circuitnet
Sponsor
Nordson-ASYMTEK

A Lifespan of Reliability
Nordson Electronics Solutions makes reliable electronics an everyday reality. Selective soldering, dispensing, coating, and plasma solutions.
Nordson Electronics Solutions
ECD
Sponsor
Master-Bond

Epoxy Offers Ultra High Heat Transfer
Bond EP5TC-80 is a NASA low outgassing rated epoxy that achieves a thermal conductivity of 3.3-3.7 W/(m·K), while also retaining its electrical non-conductivity.
Master Bond

Development of Materials Informatics Platform



Development of Materials Informatics Platform
Materials Informatics is one of the hottest technologies because of its potential to reduce the time and costs of discovering innovative materials.
Technical Paper

DOWNLOAD

Authored By:


Yasumitsu Orii, Ph.D., Shuichi Hirose, Ph.D., Hiroki Toda, Masakazu Kobayashi
New Value Creation Office, Nagase & Co., LTD
Japan

As the use of IT increases importance with big data and AI, the issue of power consumption has been highlighted. Under these circumstances, the development of new materials is more and more important. Materials Informatics (MI) is one of the hottest technologies in the material development field, because of its potential to reduce the time and costs of discovering innovative materials. To achieve this, the key is to collect data that has been accumulated for many years at research institutions and companies, and to make information extracted from the data into knowledge. This article introduces the development of two methods based on AI: the “cognitive approach”, which reads vast amounts of literature information and digitizes data, and the “analytic approach”, which theoretically estimates the structure and physical properties of chemical substances from predictive models.

Summary


As the use of IT increases importance with big data and AI, the issue of power consumption has been highlighted. Under these circumstances, the development of new materials is more and more important. Materials Informatics (MI) is one of the hottest technologies in the material development field, because of its potential to reduce the time and costs of discovering innovative materials. To achieve this, the key is to collect data that has been accumulated for many years at research institutions and companies, and to make information extracted from the data into knowledge.

This article introduces the development of two methods based on AI: the “cognitive approach”, which reads vast amounts of literature information and digitizes data, and the “analytic approach”, which theoretically estimates the structure and physical properties of chemical substances from predictive models.

Conclusions


In this article, the use case of AI and the future demand of Materials Informatics are described. With the evolution of IoT, the advancement of 5G, and the growth of energy consumption due to the enormous amount of data processing on servers, the increasing needs for new material development and intensifying competition in material development are inevitable. MI technology will be an indispensable technology for improving the speed of development in the search and design of such new materials, not only organic materials but also inorganic materials. And also, MI will certainly be the source of future corporate competitiveness. MI can search for target materials directly from the database which is based on conventional method depending on the intuition and experience of researchers. And it also enables efficient or direct way to develop materials to meet the needs of users.

There are many advantages of MI, however we should do more for improving the systems for commonly using. For example, further improvement of data analysis technology, accumulation of data, and establishment of support system for MI introduction to users, is needed. The training of data scientists who can analyze data is also urgent. The future direction of MI evolution is the accumulation of unstructured data collected from sensing devices, combined with clustering processing by AI, and new material simulation using quantum computers as accelerators. The field of quantum chemical calculation is also expected to be actively developed with MI field, as a more effective way to find out materials properties compare to conventional calculation methods.

Initially Published in the SMTA Proceedings

Comments

No comments have been submitted to date.

Submit A Comment


Comments are reviewed prior to posting. You must include your full name to have your comments posted. We will not post your email address.

Your Name


Your Company
Your E-mail


Your Country
Your Comments



Free Newsletter Subscription
Circuitnet is built for professionals who bear the responsibility of looking ahead, imagining the future, and preparing for it.

Insert Your Email Address

Sponsor
Viscom-SE

iX7059 Series by Viscom: Inline X-ray Inspection Power
High-performance Inline X-ray Inspection Systems for complex electronics, semiconductors, and power modules up to 200 kg. Seamless integration, AI-powered accuracy, and maximum reliability for every application.
Viscom SE