The four institutions: Showa Denko (SDK), the National Institute of Advanced Industrial Science and Technology (AIST), the New Energy and Industrial Technologies Development Organization (NEDO), and the High Performance Design and Development Research Association for Materials Advanced Functionals (ADMAT): claim that by using AI, they managed to reduce the number of experiments required to produce flexible transparent films that satisfy specific properties to twenty-five (1/25) or less than required when using conventional development methods .
Development of flexible and transparent film.
The researchers’ focus has been to conduct AI-based searches for polymers that exhibit the properties required to design flexible films for mobile devices. The first step of the teams’ research was to produce 27 types of films, then the researchers incorporated chemical information into them, including molecular structures and molar relationships in explanatory variables using a special method: Extended Connectivity Circular Fingerprints (ECFP4) and They chose three objective variables (converted transmissivity, break stress, and stretch) out of the relationships. The researchers then had the AI learn the actual values of these variables and produced three types of film based on their recommendations.
A graphical representation of the flexible transparent film developed by researchers, intended to be used in the development of mobile devices. Image used courtesy of SDK / AIST, NEDO / ADMAT
A superior film by using AI
The three types of film recommended by the AI were found to outperform all types of film initially made by the researchers, and the three AI films exhibited superior physical properties than theirs. Therefore, the researchers claim, they showed that it is It is possible to substantially shorten the development period of flexible transparent films through the use of AI and that it is possible to develop films that exhibit properties superior to films made by highly skilled and experienced researchers. The researchers hope to refine their technology and develop a system in which AI can suggest ratios of different materials to produce predefined target products with improved properties above what human designers could achieve.