonomic Studies ◽  
First Time ◽  
Tetragonal Bipyramid ◽  
Scanning Electron

AbstractIn this work, weddellite and sylvite crystals are identified for the first time on the involucral bracts and petals of Xeranthemum annuum and Xeranthemum cylindraceum using scanning electron microscopy coupled with energy dispersive spectrometric (SEM-EDS) analysis. Well-developed crystals of weddellite (CaC2O4·2H2O) occur in the form of a tetragonal bipyramid (hhl), rarely in combination of a bipyramid and tetragonal prism (h00). Indumentum of involucral bracts of X. cylindraceum consists of nonglandular and glandular trichomes. Sylvite (KCl) crystals are observed only on the petal surface of X. cylindraceum. The crystals of sylvite occur in the form of perfect cubes (hexahedrons), but some crystals are deformed, i.e., partially elongated. Taxonomic significance of investigated microcharacters as well as the use of SEM-EDS analysis in taxonomic studies of plants are discussed.

Effects of Vanadium Microalloying on Hardness of Alloy ZG270-500

2011 ◽  
Vol 216 ◽  
pp. 397-401
Author(s):  
Hai Tao Wang ◽  
Bing Xi Huang ◽  
Li Jian Wang
Keyword(s):  
Lattice Distortion ◽  
Induction Furnace ◽  
Intermediate Frequency ◽  
Shrinkage Porosity ◽  
Hardness Distribution ◽  
Liquid Feeding ◽  
Eds Analysis ◽  
Solid Phases ◽  
Front Section ◽  
Scanning Electron

The effects of vanadium microalloying on the hardness and its distribution of alloy ZG270-500 smelted in intermediate frequency induction furnace were studied. Vanadium microalloying increased the hardness of test alloys effectively. By scanning electron microscope (SEM) and energy disperse spectroscope (EDS) analysis, it was found that VC was the powerful heterogeneous nuclei, which prompted numerous nucleating, refined the structure grains and caused the serious crystallographic lattice distortion, so the hardness increased. Proper content of vanadium prompted more even hardness distribution across the whole temperature front section. However, overdoes vanadium microalloying easily caused mass oxides of V2O3, which kept solid phases with high meting point in metal liquid to increase the viscosity and decrease the fluidity of metal liquid, resulting in inadequate metal liquid feeding, serious structure shrinkage porosity in center and worse hardness distribution along the different isotherm fields. 0.16wt.% vanadium microalloying brought the optimal hardness uniformity among test alloys with the approximate 1 hardness ratio R between the center and the margin.

Effect of the sample form on the corrosion behavior of steels for concrete in 3% NaCl medium

2021 ◽  
Vol 109 (2) ◽  
pp. 201
Author(s):  
Laidi Babouri ◽  
Cheikh Mokrani ◽  
Yassine El Mendili
Keyword(s):  
Electron Microscopy ◽  
Linear Polarization ◽  
Saline Solution ◽  
Electrochemical Impedance ◽  
Nacl Solution ◽  
Tafel Polarization ◽  
Eds Analysis ◽  
Corrosion Of Steel ◽  
Surface Morphologies ◽  
Scanning Electron

Corrosion of steel constitutes a major preoccupation in the field of civil engineering and the building sector. In this paper, we investigated the electrochemical behavior of two steel specimens with different forms (latched steel and smooth steel) in a 3 wt.% NaCl solution. For this purpose, we studied the steel samples by linear polarization, potentiodynamic polarization and electrochemical impedance spectroscopy (EIS). The surface morphologies of the substrates were examined by scanning electron microscopy coupled with energy diffraction spectroscopy (SEM/EDS). Results of linear polarization, Tafel polarization curves and EIS show that latched steel (LS) is more susceptible to corrosion than smooth steel (SS) in saline solution. Gravimetric and SEM/EDS analysis after 10 days of immersion confirmed the results obtained by electrochemical methods. All of our results are in agreement and demonstrate that the sample form plays a key role in corrosion resistance.

Enhancement of SEM/EDS Analysis Using FIB Sample Preparation

1999 ◽  
Vol 5 (S2) ◽  
pp. 896-897
Author(s):  
C.B. Vartuli ◽  
F.A. Stevie ◽  
J.B. Bindell ◽  
T.L. Shofner ◽  
B.M. Purcell
Keyword(s):  
Electron Microscopy ◽  
Focused Ion Beam ◽  
Ion Beam ◽  
Primary Electron ◽  
Primary Electron Beam ◽  
Interaction Volume ◽  
Eds Analysis ◽  
Overlapping Peaks ◽  
Large Interaction ◽  
Scanning Electron

Scanning Electron Microscopy/Energy Dispersive Spectroscopy (SEM/EDS) has become less useful for semiconductor samples as feature dimensions decrease. It has become increasingly difficult to get sufficient signal from small features because of the large interaction volume of the primary beam. As the interaction volume is dependent on the accelerating energy of the primary electron beam, decreasing the accelerating voltage will decrease the interaction volume. This increases the percentage of signal from the feature of interest, but also lowers the number of peaks available for interpretation, reducing the sensitivity of the analysis. Several elements commonly used in the fabrication of semiconductors have overlapping peaks at lower energies, and the ability to distinguish between them is lost at low accelerating energies. It is possible to modify samples using Focused Ion Beam (FIB) to improve EDS resolution without decreasing the accelerating voltage.The samples were prepared in an FIE 800 FIB and imaged in an Hitachi S-4700 SEM.

Bayesian nonparametric latent class model for longitudinal data

2020 ◽  
Vol 29 (11) ◽  
pp. 3381-3395
Author(s):  
Wonmo Koo ◽  
Heeyoung Kim
Keyword(s):  
Longitudinal Data ◽  
Latent Class ◽  
Latent Class Model ◽  
Latent Class Models ◽  
Model Parameters ◽  
Latent Classes ◽  
Bayesian Nonparametric ◽  
Class Model ◽  
Proposed Model ◽  
Class Models

Latent class models have been widely used in longitudinal studies to uncover unobserved heterogeneity in a population and find the characteristics of the latent classes simultaneously using the class allocation probabilities dependent on predictors. However, previous latent class models for longitudinal data suffer from uncertainty in the choice of the number of latent classes. In this study, we propose a Bayesian nonparametric latent class model for longitudinal data, which allows the number of latent classes to be inferred from the data. The proposed model is an infinite mixture model with predictor-dependent class allocation probabilities; an individual longitudinal trajectory is described by the class-specific linear mixed effects model. The model parameters are estimated using Markov chain Monte Carlo methods. The proposed model is validated using a simulated example and a real-data example for characterizing latent classes of estradiol trajectories over the menopausal transition using data from the Study of Women’s Health Across the Nation.

scholarly journals Scanning Electron Microscopy–Energy-Dispersive X-ray Spectrometry (SEM–EDS) Analysis of PM1–2 Microspheres Located in Coal Char Particles with Different Morphologies

2020 ◽  
Vol 34 (7) ◽  
pp. 8848-8856
Author(s):  
Elena V. Fomenko ◽  
Vladimir V. Yumashev ◽  
Sergey V. Kukhtetskiy ◽  
Anatoliy M. Zhizhaev ◽  
Alexander G. Anshits
Keyword(s):  
Electron Microscopy ◽  
Scanning Electron Microscopy ◽  
Coal Char ◽  
Energy Dispersive ◽  
X Ray ◽  
Eds Analysis ◽  
Scanning Electron

Analysis of Inclusion Microstructure in Material Engineering of Steel

2012 ◽  
Vol 568 ◽  
pp. 324-327
Author(s):  
Ding Guo Zhao ◽  
Shu Huan Wang ◽  
Ming Jian Guo
Keyword(s):  
Electron Microscopy ◽  
High Carbon Steel ◽  
Oxide Inclusion ◽  
Raw Material ◽  
High Carbon ◽  
Silicate Inclusion ◽  
Calcium Aluminates ◽  
Material Requirement ◽  
Lf Refining ◽  
Scanning Electron

The sample of oxide inclusion was obtained in the different stage of steelmaking for the 65 steel. The microstructure was observed by using scanning electron microscopy (SEM) to analyze the composition and type of inclusions. It was shown that the microscopic inclusions in the high carbon steel were mainly massive and cluster Al2O3, spherical and slope silicate inclusion, calcium-aluminates inclusions and sulphide complex inclusions. The measures including raw material requirement, improving of the converter, LF refining and continuous casting operations were put forward to decrease inclusion.

Non-Metallic Inclusions in Mg-RE-Zr Casting Alloys

2014 ◽  
Vol 782 ◽  
pp. 398-403
Author(s):  
Bartłomiej Dybowski ◽  
Andrzej Kiełbus
Keyword(s):  
Electron Microscopy ◽  
Scanning Electron Microscopy ◽  
Liquid Metal ◽  
Magnesium Alloys ◽  
Gating System ◽  
Mould Material ◽  
Casting Alloys ◽  
Metallic Inclusions ◽  
Liquid Metal Surface ◽  
Scanning Electron

Non-metallic inclusions in Elektron 21 and WE43 magnesium alloys have been investigated by means of scanning electron microscopy. Investigations were conducted both on the fracture surfaces and microsections. Researches revealed presence of alloying elements oxides, inclusions originating in mould material and inclusions originating in the fluxes covering liquid metal surface in the cruicible. The number of inclusions is reduced by application of complex gating system and by leaving small amount of alloy in the cruicible after the pouring process.

Sign in / Sign up

Export Citation Format

Share Document