journal article·2022-11Open access

Creep lifetime prediction of 9% Cr martensitic heat-resistant steel based on ensemble learning method

Yumeng Tan, Xiaowei Wang, Zitong Kang, Fei Ye, Yefeng Chen, Dewen Zhou, Xiancheng Zhang, Jianming Gong

Abstract

Creep lifetime prediction is critical for the design of high-temperature components. Due to creep lifetime being affected by many factors, its prediction with high accuracy is still challenging. The 9% Cr martensitic heat-resistant steel is currently the world's most widely used creep-resistant steel in supercritical power plant equipment. In this work, variables like material chemical compositions, heat treatment conditions and creep test conditions are considered in various machine learning (ML) models to predict creep lifetime. First, series of typical individual regression algorithms are assessed, but the prediction results are imperfect. Second, severa l ensemble learning algorithms are optimized by bagging and boosting, and a noticeable improvement in predictive performance is observed, especially for the extreme gradient boosting algorithm. Finally, a model coupled with Larson-Miller (LM) parameter is proposed based on stacking, which gives the best prediction results. R-square (R2), mean absolute error (MAE), and mean square error (MSE) of the proposed model is 0.918, 0.516, and 0.450, respectively.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: High Temperature Alloys and Creep · Microstructure and Mechanical Properties of Steels · Metallurgy and Material Forming

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (63)

Show source-provided references
1. Creep Rupture:From physical failure mechanisms to lifetime prediction of structures10.3901/JME.2021.16.132 ↗
2. Wang · 2021
3. Catalog of NIMS creep data sheets10.1080/14686996.2019.1697616 ↗
4. Error estimates in extrapolation of creep rupture data: applied to an austenitic stainless steel
5. An empirical relationship between rupture life and minimum creep rate in creep rupture tests
6. A time-temperature relationship for rupture and creep stresses
7. Wilshire · 1982 · vol. 353
8. Metallographic methods of determining residual creep life10.1016/0025-5416(80)90178-0 ↗
9. Microstructure evolution and life assessment of T92 steel during long-term creep10.1016/j.jallcom.2013.11.080 ↗
10. Creep crack growth simulations in 316H stainless steel10.1016/j.engfracmech.2008.08.001 ↗
11. Computer simulation of the high temperature creep behaviour of Cr–Mo steels10.1016/j.msea.2011.04.050 ↗
12. Numerical simulation and creep-life prediction of X20 steam piping10.1016/j.matpr.2020.05.125 ↗
13. The ‘effective-stress-function’algorithm for thermo-elasto-plasticity and creep10.1002/nme.1620240808 ↗
14. Use of CDM in materials modeling and component creep life prediction10.1115/1.556185 ↗
15. Editorial —big data, data science, and analytics: the opportunity and challenge for IS research10.1287/isre.2014.0546 ↗
16. An artificial neural network model to characterize porosity defects during solidification of A356 aluminum alloy10.1007/s00521-013-1532-6 ↗
17. Modern data analytics approach to predict creep of high-temperature alloys10.1016/j.actamat.2019.02.017 ↗
18. Predicting creep rupture life of Ni-based single crystal superalloys using divide-and-conquer approach based machine learning10.1016/j.actamat.2020.05.001 ↗
19. A deep learning based life prediction method for components under creep, fatigue and creep-fatigue conditions10.1016/j.ijfatigue.2021.106236 ↗
20. Uncertainty quantification for Bayesian active learning in rupture life prediction of ferritic steels10.1038/s41598-022-06051-8 ↗
21. Ensemble learning for remaining fatigue life prediction of structures with stochastic parameters: a data-driven approach10.1016/j.apm.2021.08.033 ↗
22. An ensemble-learning model for failure rate prediction10.1016/j.promfg.2020.02.022 ↗
23. A novel decomposition-ensemble learning framework for multi-step ahead wind energy forecasting
24. A stacking-based ensemble learning method for earthquake casualty prediction10.1016/j.asoc.2020.107038 ↗
25. Strength of stacking technique of ensemble learning in rockburst prediction with imbalanced data: comparison of eight single and ensemble models10.1007/s11053-020-09787-0 ↗
26. Machine learning predictions of superalloy microstructure10.1016/j.commatsci.2021.110916 ↗
27. Lattice misfit predictions via the Gaussian process regression for Ni-based single crystal superalloys10.1007/s12540-020-00883-7 ↗
28. The learning of the precipitates morphological parameters from the composition of nickel-based superalloys
29. sheet · 2019
30. Steel Grade 91
31. Kimura · 2012
32. Effect of V and Nb on precipitation behavior and mechanical properties of high Cr steel10.1016/j.nucengdes.2006.09.013 ↗
33. Effect of carbon concentration on precipitation behavior of M23C6 carbides and MX carbonitrides in martensitic 9Cr steel during heat treatment10.1007/s11661-004-0299-x ↗
34. Influences of Mo substitution by W on the precipitation kinetics of secondary phases and the associated localized corrosion and embrittlement in 29% Cr ferritic stainless steels10.1016/j.msea.2005.11.053 ↗
35. A physically-based constitutive model for high temperature microstructural degradation under cyclic deformation10.1016/j.ijfatigue.2017.03.018 ↗
36. Effect of normalizing and tempering temperatures on microstructure and mechanical properties of P92 steel10.1016/j.ijpvp.2015.07.001 ↗
37. 2019 · 1
38. 2022 · 1
39. Rebala G, Ravi A, Churiwala S. Machine learning definition and basics, An Introduction to Machine Learning, Springer2019, pp. 1-17.10.1007/978-3-030-15729-6_1 ↗
40. Improving your data transformations: applying the Box-Cox transformation
41. Semi-random partitioning of data into training and test sets in granular computing context10.1007/s41066-017-0049-2 ↗
42. Kernel density estimation and its application
43. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation10.7717/peerj-cs.623 ↗
44. Liashchynskyi · 2019
45. An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization10.1023/A:1007607513941 ↗
46. Ferreira · 2012
47. The strength of weak learnability10.1023/A:1022648800760 ↗
48. Xgboost: a scalable tree boosting system
49. Stacked generalization10.1016/S0893-6080(05)80023-1 ↗
50. Mathematical model and its validation of P92 material endurance strength based on larson miller parameters10.1016/j.msea.2015.04.050 ↗
51. Mathematical model for creep-rupture strength based on Larson-Miller parameter
52. Boundary defects, and atomistic aspects of boundary sliding and diffusional creep10.1016/0039-6028(72)90273-7 ↗
53. A novel scalable intrusion detection system based on deep learning10.1007/s10207-020-00508-5 ↗
54. The global k-means clustering algorithm10.1016/S0031-3203(02)00060-2 ↗
55. Advances in neural networks and potential for their application to steel metallurgy10.1080/02670836.2020.1839206 ↗
56. Decision jungles: compact and rich models for classification
57. A model for boundary diffusion controlled creep in polycrystalline materials10.1063/1.1702656 ↗
58. Diffusional viscosity of a polycrystalline solid10.1063/1.1699681 ↗
59. A dislocation mechansim of transient creep10.1016/0001-6160(63)90116-0 ↗
60. Influence of data scattering on estimation of 100,000 hrs creep rupture strength of alloy 617 at 700 C by Larson–Miller method10.1115/1.4033290 ↗
61. Microstructural damage mechanics-based model for creep fracture of 9% Cr steel under prior fatigue loading10.1016/j.tafmec.2019.102269 ↗
62. Development of new nano-particle-strengthened martensitic steels10.1016/j.scriptamat.2005.04.019 ↗
63. Weld metal microstructure analysis of 9–12% Cr steels10.1016/j.ijpvp.2006.03.005 ↗