Micromagnetic materials characterization using machine learning

2020 ◽  
Vol 87 (6) ◽  
pp. 428-437
Author(s):  
Klaus Szielasko ◽  
Bernd Wolter ◽  
Ralf Tschuncky ◽  
Sargon Youssef
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Inverse Problem ◽  
Magnetic Behaviour ◽  
Machine Learning Algorithms ◽  
Materials Characterization ◽  
Value Prediction ◽  
Prediction Of Mechanical Properties ◽  
Definition Of ◽  
Insight Into

AbstractMicromagnetic materials characterization is a nondestructive means of predicting mechanical properties and stress of steel and iron products. The method is based on the circumstance that both mechanical and magnetic behaviour relate to microstructure over similar interaction mechanisms, which leads to characteristic correlations between mechanical and magnetic properties of ferromagnetic materials. The prediction of mechanical properties or stress from micromagnetic parameters represents an inverse problem commonly addressed by regression and classification approaches. Challenges for the industrial application of micromagnetic methods lie in the development of robust sensors, definition of significant features, and implementation of powerful machine learning algorithms for a reliable quantitative target value prediction by processing of the micromagnetic features. This contribution briefly explains the background of micromagnetics, describes the typical challenges experienced in practice and provides insight into latest progress in the application of machine learning to micromagnetic data.

Integration of Chemofacies and Rock Mechanical Properties Using Machine Learning Algorithms: Implications for Geomechanics and Hydraulic Fracture Stimulations in Paleozoic Formations, Saudi Arabia

2021 ◽  
Author(s):  
Maaruf Hussain ◽  
Abduljamiu Amao ◽  
Khalid Al-Ramadan ◽  
Sunday Olatunji ◽  
Ardiansyah Negara
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Saudi Arabia ◽  
Spatial Distribution ◽  
Chemical Composition ◽  
Rock Strength ◽  
Machine Learning Algorithms ◽  
Unconventional Reservoirs ◽  
Geochemical Properties ◽  
Rock Mechanical Properties

Abstract The knowledge of rock mechanical properties is critical to reducing drilling risk and maximizing well and reservoir productivity. Rock chemical composition, their spatial distribution, and porosity significantly influenced these properties. However, low porosity characterized unconventional reservoirs as such, geochemical properties considerably control their mechanical behavior. In this study, we used chemostratigraphy as a correlation tool to separate strata in highly homogenous formations where other traditional stratigraphic methods failed. In addition, we integrated the chemofacies output and reduced Young's modulus to outline predictable associations between facies and mechanical properties. Thus, providing better understanding of lithofacies-controlled changes in rock strength that are useful inputs for geomechanical models and completions stimulations.

scholarly journals Predicting the Mechanical Properties of RCA-Based Concrete Using Supervised Machine Learning Algorithms

Materials ◽  
2022 ◽  
Vol 15 (2) ◽  
pp. 647
Author(s):  
Meijun Shang ◽  
Hejun Li ◽  
Ayaz Ahmad ◽  
Waqas Ahmad ◽  
Krzysztof Adam Ostrowski ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Mean Square Error ◽  
Coarse Aggregate ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Environmental Damage ◽  
Fine Aggregate ◽  
Mean Square ◽  
The Impact

Environment-friendly concrete is gaining popularity these days because it consumes less energy and causes less damage to the environment. Rapid increases in the population and demand for construction throughout the world lead to a significant deterioration or reduction in natural resources. Meanwhile, construction waste continues to grow at a high rate as older buildings are destroyed and demolished. As a result, the use of recycled materials may contribute to improving the quality of life and preventing environmental damage. Additionally, the application of recycled coarse aggregate (RCA) in concrete is essential for minimizing environmental issues. The compressive strength (CS) and splitting tensile strength (STS) of concrete containing RCA are predicted in this article using decision tree (DT) and AdaBoost machine learning (ML) techniques. A total of 344 data points with nine input variables (water, cement, fine aggregate, natural coarse aggregate, RCA, superplasticizers, water absorption of RCA and maximum size of RCA, density of RCA) were used to run the models. The data was validated using k-fold cross-validation and the coefficient correlation coefficient (R2), mean square error (MSE), mean absolute error (MAE), and root mean square error values (RMSE). However, the model’s performance was assessed using statistical checks. Additionally, sensitivity analysis was used to determine the impact of each variable on the forecasting of mechanical properties.

scholarly journals Predicting the Tensile Behaviour of Cast Alloys by a Pattern Recognition Analysis on Experimental Data

Metals ◽  
2019 ◽  
Vol 9 (5) ◽  
pp. 557 ◽  
Author(s):  
Cristiano Fragassa ◽  
Matej Babic ◽  
Carlos Perez Bergmann ◽  
Giangiacomo Minak
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Mechanical Properties ◽  
Pattern Recognition ◽  
Cast Iron ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Tensile Behaviour ◽  
Cast Alloys ◽  
Pattern Recognition Analysis

The ability to accurately predict the mechanical properties of metals is essential for their correct use in the design of structures and components. This is even more important in the presence of materials, such as metal cast alloys, whose properties can vary significantly in relation to their constituent elements, microstructures, process parameters or treatments. This study shows how a machine learning approach, based on pattern recognition analysis on experimental data, is able to offer acceptable precision predictions with respect to the main mechanical properties of metals, as in the case of ductile cast iron and compact graphite cast iron. The metallographic properties, such as graphite, ferrite and perlite content, extrapolated through macro indicators from micrographs by image analysis, are used as inputs for the machine learning algorithms, while the mechanical properties, such as yield strength, ultimate strength, ultimate strain and Young’s modulus, are derived as output. In particular, 3 different machine learning algorithms are trained starting from a dataset of 20–30 data for each material and the results offer high accuracy, often better than other predictive techniques. Concerns regarding the applicability of these predictive techniques in material design and product/process quality control are also discussed.

scholarly journals Machine Learning Algorithms for Biological Targets: Investigating the Error Tolerance in Various Computational Methods

2019 ◽  
Author(s):  
Thomas M. Kaiser ◽  
Pieter B. Burger
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Naive Bayes ◽  
Probabilistic Neural Network ◽  
Naïve Bayes ◽  
Machine Learning Algorithms ◽  
Learning Models ◽  
Bayes Network ◽  
Insight Into ◽  
Machine Learning Models

Machine learning continues to make strident advances in the prediction of desired properties concerning drug development. Problematically, the efficacy of machine learning in these arenas is reliant upon highly accurate and abundant data. These two limitations, high accuracy and abundance, are often taken together; however, insight into the dataset accuracy limitation of contemporary machine learning algorithms may yield insight into whether non-bench experimental sources of data may be used to generate useful machine learning models where there is a paucity of experimental data. We took highly accurate data across six kinase types, one GPCR, one polymerase, a human protease, and HIV protease, and intentionally introduced error at varying population proportions in the datasets for each target. With the generated error in the data, we explored how the retrospective accuracy of a Naïve Bayes Network, a Random Forest Model, and a Probabilistic Neural Network model decayed as a function of error. Additionally, we explored the ability of a training dataset with an error profile resembling that produced by the Free Energy Perturbation method (FEP+) to generate machine learning models with useful retrospective capabilities. The categorical error tolerance was quite high for a Naïve Bayes Network algorithm averaging 39% error in the training set required to lose predictivity on the test set. Additionally, a Random Forest tolerated a significant degree of categorical error introduced into the training set with an average error of 29% required to lose predictivity. However, we found the Probabilistic Neural Network algorithm did not tolerate as much categorical error requiring an average of 20% error to lose predictivity. Finally, we found that a Naïve Bayes Network and a Random Forest could both use datasets with an error profile resembling that of FEP+. This work demonstrates that computational methods of known error distribution like FEP+ may be useful in generating machine learning models not based on extensive and expensive in vitro-generated datasets.

Discovering News Frames

2020 ◽  
pp. 702-721
Author(s):  
Loretta H. Cheeks ◽  
Tracy L. Stepien ◽  
Dara M. Wald ◽  
Ashraf Gaffar
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Online News ◽  
Machine Learning Algorithms ◽  
News Frames ◽  
Water Insecurity ◽  
News Content ◽  
Making Sense ◽  
Mathematical Techniques ◽  
Definition Of

The Internet is a major source of online news content. Current efforts to evaluate online news content including text, storyline, and sources is limited by the use of small-scale manual techniques that are time consuming and dependent on human judgments. This article explores the use of machine learning algorithms and mathematical techniques for Internet-scale data mining and semantic discovery of news content that will enable researchers to mine, analyze, and visualize large-scale datasets. This research has the potential to inform the integration and application of data mining to address real-world socio-environmental issues, including water insecurity in the Southwestern United States. This paper establishes a formal definition of framing and proposes an approach for the discovery of distinct patterns that characterize prominent frames. The authors' experimental evaluation shows the proposed process is an effective approach for advancing semi-supervised machine learning and may assist in advancing tools for making sense of unstructured text.

Sign in / Sign up

Export Citation Format

Share Document