An online tool for predicting fatigue strength of steel alloys based on ensemble data mining
Source abstract
Abstract
Abstract Fatigue strength is one of the most important mechanical properties of steel. Here we describe the development and deployment of data-driven ensemble predictive models for fatigue strength of a given steel alloy represented by its composition and processing information. The forward models for PSPP relationships (predicting property of a material given its composition and processing parameters) are built using over 400 experimental observations from the Japan National Institute of Materials Science (NIMS) steel fatigue dataset. Forty modeling techniques, including ensemble modeling were explored to identify the set of best performing models for different attribute sets. Data-driven feature selection techniques were also used to find a small non-redundant subset of attributes, and the processing/composition parameters most influential to fatigue strength were identified to inform future design efforts. The developed predictive models are deployed in a user-friendly online web-tool available at http://info.eecs.northwestern.edu/SteelFatigueStrengthPredictor .
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Non-Destructive Testing Techniques · Software Engineering Research · Fatigue and fracture mechanics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (55)
Show source-provided references
1. Agrawal A, Choudhary A. A fatigue strength predictor for steels using ensemble data mining. In: Proceedings of 25th ACM international conference on information and knowledge management (CIKM) (Demo); 2016. p. 2497–500.10.1145/2983323.2983343 ↗
2. Hey T, Tansley S, Tolle K. The fourth paradigm: data-intensive scientific discovery, microsoft research; 2009. .
3. Materials data science: current status and future outlook10.1146/annurev-matsci-070214-020844 ↗
4. Materials informatics: the materials gene and big data10.1146/annurev-matsci-070214-021132 ↗
5. Perspective: materials informatics and big data: Realization of the fourth paradigm of science in materials science
6. Finding natures missing ternary oxide compounds using machine learning and density functional theory10.1021/cm100795d ↗
7. Knowledge discovery and data mining in pavement inverse analysis10.3846/16484142.2013.777941 ↗
8. Deshpande · 2013
9. Combinatorial screening for new materials in unconstrained composition space with machine learning
10. On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets10.1038/srep06367 ↗
11. Machine learning approaches for elastic localization linkages in high-contrast composite materials
12. Materials prediction via classification learning10.1038/srep13285 ↗
13. A predictive machine learning approach for microstructure optimization and materials design
14. Crystal structure representations for machine learning models of formation energies10.1002/qua.24917 ↗
15. Liu R, Ward L, Wolverton C, Agrawal A, Liao W-K, Choudhary A. Deep learning for chemical compound stability prediction. In: Proceedings of ACM SIGKDD workshop on large-scale deep learning for data mining (DL-KDD); 2016. p. 1–7.
16. A general-purpose machine learning framework for predicting properties of inorganic materials10.1038/npjcompumats.2016.28 ↗
17. Liu R, Agrawal A, Liao W-K, Graef MD, Choudhary A. Materials discovery: understanding polycrystals from large-scale electron patterns. In: Proceedings of IEEE BigData workshop on advances in software and hardware for big data to knowledge discovery (ASH); 2016. p. 2261–9.10.1109/BigData.2016.7840857 ↗
18. Predictive analytics for crystalline materials: bulk modulus10.1039/C6RA19284J ↗
19. Agrawal A, Meredig B, Wolverton C, Choudhary A. A formation energy predictor for crystalline materials using ensemble data mining. In: Proceedings of IEEE international conference on data mining (ICDM) (Demo); 2016. p. 1276–9.10.1109/ICDMW.2016.0183 ↗
20. Including crystal structure attributes in machine learning models of formation energies via Voronoi tessellations10.1103/PhysRevB.96.024104 ↗
21. Context aware machine learning approaches for modeling elastic localization in three-dimensional composite microstructures
22. Improved scaling of molecular network calculations: the emergence of molecular domains10.1021/acs.jpclett.6b02921 ↗
23. Deep convolutional neural networks with transfer learning for computer vision-based data-driven pavement distress detection10.1016/j.conbuildmat.2017.09.110 ↗
24. Prediction of seebeck coefficient for compounds without restriction to fixed stoichiometry: a machine learning approach10.1002/jcc.25067 ↗
25. Crack damage detection in unmanned aerial vehicle images of civil infrastructure using pre-trained deep learning model10.7708/ijtte.2018.8(1).01 ↗
26. Data sampling schemes for microstructure design with vibrational tuning constraints10.2514/1.J056170 ↗
27. Materials Genome Initiative for Global Competitiveness, June 2011; OSTP 2011.
28. Materials Genome Initiative Strategic Plan, National Science and Technology Council Committee on Technology Subcommittee on the Materials Genome Initiative; June 2014.
29. Making materials science and engineering data more valuable research products10.1186/s40192-014-0022-8 ↗
30. Materials science and engineering data challenge. [accessed: March 31, 2016].
31. Dieter · 1986
32. National Institute of Materials Science. [accessed: March 31, 2016].
33. Gautham BP, Kumar R, Bothra S, Mohapatra G, Kulkarni N, Padmanabhan KA. More efficient ICME through materials informatics and process modeling. John Wiley & Sons, Inc.; 2011. p. 35–42.10.1002/9781118147726.ch5 ↗
34. Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters
35. Hall M. Correlation-based feature selection for machine learning [Ph.D. thesis]. Citeseer; 1999.
36. Weher E. Edwards, Allen, l.: an introduction to linear regression and correlation. (A series of books in psychology.) W.H. Freeman and Comp., San Francisco 1976. 213 S., Tafelanh., s 7.00. Biometrical J 1977;19(1):83–4.10.1002/bimj.4710190121 ↗
37. Aha DW, Kibler D. Instance-based learning algorithms. Mach Learn 1991;37–66.10.1007/BF00153759 ↗
38. Bishop · 1995
39. Fausett L. Fundamentals of neural networks. New York: Prentice Hall; 1994.
40. Ebden M. Gaussian processes for regression: a quick introduction; 2008. [accessed: March 30, 2016].
41. Vapnik · 2000
42. Shevade S, Keerthi S, Bhattacharyya C, Murthy K. Improvements to the SMO algorithm for SVM regression. In: IEEE transactions on neural networks; 1999.10.1109/72.870050 ↗
43. The power of decision tables
44. Witten · 2005
45. Wang Y, Witten I. Induction of model trees for predicting continuous classes. In: Proc European conference on machine learning poster papers, Prague, Czech Republic; 1997. p. 128–37.
46. Quinlan JR. Learning with continuous classes. World Scientific; 1992. p. 343–8.
47. Breiman L, Friedman J, Olshen R, Stone C. Classification and regression trees. Monterey, CA: Wadsworth and Brooks; 1984.
48. Random forests10.1023/A:1010933404324 ↗
49. Stochastic gradient boosting10.1016/S0167-9473(01)00065-2 ↗
50. Bagging predictors10.1023/A:1018054314350 ↗
51. The random subspace method for constructing decision forests10.1109/34.709601 ↗
52. Rotation forest: a new classifier ensemble method10.1109/TPAMI.2006.211 ↗
53. Jolliffe · 2002
54. On combining classifiers10.1109/34.667881 ↗
55. Hall M, Frank E, et al. The weka data mining software: an update, SIGKDD Explor 2009;11(1).10.1145/1656274.1656278 ↗