Machine Learning Driven Prediction of Residual Stresses for the Shot Peening Process Using a Finite Element Based Grey-Box Model Approach
The shot peening process is a common procedure to enhance fatigue strength on load-bearing components in the metal processing environment. The determination of optimal process parameters is often carried out by costly practical experiments. An efficient method to predict the resulting residual stres...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Journal of Manufacturing and Materials Processing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4494/5/2/39 |
| _version_ | 1797536903816282112 |
|---|---|
| author | Benjamin James Ralph Karin Hartl Marcel Sorger Andreas Schwarz-Gsaxner Martin Stockinger |
| author_facet | Benjamin James Ralph Karin Hartl Marcel Sorger Andreas Schwarz-Gsaxner Martin Stockinger |
| author_sort | Benjamin James Ralph |
| collection | DOAJ |
| description | The shot peening process is a common procedure to enhance fatigue strength on load-bearing components in the metal processing environment. The determination of optimal process parameters is often carried out by costly practical experiments. An efficient method to predict the resulting residual stress profile using different parameters is finite element analysis. However, it is not possible to include all influencing factors of the materials’ physical behavior and the process conditions in a reasonable simulation. Therefore, data-driven models in combination with experimental data tend to generate a significant advantage for the accuracy of the resulting process model. For this reason, this paper describes the development of a grey-box model, using a two-dimensional geometry finite element modeling approach. Based on this model, a Python framework was developed, which is capable of predicting residual stresses for common shot peening scenarios. This white-box-based model serves as an initial state for the machine learning technique introduced in this work. The resulting algorithm is able to add input data from practical residual stress experiments by adapting the initial model, resulting in a steady increase of accuracy. To demonstrate the practical usage, a corresponding Graphical User Interface capable of recommending shot peening parameters based on user-required residual stresses was developed. |
| first_indexed | 2024-03-10T12:07:28Z |
| format | Article |
| id | doaj.art-3fc49d06106f467cbafd018f7f6c0df8 |
| institution | Directory Open Access Journal |
| issn | 2504-4494 |
| language | English |
| last_indexed | 2024-03-10T12:07:28Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Manufacturing and Materials Processing |
| spelling | doaj.art-3fc49d06106f467cbafd018f7f6c0df82023-11-21T16:28:07ZengMDPI AGJournal of Manufacturing and Materials Processing2504-44942021-04-01523910.3390/jmmp5020039Machine Learning Driven Prediction of Residual Stresses for the Shot Peening Process Using a Finite Element Based Grey-Box Model ApproachBenjamin James Ralph0Karin Hartl1Marcel Sorger2Andreas Schwarz-Gsaxner3Martin Stockinger4Chair of Metal Forming, Montanuniversität Leoben, Franz Josef Str. 18, 8700 Leoben, AustriaChair of Metal Forming, Montanuniversität Leoben, Franz Josef Str. 18, 8700 Leoben, AustriaChair of Metal Forming, Montanuniversität Leoben, Franz Josef Str. 18, 8700 Leoben, AustriaChair of Metal Forming, Montanuniversität Leoben, Franz Josef Str. 18, 8700 Leoben, AustriaChair of Metal Forming, Montanuniversität Leoben, Franz Josef Str. 18, 8700 Leoben, AustriaThe shot peening process is a common procedure to enhance fatigue strength on load-bearing components in the metal processing environment. The determination of optimal process parameters is often carried out by costly practical experiments. An efficient method to predict the resulting residual stress profile using different parameters is finite element analysis. However, it is not possible to include all influencing factors of the materials’ physical behavior and the process conditions in a reasonable simulation. Therefore, data-driven models in combination with experimental data tend to generate a significant advantage for the accuracy of the resulting process model. For this reason, this paper describes the development of a grey-box model, using a two-dimensional geometry finite element modeling approach. Based on this model, a Python framework was developed, which is capable of predicting residual stresses for common shot peening scenarios. This white-box-based model serves as an initial state for the machine learning technique introduced in this work. The resulting algorithm is able to add input data from practical residual stress experiments by adapting the initial model, resulting in a steady increase of accuracy. To demonstrate the practical usage, a corresponding Graphical User Interface capable of recommending shot peening parameters based on user-required residual stresses was developed.https://www.mdpi.com/2504-4494/5/2/39python scriptingresidual stressesshot peeningfinite element analysisdigitalizationmachine learning |
| spellingShingle | Benjamin James Ralph Karin Hartl Marcel Sorger Andreas Schwarz-Gsaxner Martin Stockinger Machine Learning Driven Prediction of Residual Stresses for the Shot Peening Process Using a Finite Element Based Grey-Box Model Approach Journal of Manufacturing and Materials Processing python scripting residual stresses shot peening finite element analysis digitalization machine learning |
| title | Machine Learning Driven Prediction of Residual Stresses for the Shot Peening Process Using a Finite Element Based Grey-Box Model Approach |
| title_full | Machine Learning Driven Prediction of Residual Stresses for the Shot Peening Process Using a Finite Element Based Grey-Box Model Approach |
| title_fullStr | Machine Learning Driven Prediction of Residual Stresses for the Shot Peening Process Using a Finite Element Based Grey-Box Model Approach |
| title_full_unstemmed | Machine Learning Driven Prediction of Residual Stresses for the Shot Peening Process Using a Finite Element Based Grey-Box Model Approach |
| title_short | Machine Learning Driven Prediction of Residual Stresses for the Shot Peening Process Using a Finite Element Based Grey-Box Model Approach |
| title_sort | machine learning driven prediction of residual stresses for the shot peening process using a finite element based grey box model approach |
| topic | python scripting residual stresses shot peening finite element analysis digitalization machine learning |
| url | https://www.mdpi.com/2504-4494/5/2/39 |
| work_keys_str_mv | AT benjaminjamesralph machinelearningdrivenpredictionofresidualstressesfortheshotpeeningprocessusingafiniteelementbasedgreyboxmodelapproach AT karinhartl machinelearningdrivenpredictionofresidualstressesfortheshotpeeningprocessusingafiniteelementbasedgreyboxmodelapproach AT marcelsorger machinelearningdrivenpredictionofresidualstressesfortheshotpeeningprocessusingafiniteelementbasedgreyboxmodelapproach AT andreasschwarzgsaxner machinelearningdrivenpredictionofresidualstressesfortheshotpeeningprocessusingafiniteelementbasedgreyboxmodelapproach AT martinstockinger machinelearningdrivenpredictionofresidualstressesfortheshotpeeningprocessusingafiniteelementbasedgreyboxmodelapproach |