journal article·2020-09

Integrated application of semantic segmentation-assisted deep learning to quantitative multi-phased microstructural analysis in composite materials: Case study of cathode composite materials of solid oxide fuel cells

Heesu Hwang, Sung Min Choi, Jiwon Oh, Seung-Muk Bae, Jong-Ho Lee, Jae-Pyeong Ahn, Jeong-O. Lee, Ki-Seok An, Young Yoon, Jin-Ha Hwang

Publisher page

Abstract

Abstract Automated semantic segmentation is applied to the quantification of microstructural features in three-phase composite cathode materials of solid oxide fuel cells (SOFCs), i.e., GDC/LSC/Pore where GDC stands for Gd2O3-doped CeO2 and LSC for La0.6Sr0.4CoO3-δ. Our aim is to eliminate the tedious involvement of human experts and the associated errors. The high volume of image information sets is generated using automatic acquisition systems involving focused-ion beam scanning electron microscopy through a so-called slice-view procedure. Through the integration of semantic segmentation with image processing-assisted stereography tools, the following detailed microstructural features are quantitatively extracted automatically and objectively without any human involvement: size distribution, surface (or equivalently, volume) fraction, lengths of two-phase boundaries, and density of triple-phase boundaries based on two-dimensional images. The extracted two-dimensional information is connected with three-dimensional reconstruction analysis. The implications of semantic segmentation in SOFCs are discussed considering efficient analysis and design of high-performance electrode structures in energy-oriented devices.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Advancements in Solid Oxide Fuel Cells · Nuclear Materials and Properties · Machine Learning in Materials Science

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (46)

Show source-provided references
1. Solid oxide fuel cells: fundamental aspects and prospects10.1016/S0013-4686(00)00330-3 ↗
2. Progress in material selection for solid oxide fuel cell technology: a review10.1016/j.pmatsci.2015.01.001 ↗
3. Solid oxide fuel cells10.1039/b105764m ↗
4. Advances in solid oxide fuel cell technology10.1016/S0167-2738(00)00452-5 ↗
5. Viable image analyzing method to characterize the microstructure and the properties of the Ni/YSZ cermet anode of SOFC10.1016/j.jpowsour.2004.06.031 ↗
6. Extraction of quantitative parameters for describing the microstructure of solid oxide fuel cells10.1017/S1431927613012518 ↗
7. Is 2D stereological method good enough for quantification of solid oxide fuel cell electrode microstructure?10.1007/s11434-016-1079-x ↗
8. Three-dimensional reconstruction of a solid-oxide fuel-cell anode10.1038/nmat1668 ↗
9. Quantification of SOFC anode microstructure based on dual beam FIB-SEM technique10.1016/j.jpowsour.2009.09.005 ↗
10. Evaluation of SOFC anode polarization simulation using three-dimensional microstructures reconstructed by FIB tomography10.1016/j.electacta.2011.02.010 ↗
11. Characterisation of Solid Oxide Fuel Cell Ni–8YSZ substrate by synchrotron X-ray nano-tomography: from 3D reconstruction to microstructure quantification10.1016/j.jpowsour.2011.09.105 ↗
12. Non-destructive reconstruction and analysis of SOFC anodes Using X-ray computed tomography at sub-50 nm resolution10.1149/1.2895067 ↗
13. Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition10.1109/TASL.2011.2134090 ↗
14. A unified architecture for natural language processing: deep neural networks with multitask learning
15. Deep learning for content-based image retrieval: a comprehensive study
16. Goodfellow · 2016 · vol. 2016 · 200
17. A fast learning algorithm for deep belief nets10.1162/neco.2006.18.7.1527 ↗
18. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
19. A discriminative CNN video representation for event detection
20. Region-based convolutional networks for accurate object detection and segmentation10.1109/TPAMI.2015.2437384 ↗
21. You only look once: unified, real-time object detection
22. Faster R-CNN: towards real-time object detection with region proposal networks
23. Neural network for nanoscience scanning electron microscope image recognition10.1038/s41598-017-13565-z ↗
24. Pattern recognition with machine earning on optical microscopy images of typical metallurgical microstructures10.1038/s41598-018-20438-6 ↗
25. High throughput quantitative metallography for complex microstructures using deep learning: a case study in ultrahigh carbon steel10.1017/S1431927618015635 ↗
26. Super-resolution for asymmetric resolution of FIB-SEM 3D imaging using AI with deep learning10.1038/s41598-018-24330-1 ↗
27. Deep learning of atomically resolved scanning transmission electron microscopy images: chemical identification and tracking local transformations10.1021/acsnano.7b07504 ↗
28. Synergistic approach to quantifying information on a crack-based network in loess/water material composites using deep learning and network science10.1016/j.commatsci.2019.04.014 ↗
29. Encoder-decoder with atrous separable convolution for semantic image segmentation
30. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
31. Deep residual learning for image recognition
32. Xception: deep learning with depthwise separable convolutions
33. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning10.1109/TMI.2016.2528162 ↗
34. Nickel coarsening in annealed Ni/8YSZ anode substrates for solid oxide fuel cell10.1016/S0167-2738(00)00650-0 ↗
35. Measurement of internal boundaries in three-dimensional structures by random sectioning
36. The measurement of grain contiguity in opaque samples
37. Grain growth kinetics in alumina–zirconia (CeZTA) composites10.1111/j.1151-2916.1994.tb07250.x ↗
38. Microstructure recognition using convolutional neural networks for prediction of ionic conductivity in ceramics10.1016/j.actamat.2017.09.004 ↗
39. Random forests10.1023/A:1010933404324 ↗
40. Bansal
41. Semantic image segmentation with deep convolutional nets and fully connected CRFs
42. Characterization of fine-scale microstructures by electron backscatter diffraction (EBSD)10.1016/j.scriptamat.2004.05.016 ↗
43. The use of environmental scanning electron microscopy for imaging wet and insulating materials10.1038/nmat898 ↗
44. Diffusion length evaluation of boron-implanted silicon using the SEM-EBIC/Schottky diode technique10.1088/0022-3727/12/8/014 ↗
45. A SEM-EBIC minority-carrier diffusion-length measurement technique10.1109/T-ED.1982.20721 ↗
46. Cathodoluminescence scanning electron microscopy of semiconductors10.1063/1.336491 ↗