Computational and Data-Driven Chemistry Using Artificial Intelligence Fundamentals Methods and Applications by Unknown

Author:Unknown
Language: eng
Format: epub
Published: 2022-01-19T10:12:20+00:00

Chapter 5: Application of machine learning algorithms for use in material chemistry

Christian Schmitz a , ⁎ ; Kevin Cremanns b , ⁎ ; Golnaz Bissadi c a University of Applied Sciences Niederrhein, Institute for Surface and Coatings Chemistry, Krefeld, Germany

b University of Applied Sciences Niederrhein, Institute of Modelling and High-Performance Computing, Krefeld, Germany

c University of Applied Sciences Niederrhein, Institute for Surface Technology, Krefeld, Germany

⁎ Authors equally share the first authorship.

Abstract

Chemical engineering in materials science covers tasks like the synthesis of materials, formulation of raw materials to semifinished products, and the final application of these materials. Research and development in these fields requires knowledge of the property-structure relationship of the chemical compounds and physical parameters of the material properties and processes involved. Typical products that need to be formulated are polymeric materials such as plastics, composites, coatings, adhesives, etc. These materials have to fulfill a big number of features regarding the field of application. The material properties can be related to the chemistry of the raw materials and balanced by the ratio between the ingredients. The task for the chemist in materials science is the detection of these relationships and the optimization of the mixtures with the manufacturing process and properties of the final product. The aim is to develop new materials while their processes mostly rely on empirical experience in dealing with the complex chemistry of all ingredients (resins, polymers, solvents, additives, and inorganic and organic particles). Interactions between those ingredients make the development complicated and sometimes small adjustments can have a huge impact on the characteristics of a product. Material development can also be carried out with machine learning algorithms for modeling data and digital optimization of product properties. The combination of machine learning and high-throughput formulation leads to a unit, which operates a fully automated optimization cycle without interference of the human operator.

Keywords

Modeling; Machine learning; High-throughput formulation; Polymers; Material development

Contents

Introduction

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.