Study employs image-recognition AI to determine battery composition and conditions
What does the AI technology developed by the research team do?
The AI technology developed by the research team uses image recognition to determine the elemental composition and number of charge and discharge cycles of a battery by analyzing its surface morphology. This method, based on convolutional neural networks, can predict the major elemental composition and charge-discharge state of cathode materials with 99.6% accuracy.
How accurate is the AI in predicting battery composition?
The AI developed by the international collaborative research team, led by Professor Seungbum Hong from the Korea Advanced Institute of Science and Technology (KAIST), can predict the major elemental composition and charge-discharge state of NCM cathode materials with 99.6% accuracy using convolutional neural networks (CNN).
Which universities and institutes collaborated on this research?
The research was a collaboration between the Korea Advanced Institute of Science and Technology (KAIST), the Electronics and Telecommunications Research Institute (ETRI), and Drexel University in the United States.