Use of Machine Learning Algorithms to Predict Almen (Shot Peening) Intensity Values of Various Steel Materials
Source abstract
Abstract
Wear, fatigue, and corrosion are just a few of the issues that mechanical components in engineering experience, leading to surface deterioration. Enhancing the surface characteristics of engineering components is therefore essential. The surface properties of engineering objects can be improved by applying different surface treatments. One of these processes is shot peening (SP). Process parameters are crucial for SP. This necessitates the optimization of SP process parameters. In this study, we applied SP and vibratory shot peening (VSP) processes to different steel materials (AISI 8620, AISI 5140, AISI 4140, and AISI 1020) using different process parameters, aiming to determine the effects of these parameters on hardness, residual stress, and surface roughness. The highest compressive residual stress (CRS) and hardness values for shot-peened samples were obtained at the 24–26 A intensity for all steels. For all steel-group VSP samples, the highest CRS and hardness values were obtained at the 60 s −4 mm parameter. This paper aims to predict Almen intensity values using CRS, surface roughness, and hardness values from various steels. The supplied experimental data was utilized to estimate the SP Almen intensity value using a number of machine learning (ML) methods, eliminating the need for costly and time-consuming experimentation. With an RMSE of 0.0731, R2 of 0.9665, and MAE of 0.0613, the deep neural network (DNN) surpassed the other models in terms of prediction accuracy. The results indicate that artificial intelligence technology could be utilized to accurately evaluate Almen intensity.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Surface Treatment and Residual Stress · Advanced machining processes and optimization · Erosion and Abrasive Machining
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Technologies, Technical Sciences Vocational School, Isparta University of Applied Sciences, 32260 Isparta, Turkey
Department of Mechanical and Metal Technology, Technical Sciences Vocational School, Isparta University of Applied Sciences, 32260 Isparta, Turkey
References (55)
Show source-provided references
1. Effects of Shot Peening Pre-Treatment and Plasma Nitriding Parameters on the Structural, Mechanical and Tribological Properties of AISI 4140 Low-Alloy Steel10.1016/j.surfcoat.2018.11.043 ↗
2. Influence of Prior Cold Rolling on Bainite Transformation of High Carbon Bearing Steel10.1007/s11661-024-07669-1 ↗
3. Obtaining Superior Low-Temperature Wear Resistance in Q&P-Processed Medium Mn Steel with a Low Initial Hardness10.1016/j.triboint.2022.107803 ↗
4. Improvement of fatigue properties by SP for Mg–10Gd–3Y alloys under different conditions10.1016/j.msea.2011.04.004 ↗
5. Optimization of the fatigue strength of materials due to SP: A survey
6. Effect of severe SP on microstructure and fatigue strength of cast iron10.1016/j.ijfatigue.2013.08.022 ↗
7. Effects of conventional and Severe SP on Residual Stress and fatigue Strength of Steel AISI 1060 and Residual Stress Relaxation Due to Fatigue Loading: Experimental and Numerical Simulation10.1007/s12540-020-00890-8 ↗
8. Optimization of SP effective parameters on surface hardness improvement10.1007/s12540-020-00758-x ↗
9. SP optimization with complex decision-making tool: Multi criteria decision-making10.1016/j.measurement.2018.04.077 ↗
10. Fatigue limit prediction and analysis of nanostructured AISI 304 steel by severe SP via ANN10.1007/s00366-020-00964-6 ↗
11. Influences of SP parameters on mechanical properties and fatigue behaviour of 316 L Steel: Experimental, Taguchi Method and Response Surface Methodology10.1007/s12540-021-01013-7 ↗
12. An analytical approach to relate SP parameters to Almen intensity10.1016/j.surfcoat.2010.08.105 ↗
13. Effect of initial surface treatment on SP residual stress field: Analytical approach with experimental verification10.1016/j.ijmecsci.2018.01.022 ↗
14. Gallitelli, D., Badreddine, J., Rouhaud, E., Micoulaut, M., Labergere, C., and Francois, M. (2012, January 7–9). From process parameters to residual stress field: Complete ultrasonic SP simulation. Proceedings of the 9th International Conference on Residual Stresses ICRS-9, Garmisch-Partenkirchen, Germany.
15. Simulation of SP: From process parameters to residual stress fields in a structure10.1016/j.crme.2016.02.006 ↗
16. Zarka, J. (1976). Non-Destructive Testing Method for Determining a Body’s Mechanical Properties and Stresses. (3,969,928), U.S. Patent.
17. Inglebert, G. (1984). Analyse Simplifiée des Structures Élasto-Visco-Plastiques sous Chargements Cycliques. [Ph.D. Thesis, Arts and Crafts ParisTech].
18. Relating Almen intensity to residual stresses induced by SP: A numerical approach10.1016/S0924-0136(00)00893-1 ↗
19. A numerical study of the residual stress pattern from single shot impacting on a metallic component10.1016/j.advengsoft.2007.10.002 ↗
20. Constrained probabilistic multi-objective optimization of SP process10.1080/0305215X.2010.508523 ↗
21. Smart vibratory peening: An approach towards digitalisation and integration of vibratory special process into smart factories10.1016/j.engappai.2023.107118 ↗
22. Maleki, E., Unal, O., Sahebari, S.M., and Kashyzadeh, K.R. (2023). A Novel Approach for Analyzing the Effects of Almen Intensity on the Residual Stress and Hardness of Shot-Peened (TiB + TiC)/Ti–6Al–4V Composite: Deep Learning. Materials, 16.10.3390/ma16134693 ↗
23. Optimization of shot peening parameters for blades based on the constraint of equivalent residual stress-induced deformation10.1007/s00170-024-13238-y ↗
24. Correlation of residual stress, hardness and surface roughness with crack initiation and fatigue strength of surface treated additive manufactured AlSi10Mg: Experimental and machine learning approaches10.1016/j.jmrt.2023.03.193 ↗
25. (2024, June 15). Material Properties. Available online: https://web.archive.org/save/https://www.efunda.com/home.cfm.
26. Wear Resistance, Hardness, and Residual Stress of Shot-Peened and Heat-Treated 8620 Nickel-Chromium-Molybdenum Steel
27. Daş, T. (2019). Titreşim Destekli Yüzey Aşırı Plastik Deformasyon Cihazı Tasarımı ve İmalatı. [Master’s Thesis, Karabük University].
28. Fatigue behaviour prediction and analysis of shot peened mild carbon steels10.1016/j.ijfatigue.2018.06.004 ↗
29. Fitzpatrick, M.E., Fry, A.T., Holdway, P., Kandil, F.A., Shackleton, J., and Suominen, L. (2024, September 09). Determination of Residual Stresses by X-Ray Diffraction—Issue 2; Measurement Good Practice Guide No. 52. Available online: http://eprintspublications.npl.co.uk/id/eprint/2391.
30. Methods for interpreting and understanding deep neural networks10.1016/j.dsp.2017.10.011 ↗
31. Efficient processing of deep neural networks: A tutorial and survey10.1109/JPROC.2017.2761740 ↗
32. Advances towards automatic detection and classification of parasites microscopic images using deep convolutional neural network: Methods, models and research directions10.1007/s11831-022-09858-w ↗
33. Kozma, R., Choe, Y., Alippi, C., and Morabito, F.C. (2019). Evolving deep neural networks. Artificial Intelligence in the Age of Neural Networks and Brain Computing, Academic Press.
34. Harmonizing Physical and Deep Learning Modeling: A Computationally Efficient and Interpretable Approach for Property Prediction10.1016/j.scriptamat.2024.116350 ↗
35. Artificial neural networks: A tutorial10.1109/2.485891 ↗
36. Backpropagation neural networks: A tutorial10.1016/0169-7439(93)80052-J ↗
37. Gupta, A., Bansal, A., and Roy, K. (2021, January 6–8). Solar energy prediction using decision tree regressor. Proceedings of the 5th IEEE International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India.
38. Mozer, M.C., Jordan, M.I., and Petsche, T. (1996). Support vector regression machines. Advances in Neural Information Processing Systems, MIT Press.
39. Awad, M., and Khanna, R. (2015). Support vector regression. Efficient Learning Machines, Apress.10.1007/978-1-4302-5990-9 ↗
40. Variable importance assessment in regression: Linear regression versus random forest
41. Standard errors and confidence intervals for variable importance in random forest regression, classification, and survival10.1002/sim.7803 ↗
42. Prettenhofer, P., and Louppe, G. (2014). Gradient Boosted Regression Trees in Scikit-Learn, PyData.
43. Leen, T.K., Dietterich, T.G., and Tresp, V. (2001). A gradient-based boosting algorithm for regression problems. Advances in Neural Information Processing Systems, MIT Press.10.7551/mitpress/1120.001.0001 ↗
44. Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., and Zhou, T. (2015). XGBoost: Extreme Gradient Boosting, R Package Version, XGBoost.10.32614/CRAN.package.xgboost ↗
45. Application of eXtreme gradient boosting trees in the construction of credit risk assessment models for financial institutions10.1016/j.asoc.2018.09.029 ↗
46. Motion estimation from surface electromyogram using adaboost regression and average feature values10.1109/ACCESS.2019.2892780 ↗
47. Solomatine, D.P., and Shrestha, D.L. (2004, January 25–29). AdaBoost.RT: A boosting algorithm for regression problems. Proceedings of the IEEE International Joint Conference on Neural Networks, Budapest, Hungary.
48. Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature10.5194/gmd-7-1247-2014 ↗
49. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance10.3354/cr030079 ↗
50. An R-squared measure of goodness of fit for some common nonlinear regression models10.1016/S0304-4076(96)01818-0 ↗
51. Liu, L., and Özsu, M.T. (2009). Cross-Validation. Encyclopedia of Database Systems, Springer.10.1007/978-0-387-39940-9 ↗
52. Evaluating explorative prediction power of machine learning algorithms for materials discovery using k-fold forward cross-validation10.1016/j.commatsci.2019.109203 ↗
53. High-dimensional microarray dataset classification using an improved adam optimizer (iAdam)10.1007/s12652-020-01832-3 ↗
54. GridSearchCV (2024, July 05). Sklearn Model Selection. Available online: https://web.archive.org/web/20240000000000.
55. Sample Criteria for Testing Outlying Observations10.1214/aoms/1177729885 ↗