skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Predictive analysis of the influence of the chemical composition and pre-processing regimen on structural properties of steel alloys using machine learning techniques

Authors:
; ;  [1];  [1]
  1. Foreign National
Publication Date:
Research Org.:
National Energy Technology Lab. (NETL), Pittsburgh, PA, and Morgantown, WV (United States). In-house Research
Sponsoring Org.:
USDOE Office of Fossil Energy (FE)
OSTI Identifier:
1413205
Report Number(s):
NETL-PUB-20885
Resource Type:
Conference
Resource Relation:
Conference: APS March Meeting 2017, New Orleans, LA, March 13-17, 2017.
Country of Publication:
United States
Language:
English
Subject:
20 FOSSIL-FUELED POWER PLANTS; 36 MATERIALS SCIENCE; 42 ENGINEERING; 97 MATHEMATICS AND COMPUTING; Machine Learning, steel alloys, mechanical properties

Citation Formats

Romanov, Vyacheslav, Hawk, Jeffrey A., Krishnamurthy, Narayanan, and Maddali, Siddharth. Predictive analysis of the influence of the chemical composition and pre-processing regimen on structural properties of steel alloys using machine learning techniques. United States: N. p., 2017. Web.
Romanov, Vyacheslav, Hawk, Jeffrey A., Krishnamurthy, Narayanan, & Maddali, Siddharth. Predictive analysis of the influence of the chemical composition and pre-processing regimen on structural properties of steel alloys using machine learning techniques. United States.
Romanov, Vyacheslav, Hawk, Jeffrey A., Krishnamurthy, Narayanan, and Maddali, Siddharth. Sun . "Predictive analysis of the influence of the chemical composition and pre-processing regimen on structural properties of steel alloys using machine learning techniques". United States. doi:. https://www.osti.gov/servlets/purl/1413205.
@article{osti_1413205,
title = {Predictive analysis of the influence of the chemical composition and pre-processing regimen on structural properties of steel alloys using machine learning techniques},
author = {Romanov, Vyacheslav and Hawk, Jeffrey A. and Krishnamurthy, Narayanan and Maddali, Siddharth},
abstractNote = {},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sun Mar 12 00:00:00 EST 2017},
month = {Sun Mar 12 00:00:00 EST 2017}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • A serious problem in mining industrial data bases is that they are often incomplete, and a significant amount of data is missing, or erroneously entered. This paper explores the use of machine-learning based alternatives to standard statistical data completion (data imputation) methods, for dealing with missing data. We have approached the data completion problem using two well-known machine learning techniques. The first is an unsupervised clustering strategy which uses a Bayesian approach to cluster the data into classes. The classes so obtained are then used to predict multiple choices for the attribute of interest. The second technique involves modeling missingmore » variables by supervised induction of a decision tree-based classifier. This predicts the most likely value for the attribute of interest. Empirical tests using extracts from industrial databases maintained by Honeywell customers have been done in order to compare the two techniques. These tests show both approaches are useful and have advantages and disadvantages. We argue that the choice between unsupervised and supervised classification techniques should be influenced by the motivation for solving the missing data problem, and discuss potential applications for the procedures we are developing.« less
  • Comparing the output of a physics simulation with an experiment is often done by visually comparing the two outputs. In order to determine which simulation is a closer match to the experiment, more quantitative measures are needed. This paper describes our early experiences with this problem by considering the slightly simpler problem of finding objects in a image that are similar to a given query object. Focusing on a dataset from a fluid mixing problem, we report on our experiments using classification techniques from machine learning to retrieve the objects of interest in the simulation data. The early results reportedmore » in this paper suggest that machine learning techniques can retrieve more objects that are similar to the query than distance-based similarity methods.« less
  • Most researchers with little high performance computing (HPC) experience have difficulties productively using the supercomputing resources. To address this issue, we investigated usage behaviors of the world s fastest academic Kraken supercomputer, and built a knowledge-based recommendation system to improve user productivity. Six clustering techniques, along with three cluster validation measures, were implemented to investigate the underlying patterns of usage behaviors. Besides manually defining a category for very large job submissions, six behavior categories were identified, which cleanly separated the data intensive jobs and computational intensive jobs. Then, job statistics of each behavior category were used to develop a knowledge-basedmore » recommendation system that can provide users with instructions about choosing appropriate software packages, setting job parameter values, and estimating job queuing time and runtime. Experiments were conducted to evaluate the performance of the proposed recommendation system, which included 127 job submissions by users from different research fields. Great feedback indicated the usefulness of the provided information. The average runtime estimation accuracy of 64.2%, with 28.9% job termination rate, was achieved in the experiments, which almost doubled the average accuracy in the Kraken dataset.« less
  • Only a limited number of structural studies have been performed on polyurethanes using scanning probe techniques to determine both the microstructure and the corresponding distribution of hard and soft segments within samples. This type of information is needed to better understand the mechanical properties of these materials and to facilitate modeling. In order to address these issues, we have fabricated a series of compression molded segmented poly(ester urethane) samples with hard (HS) to soft segment ratios from 19 to 100%. Samples were examined using scanning probe phase imaging techniques to obtain the topography and corresponding distribution of hard domains beforemore » and after heating at 100 C. A number of significant differences were observed between the pre- and post-heat treated samples. Variations in structure and heat-induced morphological changes were directly related to HS content. Fine strand- or fibril-like structures were most prominent in the 23 and 19% HS sample but first appeared at 30% HS. Harder, thicker elongated structures dominated the surface of the 100% HS sample and were seen to a limited extent on all samples, especially after annealing and quenching. The 23% HS sample surface structure depended on quenching rate and time after treatment.« less