Fujitsu Ltd. and the Japan Institute of Physical Chemistry recently announced that their joint research team applied first-principle calculations and artificial intelligence techniques in material design to make predictions, synthesis and evaluation tests for the solid electrolyte composition of all-solid-state lithium ion batteries, and The actual verification was carried out. The results show that even with less data, the combination of artificial intelligence methods can efficiently find the best material composition and greatly increase the material development speed.
To date, the development of materials has to rely on the long-term experience and keen intuition accumulated by researchers. Many lessons need to be accumulated to succeed. The first-principles calculation is to specify the composition of materials based on the predictable characteristics of quantum mechanics. It is possible to predict the optimal composition of new high-performance materials before the experiment, thereby greatly reducing the number of failed experiments. However, the load of the first-principles calculation is very large, and the various components of the materials require multiple calculations and will take a very long time.
The research team hopes to combine materials simulations, experiments and artificial intelligence to solve problems in material development, so that material development time will be greatly shortened, in order to more easily discover unexpected composition and crystal structure and create new high-functional materials.
The research team used Bayesian inference method, one of the artificial intelligence methods, to control the number of calculations for the first-principles calculations and predicted the three lithium-containing oxo-synthetic compounds of solid-state lithium-ion battery solid electrolytes. The results confirm that this method can predict the best combination of high lithium ion conductivities within achievable time. At the same time, high lithium ion conductivities of other compositions are also found near the predicted composition.
Lithium ion conductivity is one of the important characteristics of solid electrolyte materials, and is a factor that dominates the charge and discharge speed of lithium batteries. The results of this study have verified that the use of material simulation and artificial intelligence methods can efficiently develop a lithium-ion battery that does not leak liquid and does not catch fire. , In the future, it is expected to exert great potential in battery, semiconductor and magnetic materials.
