Development カジノ シークレット jcb a versatile, accurate AI prediction technique even with a small number カジノ シークレット jcb experiments
-NIMS with Asahi Kasei, Mitsubishi Chemical, Mitsui Chemical, and Sumitomo Chemical Advance DX in カジノ シークレット jcb Development-

Oct. 25, 2021

Abstract

NIMS, Asahi Kasei, Mitsubishi Chemical, Mitsui Chemicals and Sumitomo Chemical have used the chemical materials open platform framework to develop an AI technique capable カジノ シークレット jcb increasing the accuracy カジノ シークレット jcb machine learning-based predictions カジノ シークレット jcb material properties (e.g., strength, brittleness) through efficient use カジノ シークレット jcb material structural data obtained from only a small number カジノ シークレット jcb experiments. This technique may expedite the development カジノ シークレット jcb various materials, including polymers.

Materials informatics research exploits machine learning models to predict the physical properties カジノ シークレット jcb materials カジノ シークレット jcb interest based on compositional and processing parameters (e.g., temperature and pressure). This approach has accelerated materials development. When physical properties カジノ シークレット jcb materials are known to be strongly influenced by their post-processing microstructures, the model’s property prediction accuracy can be effectively improved by incorporating microstructure-related data (e.g., x-ray diffraction (XRD) and differential scanning calorimetry (DSC) data) into it. However, these types カジノ シークレット jcb data can only be obtained by actually analyzing processed materials. In addition to these analyses, improving prediction accuracy requires predetermined parameters (e.g., material compositions).

This research group developed an AI technique capable カジノ シークレット jcb first selecting potentially promising material candidates for fabrication and then accurately predicting their physical properties using XRD, DSC and other measurement data obtained from only a small number カジノ シークレット jcb actually synthesized materials. This technique selects candidate materials using Bayesian optimization and other methods and repeats the AI-based selection process while incorporating measurement data into machine learning models. To verify the technique’s effectiveness, the group used it to predict the physical properties カジノ シークレット jcb polyolefins. As a result, this technique was found to improve the material property prediction accuracy カジノ シークレット jcb machine learning models with a smaller sample set カジノ シークレット jcb actually synthesized materials than methods in which candidate materials were randomly selected.

The use カジノ シークレット jcb this prediction accuracy improvement technique may enable a more thorough understanding カジノ シークレット jcb the relationship between materials’ structures and physical properties, which would facilitate investigation カジノ シークレット jcb fundamental causes カジノ シークレット jcb material properties and the formulation カジノ シークレット jcb more efficient materials development guidelines. Furthermore, this technique is expected to be applicable to the development カジノ シークレット jcb a wide range カジノ シークレット jcb materials in addition to polyolefins and other polymers, thereby promoting digital transformation (DX) in materials development.

This project was carried out by Ryo Tamura (Senior Researcher, NIMS), Takashi Nakanishi (Group Leader, NIMS), Masahiko Demura (Direcカジノ シークレット jcbr, NIMS), Yuki Takei (Chief Researcher, Asahi Kasei Corporation), Shinichiro Imai (Principal Scientist, Mitsubishi Chemical Corporation), Maki Nakahara (Researcher, Mitsui Chemicals, Inc.) and Saカジノ シークレット jcbshi Shibata (Researcher, Sumiカジノ シークレット jcbmo Chemical Co., Ltd.).

This research was published in the online version カジノ シークレット jcb Science and Technology カジノ シークレット jcb Advanced Materials: Methods on September 28, 2021, Japan Time.

Contacts

For general inquiries