Magnetic microstructure machine learning analysis

Exl, Lukas; Fischbacher, Johann; Kovacs, Alexander; Oezelt, Harald; Gusenbauer, Markus; Yokota, Kazuya; Shoji, Tetsuya; Hrkac, G.; Schrefl, T.

doi:10.1088/2515-7639/aaf26d

Cited by 31 publications

(32 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A step towards automatization of the training process could be accomplished by tuning parameters of the underlying method e.g. by cross-validation like the authors did in the models for machine learning analysis for microstructures, see [11] and references therein. However, we emphasize that such hyper-parameter tuning, such as for γ in the RBF and the scaling factors for the field magnitude and in-plane angle are not within the scope of this presentation and part of future investigation.…”

Section: Discussionmentioning

confidence: 99%

Learning time-stepping by nonlinear dimensionality reduction to predict magnetization dynamics

Exl

Mauser

Schrefl

et al. 2020

Communications in Nonlinear Science and Numerical Simulation

Self Cite

View full text Add to dashboard Cite

We establish a time-stepping learning algorithm and apply it to predict the solution of the partial differential equation of motion in micromagnetism as a dynamical system depending on the external field as parameter. The data-driven approach is based on nonlinear model order reduction by use of kernel methods for unsupervised learning, yielding a predictor for the magnetization dynamics without any need for field evaluations after a data generation and training phase as precomputation. Magnetization states from simulated micromagnetic dynamics associated with different external fields are used as training data to learn a low-dimensional representation in so-called feature space and a map that predicts the time-evolution in reduced space. Remarkably, only two degrees of freedom in feature space were enough to describe the nonlinear dynamics of a thin-film element. The approach has no restrictions on the spatial discretization and might be useful for fast determination of the response to an external field.

show abstract

Section: Discussionmentioning

confidence: 99%

Learning time-stepping by nonlinear dimensionality reduction to predict magnetization dynamics

Exl

Mauser

Schrefl

et al. 2020

Communications in Nonlinear Science and Numerical Simulation

Self Cite

View full text Add to dashboard Cite

show abstract

“…With linear regression the data are assumed to correspond linearly, yet in real case scenarios, which are usually much more complex, labels depend nonlinearly on the features. Similar to Exl et al 18 , we use random forest (RF) and gradient boosting (GB) decision trees to account for the nonlinearity, which we observed in our results. RF trees combine predictions of individual decision trees trained over randomly generated sub-training samples (often called as ensemble learning).…”

Section: Machine Learningmentioning

confidence: 94%

“…Predicting the coercive field directly from a microstructural image would speed up the computation tremendously. A promising approach to reduce the computational costs is the use of machine learning to predict the coercivity of permanent magnets 18 . Even if it is only a rough approximation, one can gain qualitative information of the influence of local microstructural properties on the coercivity.…”

Section: Introductionmentioning

confidence: 99%

Extracting local nucleation fields in permanent magnets using machine learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

Microstructural features play an important role in the quality of permanent magnets. The coercivity is greatly influenced by crystallographic defects, like twin boundaries, as is well known for MnAl-C. It would be very useful to be able to predict the macroscopic coercivity from microstructure imaging. Although this is not possible now, in the present work we examine a related question, namely the prediction of simulated nucleation fields of a quasi-three-dimensional (rescaled and extruded) system constructed from a two-dimensional image. We extract features of the image and analyze them via machine learning. A large number of extruded systems are constructed from 10 × 10 pixel sub-images of an Electron Backscatter Diffraction (EBSD) image using an automated meshing procedure. A local nucleation field is calculated by micromagnetic simulation of each quasi-three-dimensional system. Decision trees, trained with the simulation results, can predict nucleation fields of these quasi-three-dimensional systems from new images within seconds. As for now we cannot quantitatively predict the macroscopic coercivity, nevertheless we can identify weak spots in the magnet and see trends in the nucleation field distribution.

show abstract

“…However, in aforementioned papers DL CNNs were used only as a component and final analyses were still conducted using FEA. Furthermore, applying DL to assist another analysis tool possibly hinders the utilization of full potential of DL [17]- [19]. In this study, DL CNNs are used for end-to-end accurate prediction of the output of Interior Permanent Magnet Synchronous Motors (IPMSMs).…”

Section: Introductionmentioning

confidence: 99%

Towards End-to-end Deep Learning Analysis of Electrical Machines

Gabdullin¹,

Madanzadeh²,

Vilkin³

2020

Preprint

View full text Add to dashboard Cite

<p>Convolutional Neural Networks (CNNs) and Deep Learning (DL) revolutionized numerous research fields including robotics, natural language processing, self-driving cars, healthcare, and others. However, DL is still relatively under-researched in fields such as physics and engineering. Recent works on DL-assisted analysis showed emerging interest and enormous potential of CNN applications. This paper explores the possibility of developing an end-to-end DL pipeline for the analysis of electrical machines. The CNNs are trained on conventional finite element method (FEA) data to predict the output torque curves of electric machines. FEA is only used for dataset collections and CNN training, whereas the analysis is done solely using CNNs. The required depth in CNN architecture is studied by comparing a simplistic CNN with three ResNet architectures. The effects of dataset balancing and data normalization are studied and torque clipping inspired by offset normalization is proposed to ease CNN training and improve the prediction accuracy. The relation between architecture depth and accuracy is identified showing that deeper CNNs improve the curve shape prediction accuracy even after torque magnitude prediction accuracy saturates. Over 90% accuracy for analysis conducted under a minute is reported for CNNs, whereas FEA of comparable accuracy required 200 hours. Predicting multidimensional outputs can improve CNN performance, which is essential for multiparameter optimization of electrical machines. </p>

show abstract

Magnetic microstructure machine learning analysis

Cited by 31 publications

References 41 publications

Learning time-stepping by nonlinear dimensionality reduction to predict magnetization dynamics

Learning time-stepping by nonlinear dimensionality reduction to predict magnetization dynamics

Extracting local nucleation fields in permanent magnets using machine learning

Towards End-to-end Deep Learning Analysis of Electrical Machines

Contact Info

Product

Resources

About