Ahmet Cecen

Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters

This paper describes the use of data analytics tools for predicting the fatigue strength of steels. Several physics-based as well as data-driven approaches have been used to arrive at correlations between various properties of alloys and their compositions and manufacturing process parameters. Data-driven approaches are of significant interest to materials engineers especially in arriving at extreme value properties such as cyclic fatigue, where the current state-of-the-art physics based models have severe limitations. Unfortunately, there is limited amount of documented success in these efforts. In this paper, we explore the application of different data science techniques, including feature selection and predictive modeling, to the fatigue properties of steels, utilizing the data from the National Institute for Material Science (NIMS) public domain database, and present a systematic end-to-end framework for exploring materials informatics. Results demonstrate that several advanced data analytics techniques such as neural networks, decision trees, and multivariate polynomial regression can achieve significant improvement in the prediction accuracy over previous efforts, with R2 values over 0.97. The results have successfully demonstrated the utility of such data mining tools for ranking the composition and process parameters in the order of their potential for predicting fatigue strength of steels, and actually develop predictive models for the same.

Versatile algorithms for the computation of 2-point spatial correlations in quantifying material structure

This paper presents a generalized framework along with the associated computational strategies for a rigorous quantification of the material structure in a range of different applications using the framework of 2-point spatial correlations. In particular, we focus on applications requiring different assumptions about the periodicity and/or involving irregular domain shapes and potentially extremely large datasets. Important details of the computational algorithms needed to address these challenges are developed and illustrated with example case studies. Algorithms developed and presented in this work are available at http://dx.doi.org/https://doi.org/10.5281/zenodo.31329.

Process-Structure Linkages Using a Data Science Approach: Application to Simulated Additive Manufacturing Data

A novel data science workflow is developed and demonstrated to extract process-structure linkages (i.e., reduced-order model) for microstructure evolution problems when the final microstructure depends on (simulation or experimental) processing parameters. This workflow consists of four main steps: data pre-processing, microstructure quantification, dimensionality reduction, and extraction/validation of process-structure linkages. Methods that can be employed within each step vary based on the type and amount of available data. In this paper, this data-driven workflow is applied to a set of synthetic additive manufacturing microstructures obtained using the Potts-kinetic Monte Carlo (kMC) approach. Additive manufacturing techniques inherently produce complex microstructures that can vary significantly with processing conditions. Using the developed workflow, a low-dimensional data-driven model was established to correlate process parameters with the predicted final microstructure. Additionally, the modular workflows developed and presented in this work facilitate easy dissemination and curation by the broader community.

Application of Statistical and Machine Learning Techniques for Correlating Properties to Composition and Manufacturing Processes of Steels

Establishing correlations between various properties of alloys and their compositions and manufacturing process parameters is of significant interest to materials engineers. Both physics-based as well as data-driven approaches have been used in pursuit of this. Of various properties of interest, fatigue strength, being an extreme value property, had only a limited amount of success with physics based models. In this paper, we explore a systematic data driven approach, supplemented by physics based understanding, employing various regression methods with dimensionality reduction and machine learning methods applied to the fatigue properties of steels available from the National Institute of Material Science public domain database to arrive at correlations for fatigue strength of steels and present an assessment of the residual errors in each method for comparison. This study is expected to provide insights into the methods studied to make objective selection of appropriate method.

Microstructure Analysis Tools for Quantification of Key Structural Properties of Fuel Cell Materials

The objective of this work is to develop advanced microstructure analysis tools for direct quantification of the key structural properties of complex fuel cell materials. Computationally efficient algorithms have been developed to extract the key structural parameters from measured microstructure datasets of these materials. In addition to determination of the traditional structural measures (e.g., porosity, surface area, phase connectivity), two novel microstructure analysis techniques are introduced for the quantification of pore size and tortuosity distributions. For initial demonstration purposes, the methods developed are applied to a digitally reconstructed sample of the micro-porous layer (MPL) of a polymer electrolyte fuel cell (PEFC). The results produced from these analyses are compared to previously reported experimental and model-derived values where applicable.

Multiscale Model for Non-Metallic Inclusions/Steel Composite System Using Data Science Enabled Structure-Property Linkages

Cleanliness is a major concern for steel manufacturers. Therefore, they constantly strive to modify and reduce non-metallic inclusions in the final product. Performance and quality of final steel sheet is strongly influenced by composition, morphology, type, size and distribution of inclusions in steel sheet. The aim of current work is to critically evaluate the versatility of a new data science enabled approach for establishing objective, high fidelity, structure-property correlations that are needed to facilitate optimal design of the processing path to realize enhanced performance of the final product.