Author ORCID Identifier
0009-0003-9895-2738
Biosketch
He completed his Ph.D. in Mechanical Engineering from SASTRA Deemed to be University, with research focused on the integration of additive manufacturing and data-driven modeling for the design and optimization of advanced engineering materials. His work primarily explores high-entropy alloys processed through laser powder bed fusion, aiming to establish robust relationships between process parameters, microstructure, and material performance. By combining experimental techniques with machine learning approaches, he develops predictive models for key properties such as hardness, density, and surface characteristics.
A significant aspect of his research is the development of machine learning frameworks for predicting phase formation and crystal structures in high-entropy alloys. These models enable rapid identification of stable phases and crystal structures, reducing reliance on extensive experimental trials and accelerating alloy design. His approach emphasizes the machine learning–assisted development of high-entropy alloys, providing deeper insights into composition–structure–property relationships.
His broader research interests include microstructural characterization and comprehensive mechanical and functional performance evaluation, including tensile behavior, hardness, wear, and corrosion properties. He also focuses on the application of machine learning in manufacturing systems to enhance material design and process efficiency. His work contributes to advancing additive manufacturing technologies and supports the development of next-generation materials with improved reliability and performance.
Date of Award
15-5-2026
Document Type
Thesis
School
School of Mechanical Engineering
Programme
Ph.D.-Doctoral of Philosophy
Second Advisor
Dr.T.Panneerselvam
Keywords
High Entropy Alloys, Machine Learning, Selective Laser Melting, Multi-Objective Grey Wolf Optimization, SMOTE Technique
Abstract
High Entropy Alloys (HEAs) are an emerging class of advanced materials that have gained significant attention due to their exceptional mechanical strength, thermal stability, and structural performance. Unlike conventional alloys based on a single principal element, HEAs are composed of multiple elements in a near-equiatomic ratio. Despite these advantages, designing HEAs with tailored properties is difficult because of the enormous number of possible combinations and the limitations of traditional trial-and-error methods. To overcome these challenges, this study presents a machine learning (ML) based approach to accelerate the design and development of an HEA.
In this work, a newly designed composition, namely Al0.2CuFeMnNi, was selected to meet the evolving requirements of next-generation engineering applications. Comprehensive empirical parameters, such as mixing enthalpy, mixing entropy, atomic size difference, valence electron concentration, and thermodynamic parameters, as well as chemical composition, were employed as input features for phase and crystal structure predictions. Among the evaluated ML models, eXtreme Gradient Boosting and Random Forest exhibited highest predictive performance, achieving 96% accuracy for crystal structure prediction. The Al0.2CuFeMnNi HEA was synthesised through Mechanical Alloying and subsequently fabricated through Selective Laser Melting.
Critical process parameters were optimised using a Multi-Objective Grey Wolf Optimisation. The optimal parameters obtained were 200 W laser power, 750 mm/s scanning speed, and 0.05 mm hatch spacing, which systematically control microstructural evolution, relative density, and surface integrity. Comprehensive characterisation was performed on the fabricated samples, including X-ray diffraction for phase analysis, scanning electron microscopy for microstructure, and elemental mapping. The surface roughness of the fabricated samples was examined using white-light interferometry.
Microhardness and tensile testing were carried out to evaluate mechanical performance. Pin-on-disc tribological testing under varying loads was performed to assess wear behaviour. Electrochemical corrosion was evaluated through potentiodynamic polarisation and electrochemical impedance spectroscopy to determine corrosion performance. These detailed characterisation studies established a correlation between processing parameters, microstructural development, and the resulting material properties. The integrated approach enabled the systematic optimisation of processing parameters, providing a comprehensive understanding of the structure-property relationship in Al0.2CuFeMnNi HEA and establishing a framework for the development of high-performance HEAs for bearing, structural, and lightweight automotive applications.
Recommended Citation
K, Hareharen Mr, "Machine Learning Assisted Development of Al0.2CuFeMnNi High Entropy Alloy through Selective Laser Melting" (2026). Theses and Dissertations. 217.
https://knowledgeconnect.sastra.edu/theses/217