Prediction of MMAW performance on nanostructured hardfaced alloys using general regression neural network: A case study
Manual metal arc welding (MMAW) is popular in hardfacing operations to enhance the surface integrity and increase the working life of important industrial parts. The functional performance of nanostructured hardfaced alloys is strongly affected by welding factors, which cannot be considered linearly but interact in a complex, non-linear way with mechanical features and tribological behaviour.To predict the performance characteristics of MMAW nanostructured hardfaced alloys, a General Regression Neural Network (GRNN) was employed in the present work. We obtained statistical results for hardness, tensile strength, and wear resistance from systematic experimental trials conducted under different welding conditions. We used these data to train and test the GRNN model, and we quantitatively evaluated its predictive accuracy using the coefficient of determination (R2) and root mean square error (RMSE). The model showed strong predictive ability, indicating its usefulness in modelling complex non-linear associations among process and performance factors and their responses. This paper demonstrates that GRNN is a reliable and effective means of improving the quality and consistency of nanostructured hardfaced surfaces for industrial use while optimizing MMAW process parameters.
Authors
- Himadri Majumder (ORCID: https://orcid.org/0000-0002-5059-5984)
- Rajeev Ranjan (ORCID: https://orcid.org/0000-0003-1294-4765)
- Alemu Workie Kebede (ORCID: https://orcid.org/0009-0004-1039-4135)
- Abhijit Saha
Institutions
- Haldia Institute of Technology (IN)
- Dr. B.C. Roy Engineering College (IN)
- Debre Markos University (ET)
Publication Details
- Journal
- PLoS ONE
- Published
- 2026-11-16
- DOI
- https://doi.org/10.1371/journal.pone.0361981
- Primary Topic
- Metal Alloys Wear and Properties
- Type
- article
- Field-Weighted Citation Impact
- 0.00