3 results
Now showing1 - 3 of 3
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Training deep neural networks to reconstruct nanoporous structures from FIB tomography images using synthetic training data(Frontiers Media S.A., 2022-02-28); ; ; ; Focused ion beam (FIB) tomography is a destructive technique used to collect three-dimensional (3D) structural information at a resolution of a few nanometers. For FIB tomography, a material sample is degraded by layer-wise milling. After each layer, the current surface is imaged by a scanning electron microscope (SEM), providing a consecutive series of cross-sections of the three-dimensional material sample. Especially for nanoporous materials, the reconstruction of the 3D microstructure of the material, from the information collected during FIB tomography, is impaired by the so-called shine-through effect. This effect prevents a unique mapping between voxel intensity values and material phase (e.g., solid or void). It often substantially reduces the accuracy of conventional methods for image segmentation. Here we demonstrate how machine learning can be used to tackle this problem. A bottleneck in doing so is the availability of sufficient training data. To overcome this problem, we present a novel approach to generate synthetic training data in the form of FIB-SEM images generated by Monte Carlo simulations. Based on this approach, we compare the performance of different machine learning architectures for segmenting FIB tomography data of nanoporous materials. We demonstrate that two-dimensional (2D) convolutional neural network (CNN) architectures processing a group of adjacent slices as input data as well as 3D CNN perform best and can enhance the segmentation performance significantly.Publicationtype: Journal ArticleScopus© Citations 5 156 860 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , A review of the application of machine learning and data mining approaches in continuum materials mechanicsMachine learning tools represent key enablers for empowering material scientists and engineers to accelerate the development of novel materials, processes and techniques. One of the aims of using such approaches in the field of materials science is to achieve high-throughput identification and quantification of essential features along the process-structure-property-performance chain. In this contribution, machine learning and statistical learning approaches are reviewed in terms of their successful application to specific problems in the field of continuum materials mechanics. They are categorized with respect to their type of task designated to be either descriptive, predictive or prescriptive; thus to ultimately achieve identification, prediction or even optimization of essential characteristics. The respective choice of the most appropriate machine learning approach highly depends on the specific use-case, type of material, kind of data involved, spatial and temporal scales, formats, and desired knowledge gain as well as affordable computational costs. Different examples are reviewed involving case-by-case dependent application of different types of artificial neural networks and other data-driven approaches such as support vector machines, decision trees and random forests as well as Bayesian learning, and model order reduction procedures such as principal component analysis, among others. These techniques are applied to accelerate the identification of material parameters or salient features for materials characterization, to support rapid design and optimization of novel materials or manufacturing methods, to improve and correct complex measurement devices, or to better understand and predict fatigue behavior, among other examples. Besides experimentally obtained datasets, numerous studies draw required information from simulation-based data mining. Altogether, it is shown that experiment- and simulation-based data mining in combination with machine leaning tools provide exceptional opportunities to enable highly reliant identification of fundamental interrelations within materials for characterization and optimization in a scale-bridging manner. Potentials of further utilizing applied machine learning in materials science and empowering significant acceleration of knowledge output are pointed out.Publicationtype: Journal ArticleScopus© Citations 240 431 705 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , General multi-fidelity framework for training artificial neural networks with computational models(2019-04-17); ; Training of artificial neural networks (ANNs) relies on the availability of training data. If ANNs have to be trained to predict or control the behavior of complex physical systems, often not enough real-word training data are available, for example, because experiments or measurements are too expensive, time-consuming or dangerous. In this case, generating training data by way of realistic computational simulations is a viable and often the only promising alternative. Doing so can, however, be associated with a significant and often even prohibitive computational cost, which forms a serious bottleneck for the application of machine learning to complex physical systems. To overcome this problem, we propose in this paper a both systematic and general approach. It uses cheap low-fidelity computational models to start the training of the ANN and gradually switches to higher-fidelity training data as the training of the ANN progresses. We demonstrate the benefits of this strategy using examples from structural and materials mechanics. We demonstrate that in these examples the multi-fidelity strategy introduced herein can reduce the total computational cost–compared to simple brute-force training of ANNs–by a half up to one order of magnitude. This multi-fidelity strategy can thus be hoped to become a powerful and versatile tool for the future combination of computational simulations and artificial intelligence, in particular in areas such as structural and materials mechanics.Publicationtype: Journal ArticleScopus© Citations 25 471 421