Publication: Optimizing Parameters of the Pack Carburizing Process with Natural Energizers to Improve the Impact and Hardness Properties of Low-Carbon Steel Using NSGA-II-Based Artificial Intelligence
4
0
Issued Date
2024-12-01
Resource Type
ISSN
10599495
eISSN
15441024
Scopus ID
2-s2.0-85177474143
Journal Title
Journal of Materials Engineering and Performance
Volume
33
Issue
24
Start Page
13954
End Page
13966
Rights Holder(s)
SCOPUS
Bibliographic Citation
Journal of Materials Engineering and Performance Vol.33 No.24 (2024) , 13954-13966
Suggested Citation
Wiangkham A., Aengchuan P., Sudtachat K., Ariyarit A., Srisuk S., Thammachot N. Optimizing Parameters of the Pack Carburizing Process with Natural Energizers to Improve the Impact and Hardness Properties of Low-Carbon Steel Using NSGA-II-Based Artificial Intelligence. Journal of Materials Engineering and Performance Vol.33 No.24 (2024) , 13954-13966. 13966. doi:10.1007/s11665-023-08953-8 Retrieved from: https://hdl.handle.net/20.500.14740/20700
Corresponding Author(s)
Other Contributor(s)
Abstract
The "Big Knife" or "Eto" is the local name for one of the popular types of knives in Thailand which has many applications. These knives are typically forged from car leaf spring steel that the villagers buy wholesale into the knife forging shop at the scale of a community industry. However, occasionally the materials used in knives are insufficient to meet their needs and there may be uncertainty because of various or unidentified sources. This study investigates the replacement of car leaf spring steel used in knife forging with commercial AISI 1010 low-carbon steel in order to solve the problem mentioned above. The low-carbon steel that was used as the replacement knife forging material was processed by the pack carburizing process with several types of energizers, including calcium carbonates, egg duck shells, cow bone, river snail shells, and golden apple snail shells under different conditions of temperature and time, and the properties in terms of hardness and impact tolerance were investigated. To make it easier to implement, the pack carburizing process conditions were optimized for hardness and impact properties via the NSGA-II multi-objective optimization algorithm with the Gaussian process regression model (GPR), which is one artificial intelligence algorithm, as a surrogate model. After the experiment, results clearly indicated the effect of heat treatment conditions (energizer type, temperature, and time) on the hardness and impact of treated AISI 1010 steel; moreover, the GPR model also shows a relatively high efficiency measured in various terms of performance metrics representing the behavior of hardness and impact that arise from the pack carburized process parameters.