ICAMS / Interdisciplinary Centre for Advanced Materials Simulation

Data Mining and Statistical Analysis

Irina Roslyakova

The group works on the development of data-driven and physically-based modeling strategies and their application to analysis and interpretation of materials data.
At the moment, one of key research topics is the development of physically-based and data-driven models to identify statistically sound correlations between materials chemistry, thermodynamic, microstructure and mechanical data of single crystal Ni- and Co-based super alloys. In comparison to the existing purely phenomenological modeling methods, such hybrid modeling strategies allow to identify the influence of individual physical effects from the considered contribution on selected material properties. Moreover, they are frequently required to accelerate the computer-based design of new materials and alloys, for example, the development of rhenium-free Ni-based alloys with the desirable mechanical properties.

fig1

Normalized standardized regression coefficients of alloying elements and their variations in at% for property variation within a full linear regression model.

 

 


Group members in Mai 2019.

Due to the high complexity and heterogeneity of materials data, we focus mainly on three key goals:

  • the establishment of a well-organized data infrastructure for storage of experimental data and simulation results,
  • the development of robust physics-based models of materials properties and their application for thermodynamic and kinetic calculations and integration into computer-based alloy-by-design framework,
  • the development and application of data mining and machine learning methods to identify statistically sound correlations between materials chemistry, microstructure and mechanical data.

fig2_493x264

Third generation CALPHAD databases from 0K by automated statistical regression analysis.

Moreover, a combination of this modelling technique and the application of statistical design of experiments allow to reduce the number of experimental trials required for the development of new materials and processes.

Competences

  • Data mining and machine learning
  • Automation of data processing
  • Physics-based models
  • Third generation CALPHAD databases: mathematical aspects
  • Development of the pair-diffusion model and automation of atomic mobility assessments
  • Design of experiments

 

Group Members

 

Contact

Dr. Irina Roslyakova
Department of Scale Bridging Thermodynamic and Kinetic Simulation
ICAMS
Ruhr-Universität Bochum
44801 Bochum
Germany

Tel: +49 234 32 22605

Email: irina.roslyakova@rub.de

 

Recent publications

S. Zomorodpoosh, B. Bocklund, A. Obaied, R. Otis et al. Statistical approach for automated weighting of datasets: application to heat capacity data CALPHAD: Computer Coupling of Phase Diagrams and Thermochemistry, 71, 101994, (2020)

I. Roslyakova, A. Obaied, S. Zomorodpoosh. Application of machine learning methods to support the development of the 3d generation CALPHAD databases 17th Discussion Meeting on Thermodynamics of Alloys (TOFA), Bad Staffelstein, Germany, (2020)

A. Obaied, F. Tang, I. Roslyakova, M. to Baben. 2 1/2th generation CALPHAD databases: experopolating heat capacities of elements and compounds to 0K 17th Discussion Meeting on Thermodynamics of Alloys (TOFA), Bad Staffelstein, Germany, (2020)

I. Roslyakova, S. Zomorodpoosh, A. Obaied, I. Steinbach. Artificial materials intelligence to accelerate discovery of novel superalloys 17th Discussion Meeting on Thermodynamics of Alloys (TOFA), (2020)

A. Obaied, S. Zomorodpoosh, I. Roslyakova. 3G_TDB software for automated generati on of TDB files using modified segmented regression (MSR) model: pure Mn as an example 17th Discussion Meeting on Thermodynamics of Alloys (TOFA), Bad Staffelstein, Germany, (2020)

« back