Fujitsu Corporation and RIKEN recently announced that their joint research team applied first-principles calculation and artificial intelligence technology in material design to predict, synthesize and evaluate the solid electrolyte composition of all-solid-state lithium-ion batteries. Practical verification was carried out. The results proved that even with less data, by combining with artificial intelligence methods, the optimal material composition can be efficiently found, which can greatly improve the speed of material development.
So far, the development of materials has had to rely on the researchers' long-term accumulated experience and keen intuition, requiring many lessons from failures to be successful. First-principles calculations, on the other hand, are that if the composition of the material is specified, based on the predictable characteristics of quantum mechanics, the optimal composition of the new highly functional material can be predicted before the experiment, thereby greatly reducing the number of experimental failures. However, the load of the first-principle calculation is very huge, and the various compositions of materials require multiple calculations, which will take a very long time.
The research team hopes to solve the problems in material development through the close combination of material simulation, experiment and artificial intelligence, so that the material development time can be greatly shortened, in order to more easily discover unexpected compositions and crystalline structures, and create new high-functional materials.
The research team used a combination of Bayesian inference methods, one of the artificial intelligence methods, to control the number of operations of the first-principles calculations to predict the synthesis of three lithium-containing oxo-acid salt compounds in the solid electrolyte of all-solid-state lithium-ion batteries. The results confirm that the method can predict the best combination of high Li-ion conductivity in achievable time. At the same time, high lithium ion conductivity for other compositions was also found near the predicted composition.
Lithium ion conductivity is one of the important characteristics of solid electrolyte materials, and it is the factor that dominates the charging and discharging speed of lithium batteries. The results of this research have verified that the use of material simulation and artificial intelligence methods can efficiently develop lithium-ion batteries that do not leak and fire, and are expected to play a huge potential in the fields of batteries, semiconductors, and magnetic materials in the future.
(More Clicks: Independent Innovation ) (Link: http://www.chuangxin360.com )