Machine Learning in the development of Si-based anodes using Small-Angle X-ray Scattering for structural property analysis
Source abstract
Abstract
Material development processes are highly iterative and driven by the experience and intuition of the researcher. This can lead to time consuming procedures. Data-driven approaches such as Machine Learning can support decision processes with trained and validated models to predict certain output parameter. In a multifaceted process chain of material synthesis of electrochemical materials and their characterization, Machine Learning has a huge potential to shorten development processes. Based on this, the contribution presents a novel approach to utilize data derived from Small-Angle X-ray Scattering (SAXS) of SiO2 matrix materials for battery anodes with Neural Networks. Here, we use SAXS as an intermediate, high-throughput method to characterize sol–gel based porous materials. A multi-step-method is presented where a Feed Forward Net is connected to a pretrained autoencoder to reliably map parameters of the material synthesis to the SAXS curve of the resulting material. In addition, a direct comparison shows that the prediction error of Neural Networks can be greatly reduced by training each output variable with a separate independent Neural Network.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Electron and X-Ray Spectroscopy Techniques · X-ray Diffraction in Crystallography
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Advances in the development of sol-gel materials combining small-angle X-Ray scattering (SAXS) and machine learning (ML)10.3390/pr9040672 ↗
2. Advances in machine learning detecting changeover processes in cyber physical production systems
3. Machine learning for continuous innovation in battery technologies10.1038/s41578-020-0216-y ↗
4. Secretary · 2020
5. Coherent expanded aerogels10.5254/1.3539386 ↗
6. Advances in sol-gel derived materials and technologies
7. Compression of aerogels10.1016/0022-3093(95)00074-7 ↗
8. Highly porous silica xerogels without surface modification10.1016/j.supflu.2015.08.016 ↗
9. The impact of residual adsorbate on the characterization of microporous carbons with small angle scattering10.1016/j.carbon.2012.02.093 ↗
10. Reliable surface area determination of powders and meso/macroporous materials: Small-angle X-ray scattering and gas physisorption
11. A predictive failure framework for brittle porous materials via machine learning and geometric matching methods10.1007/s10853-019-04339-1 ↗
12. Machine learning in materials informatics: recent applications and prospects10.1038/s41524-017-0056-5 ↗
13. Perspectives on the impact of machine learning, deep learning, and artificial intelligence on materials, processes, and structures engineering10.1007/s40192-018-0117-8 ↗
14. Recent advances and applications of machine learning in solid-state materials science10.1038/s41524-019-0221-0 ↗
15. Cockburn · 2019
16. Data-driven studies of li-ion-battery materials10.3390/cryst9010054 ↗
17. Data-driven materials exploration for li-ion conductive ceramics by exhaustive and informatics-aided computations10.1002/tcr.201800129 ↗
18. Application of machine learning methods for the prediction of crystal system of cathode materials in lithium-ion batteries10.1016/j.commatsci.2016.02.021 ↗
19. Machine learning-assisted discovery of solid Li-ion conducting materials10.1021/acs.chemmater.8b03272 ↗
20. Materials discovery and design using machine learning10.1016/j.jmat.2017.08.002 ↗
21. Machine learning approaches for designing mesoscale structure of li-ion battery electrodes10.3390/batteries5030054 ↗
22. Machine-learning-revealed statistics of the particle-carbon/binder detachment in lithium-ion battery cathodes
23. Toward data-driven applications in lithium-ion battery cell manufacturing10.1002/ente.201900136 ↗
24. Data-driven nonparametric Li-ion battery ageing model aiming at learning from real operation data-Part B: Cycling operation
25. Gaussian process regression for in situ capacity estimation of lithium-ion batteries10.1109/TII.2018.2794997 ↗
26. Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning
27. State-of-charge estimation of Li-ion batteries using deep neural networks: A machine learning approach10.1016/j.jpowsour.2018.06.104 ↗
28. Toward enhanced state of charge estimation of lithium-ion batteries using optimized machine learning techniques10.1038/s41598-020-61464-7 ↗
29. State-of-health identification of lithium-ion batteries based on nonlinear frequency response analysis: First steps with machine learning10.3390/app8050821 ↗
30. Accuracy enhancement in mobile phone recycling process using machine learning technique and MEPH process10.1016/j.eti.2020.101137 ↗
31. Machine learning deciphers structural features of RNA duplexes measured with solution X-ray scattering10.1107/S2052252520008830 ↗
32. Machine learning methods for X-ray scattering data analysis from biomacromolecular solutions10.1016/j.bpj.2018.04.018 ↗
33. Machine learning-assisted analysis of small angle X-ray scattering
34. A SAXS outlook on disordered carbonaceous materials for electrochemical energy storage10.1016/j.ensm.2019.05.007 ↗
35. In situ SAXS studies of the structural changes of polymer nanocomposites used in battery applications10.1021/cm020670z ↗
36. Operando SAXS/WAXS on the AP/C as the anode for Na-Ion batteries10.1021/acs.jpcc.7b12825 ↗
37. Prelithiation of silicon/graphite composite anodes: Benefits and mechanisms for long-lasting Li-Ion batteries10.1016/j.ensm.2020.04.008 ↗
38. Accelerating neural network training using weight extrapolations10.1016/S0893-6080(99)00072-6 ↗
39. Low-rank matrix factorization for deep neural network training with high-dimensional output targets
40. Using evolutionary artificial neural networks in monitoring binary and polytomous logistic profiles10.1016/j.jmsy.2021.10.007 ↗
41. Selection of proper neural network sizes and architectures—A comparative study10.1109/TII.2012.2187914 ↗
42. Computing gradient vector and Jacobian matrix in arbitrarily connected neural networks10.1109/TIE.2008.2003319 ↗
43. The universal approximation property10.1007/s10472-020-09723-1 ↗
44. Approximation capabilities of multilayer feedforward networks10.1016/0893-6080(91)90009-T ↗
45. Combining a neural network with a genetic algorithm for process parameter optimization10.1016/S0952-1976(00)00021-X ↗