ndustry guided harnessing of materials big-data using machine learning

Reference number 2018-04297
Coordinator Linköpings universitet - Institutionen för ekonomisk och industriell utveckling
Funding from Vinnova SEK 500 000
Project duration November 2018 - November 2019
Status Ongoing
Venture Banbrytande idéer inom industriell utveckling
Call Banbrytande idéer inom industriell utveckling - 2018

Purpose and goal

Artificial intelligence-based methods will be utilized to accelerate the search of multifunctional coatings. We will develop and train a machine-learning algorithm that connects materials composition, structures etc. with properties obtained from open databases combined with information about materials behavior at industrial conditions. Two world-leading Swedish companies in the field of hard coatings will provide control knowledge for uncovering potentials of nitride, carbide and oxide materials and promising materials combinations for high-entropy alloys.

Expected results and effects

We will develop a machine learning approach for materials exploration and developments for the hard coating industry. The software will be adapted to industrial platforms. We deliver a partition of potential materials in categories for different hard coating applications. The multifunctionalities (piezoelectric, pyroelectric etc. properties) of the materials will be explored by our collaboration with FunMat-II competence center. The project will serve renewal for both, industry and academic research.

Planned approach and implementation

The project is comprised by three work packages: i) Data collection, ii) Knowledge extraction by machine learning and iii) validation. All the collected and newly generated new data will be classified according to industrial control descriptions provided by two world-leading Swedish companies. We capitalize on our broad competence ranging from computational materials science to industrial R&D expertise.

The project description has been provided by the project members themselves and the text has not been examined by our editors.