Subhodwip Saha

Mr. Subhodwip Saha

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2025 in Crystals
Verified
Journal Article
Open access
PDF file
Subhodwip SahaSubhodwip Saha
Subhodwip Saha
Barun HaldarBarun Haldar
Barun Haldar
HJHillol Joardar
Hillol Joardar
Santanu DasSantanu Das
Santanu Das
SMSubrata Mondal
Subrata Mondal
STSRINIVAS TADEPALLI
SRINIVAS TADEPALLI
This investigation explores the application of supervised machine learning regression approaches to predict various responses, including penetration, bead width, bead height, hardness, ultimate tensile strength, and percentage elongation in autogenous TIG-, A-TIG-, and TIG-welded joints of SS304H, which is considered as an advanced high-temperature resistant material. The machine learning (ML) models were constructed based on the data gathered from 50 experimental runs, considering eight key input variables: gas flow rate, torch angle, filler material, welding pass, flux application, root gap, arc gap, and heat input. A total of 80% of the collected dataset was used for training the models, while the remaining 20% was reserved for testing their performance. Six ML algorithms—Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), Support Vector Regression (SVR), Random Forest (RF), Gradient Boosting Regression (GBR), and Extreme Gradient Boosting (XGBoost)—were implemented to assess their predictive accuracy. Among these, the XGBoost model has demonstrated the highest predictive capability, achieving R2 scores of 0.886 for penetration, 0.926 for width, 0.915 for weld bead height, 0.868 for hardness, 0.906 for ultimate tensile strength, and 0.926 for percentage elongation, along with the lowest values of RMSE, MAE, and MSE across all responses. The outcomes establish that machine learning models, particularly XGBoost, can accurately predict welding characteristics, marking a significant advancement in the optimization of TIG welding parameters. Consequently, integrating such predictive models can substantially enhance the precision, reliability, and overall efficiency of welding processes.

6 October 2025 in International Journal of the Analytic Hierarchy Process
Verified
Journal Article
Closed access
Subhodwip SahaSubhodwip Saha
Subhodwip Saha
MBMainak Bandyopadhyay
Mainak Bandyopadhyay
Santanu DasSantanu Das
Santanu Das
SMSubrata Mondal
Subrata Mondal
RIRafikul Islam
Rafikul Islam
Weldability is a critical factor in the fabrication of various grades of stainless steel used in industries. Tungsten Inert Gas (TIG) welding, known for its precision and high-quality results, is frequently employed in industrial applications. However, one of the common challenges with TIG welding is achieving adequate penetration of weld joints, despite the flexibility to modify welding parameters. A suitable combination of welding parameters such as current, inert gas flow rate and root gap can increase heat input and improve penetration depth, leading to a significant enhancement in the quality of weld joints and its productivity. This, in turn, ensures better performance and long-term reliability. In this work, the welding process of 304H austenitic stainless steel is tried to be optimized, that is known for its strength and corrosion resistance in boiler components. The experiment is designed using Response Surface Methodology (RSM) with Central Composite Design (CCD), considering three factors: heat input, root gap and gas flow rate. Each factor is tested at three different levels to understand their effect on the quality of the welds, aiming primarily for full penetration, which is crucial for creating a strong joint. A total of 14 samples of 8mm thick 304H stainless steel plates, each measuring 50 mm by 50 mm, are welded using Gas Tungsten Arc Welding (GTAW), popularly known as TIG welding, with similar filler material to improve the overall weld quality. In this study, the Analytical Hierarchy Process (AHP), a multi-criteria decision-making tool, is employed to validate the optimal values determined. The results obtained from the research align well with the AHP results.