Theory-guided and supervised machine learning of shrinkage and creep properties for cement-based materials

With this collaborative project with Master Builders Solutions Deutschland GmbH, we are aiming at setting the bases for complementing poromechanics theory with machine learning models to address the general goal of predicting shrinkage and creep properties of cement-based materials

Among the basics, we focus on building up an infrastructure for creep and shrinkage data curation (the Shrinkage and Creep Data Curation System, SCDCS in short). For such purpose, we have adopted approaches/concepts/tools developed within the framework of the Materials Genome Initiative (MGI) of the USA Govt.
 

Among all the software tools used, the most important one is the open source Materials Data Curation System (MDCS), developed and maintained by the USA National Institute of Standards and Technology (NIST). The SCDCS is an example of domain application of the MDCS.

Project Period

October 2018 – September 2021

DataMining.png
Home page of the Shrinkage and Creep Data Curation System (https://mdcs.empa.ch), a knowledge base of shrinkage and creep properties of cement-based materials built by using NIST's Materials Data Curation System.
Project Team

Project leader

Members   
Beat Münch, Nikolajs Toropovs, Zhangli Hu, Mateusz Wyrzykowski, Patrik Burkhalter, Fabian Bucher, Janis Justs, Pietro Lura

 


Partners

Kai Steffen Weldert, Vadzim Yermakou, Steffen Wache Construction Chemicals Research
Master Builders Solutions Deutschland GmbH

Kevin Brady, Benjamin Long
Information Systems Group
Information Technology Laboratory
National Institute of Standards and Technology (NIST)
USA Dept. of Commerce

 

Funding Organization

Master Builders Solutions Deutschland GmbH


  • Print
    •  
    •  
    •  
    •