Artificial Neural Networks-Based Prediction of Hardness of Low-Alloy Steels Using Specific Jominy Distance
Successful prediction of the relevant mechanical properties of steels is of great importance to materials engineering. The aim of this research is to investigate the possibility of reducing the complexity of artificial neural networks-based prediction of total hardness of hypoeutectoid, low-alloy st...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/11/5/714 |
| _version_ | 1797536211612467200 |
|---|---|
| author | Sunčana Smokvina Hanza Tea Marohnić Dario Iljkić Robert Basan |
| author_facet | Sunčana Smokvina Hanza Tea Marohnić Dario Iljkić Robert Basan |
| author_sort | Sunčana Smokvina Hanza |
| collection | DOAJ |
| description | Successful prediction of the relevant mechanical properties of steels is of great importance to materials engineering. The aim of this research is to investigate the possibility of reducing the complexity of artificial neural networks-based prediction of total hardness of hypoeutectoid, low-alloy steels based on chemical composition, by introducing the specific Jominy distance as a new input variable. For prediction of total hardness after continuous cooling of steel (output variable), ANNs were developed for different combinations of inputs. Input variables for the first configuration of ANNs were the main alloying elements (C, Si, Mn, Cr, Mo, Ni), the austenitizing temperature, the austenitizing time, and the cooling time to 500 °C, while in the second configuration alloying elements were substituted by the specific Jominy distance. Comparing the results of total hardness prediction, it can be seen that the ANN using the specific Jominy distance as input variable (<i>r</i><sub>unseen</sub> = 0.873, <i>RMSE</i><sub>unseen</sub> = 67, <i>MAPE</i> = 14.8%) is almost as successful as ANN using main alloying elements (<i>r</i><sub>unseen</sub> = 0.940, <i>RMSE</i><sub>unseen</sub> = 46, <i>MAPE</i> = 10.7%). The research results indicate that the prediction of total hardness of steel can be successfully performed only based on four input variables: the austenitizing temperature, the austenitizing time, the cooling time to 500 °C, and the specific Jominy distance. |
| first_indexed | 2024-03-10T11:56:25Z |
| format | Article |
| id | doaj.art-e4a700c951f640318437a7c8caab908a |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-03-10T11:56:25Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-e4a700c951f640318437a7c8caab908a2023-11-21T17:19:00ZengMDPI AGMetals2075-47012021-04-0111571410.3390/met11050714Artificial Neural Networks-Based Prediction of Hardness of Low-Alloy Steels Using Specific Jominy DistanceSunčana Smokvina Hanza0Tea Marohnić1Dario Iljkić2Robert Basan3University of Rijeka, Faculty of Engineering, Vukovarska 58, 51000 Rijeka, CroatiaUniversity of Rijeka, Faculty of Engineering, Vukovarska 58, 51000 Rijeka, CroatiaUniversity of Rijeka, Faculty of Engineering, Vukovarska 58, 51000 Rijeka, CroatiaUniversity of Rijeka, Faculty of Engineering, Vukovarska 58, 51000 Rijeka, CroatiaSuccessful prediction of the relevant mechanical properties of steels is of great importance to materials engineering. The aim of this research is to investigate the possibility of reducing the complexity of artificial neural networks-based prediction of total hardness of hypoeutectoid, low-alloy steels based on chemical composition, by introducing the specific Jominy distance as a new input variable. For prediction of total hardness after continuous cooling of steel (output variable), ANNs were developed for different combinations of inputs. Input variables for the first configuration of ANNs were the main alloying elements (C, Si, Mn, Cr, Mo, Ni), the austenitizing temperature, the austenitizing time, and the cooling time to 500 °C, while in the second configuration alloying elements were substituted by the specific Jominy distance. Comparing the results of total hardness prediction, it can be seen that the ANN using the specific Jominy distance as input variable (<i>r</i><sub>unseen</sub> = 0.873, <i>RMSE</i><sub>unseen</sub> = 67, <i>MAPE</i> = 14.8%) is almost as successful as ANN using main alloying elements (<i>r</i><sub>unseen</sub> = 0.940, <i>RMSE</i><sub>unseen</sub> = 46, <i>MAPE</i> = 10.7%). The research results indicate that the prediction of total hardness of steel can be successfully performed only based on four input variables: the austenitizing temperature, the austenitizing time, the cooling time to 500 °C, and the specific Jominy distance.https://www.mdpi.com/2075-4701/11/5/714low-alloy steelsquenchingmechanical propertieshardnessartificial neural networks |
| spellingShingle | Sunčana Smokvina Hanza Tea Marohnić Dario Iljkić Robert Basan Artificial Neural Networks-Based Prediction of Hardness of Low-Alloy Steels Using Specific Jominy Distance Metals low-alloy steels quenching mechanical properties hardness artificial neural networks |
| title | Artificial Neural Networks-Based Prediction of Hardness of Low-Alloy Steels Using Specific Jominy Distance |
| title_full | Artificial Neural Networks-Based Prediction of Hardness of Low-Alloy Steels Using Specific Jominy Distance |
| title_fullStr | Artificial Neural Networks-Based Prediction of Hardness of Low-Alloy Steels Using Specific Jominy Distance |
| title_full_unstemmed | Artificial Neural Networks-Based Prediction of Hardness of Low-Alloy Steels Using Specific Jominy Distance |
| title_short | Artificial Neural Networks-Based Prediction of Hardness of Low-Alloy Steels Using Specific Jominy Distance |
| title_sort | artificial neural networks based prediction of hardness of low alloy steels using specific jominy distance |
| topic | low-alloy steels quenching mechanical properties hardness artificial neural networks |
| url | https://www.mdpi.com/2075-4701/11/5/714 |
| work_keys_str_mv | AT suncanasmokvinahanza artificialneuralnetworksbasedpredictionofhardnessoflowalloysteelsusingspecificjominydistance AT teamarohnic artificialneuralnetworksbasedpredictionofhardnessoflowalloysteelsusingspecificjominydistance AT darioiljkic artificialneuralnetworksbasedpredictionofhardnessoflowalloysteelsusingspecificjominydistance AT robertbasan artificialneuralnetworksbasedpredictionofhardnessoflowalloysteelsusingspecificjominydistance |