AI for Additive Manufacturing
Machine learning models for process optimization, reduced-order modeling, uncertainty analysis, and data-driven prediction of AM outcomes.
ANNCAE-MLPPOD-ANN
Faculty Candidate · Mechanical Engineering
AI-driven additive manufacturing for sustainable aerospace materials.
Ph.D. researcher and educator working across metal additive manufacturing, computational mechanics, machine learning, optimization, microstructure analysis, and sustainable powder recycling.
I develop data-driven and physics-informed frameworks that connect process parameters, thermal history, microstructure, and mechanical performance in metal additive manufacturing. My academic profile combines experimental AM, finite element simulation, reduced-order modeling, AI/ML, engineering teaching, and student supervision.
7+
Years research & teaching
10
Publications & conferences
5
Supervised students
0.0003
Relative L2 error in ROM
Research Agenda
From process parameters to reliable, sustainable AM components.
My work focuses on the scientific and computational bridge between additive manufacturing process design, microstructure evolution, material performance, uncertainty, and sustainability.
Process–Microstructure–Property Links
Experimental and computational methods to understand how AM process windows influence microstructure, tensile behavior, fatigue response, and structural integrity.
LPBFTi-6Al-4VMicrostructure
Sustainable Metal Powder Recycling
Research on recyclability, degradation mechanisms, and sustainable reuse of metal powders for reducing cost, waste, and environmental impact in AM.
SS316Powder reuseNet zero
Computational Mechanics
Thermo-mechanical finite element modeling of SLM/LPBF processes, calibration algorithms, residual stress analysis, and structural performance evaluation.
ANSYSFEAThermal-structural
Optimization & Inverse Design
Genetic algorithms, differential evolution, and particle swarm optimization for identifying optimal AM process parameters and material performance targets.
GADEPSO
Digital Twin for AM
Long-term vision: integrated sensing, simulation, surrogate modeling, and decision-making loops for intelligent additive manufacturing systems.
Digital twinAM monitoring
Teaching Philosophy
Engineering education through simulation, experiments, and applied problem solving.
My teaching approach connects theory with hands-on tutorials, computational tools, design problems, and research-inspired examples that help students see engineering as a living, applied discipline.
Teaching Experience
Jan 2022 – May 2022
Teaching Assistant · Application of the Finite Element Method
Facilitated FEM sessions, hands-on Workbench tutorials, and student mentoring in structural and thermal analysis.
Sep 2021 – Dec 2021
Teaching Assistant · Advanced Fluid Mechanics
Conducted tutorials in compressible and incompressible fluid dynamics, including CFD demonstrations using ANSYS Fluent.
Aug 2015 – May 2018
Teacher · Ek Pehal
Taught science and mathematics, designed curriculum materials, and supported volunteer training and student mentorship.
Courses I Can Teach
Finite Element Method
Computational Fluid Dynamics
Introduction to AI/ML
Heat Transfer
Structural Analysis
Fluid Dynamics
Additive Manufacturing
Computational Mechanics
Engineering Optimization
Academic Path
Research experience across universities, aerospace, and industry collaboration.
Sep 2025 – Present
Postdoctoral Research Fellow
Sustainability and Design Engineering, University of Prince Edward Island
- Developing machine learning models for rare earth mineral deposit identification and critical-material exploration.
- Applying AI-based microstructure analysis to process–structure relationships in metal additive manufacturing.
- Investigating metal powder recyclability and degradation mechanisms for sustainable powder-based AM.
Mar 2026 – Present
Mitacs Research Intern
WEICAN, Charlottetown
- Designing AI-driven and federated learning solutions for efficient, reliable wind power systems.
- Building ML models for renewable energy data analysis and optimization.
Oct 2024 – Mar 2025
Research Associate
Aerospace and Mechanical Engineering, Royal Military College of Canada
- Conducted experimental parametric optimization for AM aerospace components with focus on microstructure and fatigue resistance.
- Performed tensile testing, fatigue analysis, and microstructural characterization to establish process-property relationships.
- Led a team of four researchers to enhance parametric optimization workflows for aerospace applications.
Jan 2018 – Oct 2023
Doctoral Researcher
Mechanical Engineering, ÉTS / University of Québec, Montréal
- Developed non-intrusive reduced-order models for SLM-built parts using CAE-MLP and POD-ANN frameworks.
- Achieved relative L2 error of 0.0003 in ROM prediction and 0.2% error in ML-assisted AM optimization.
- Applied Monte Carlo simulation, Sobol sensitivity analysis, and optimization algorithms for AM parameter identification.
Education
Academic training in mechanical engineering, machine learning, physics, and computational modeling.
Ph.D. in Mechanical Engineering and Machine Learning
ÉTS, University of Québec, Montréal, Canada · 2018–2023
Thesis: Optimizing the structural properties of metal 3D printed parts for aerospace application using machine learning.
Bachelor of Science & Master of Science in Physics
IISER Kolkata, India · 2013–2017
Thesis: Analysis of flow and heat transfer in a radial jet.
Publications
Selected scholarly contributions.
Journal articles and conference contributions across additive manufacturing, reduced-order modeling, computational mechanics, microstructure-property modeling, and thermo-hydrodynamics.
2026
Recycled Stainless Steel as a Sustainable Feedstock for Direct Metal Laser Sintering: Challenges and Opportunities
2025
Data-driven non-intrusive reduced order modelling of selective laser melting additive manufacturing process using POD and convolutional autoencoder
2025
Experimental and Numerical Modal Analysis of a Honeycomb Panel for Aircraft Structures Application
2023
Sensitivity and Uncertainty Analysis of SLM Process Using Artificial Neural Network
2022
A comparative study of machine learning methods for computational modelling of the selective laser melting additive manufacturing process
2022
Computational modelling of SLM additive manufacturing of metals
2018
Effects of gravity on the thermo-hydrodynamics of moving contact lines
Mentorship
Student supervision and academic leadership.
Ph.D. Co-Supervision
Liem Huynh and David Holsworth, Royal Military College of Canada.
Master’s Co-Supervision
Syed Imran Ali, University of Prince Edward Island.
MITACS Exchange Students
Pratyush Bhatt and Yash Kumar, ÉTS Montréal.
Leadership
Lab Coordinator at ÉTS, managing supplies, budgets, procurement, and support for research and academic activities.
Community Engagement
Co-founder of Ek Pehal NGO, supporting educational outreach, volunteer training, and science/mathematics learning.
Technical Profile
Tools for computational research and engineering education.
Programming & ML
PythonSQLRMatlabFortranC++TensorFlowScikit-LearnXGBoostKeras
Simulation & Engineering Software
ANSYS WorkbenchANSYS FluentWorkbench AdditiveANSYS Additive PrintSolidWorksAPDLCOMSOLParaviewLaTeX
Honors
Awards and fellowships.
Mitacs Research Fellowship · 2026
Excellence Award for Ph.D. Research · 2023
ÉTS Institute Fellowship · 2018–2023
INSPIRE Fellowship · MS · 2015–2017
INSPIRE Fellowship · BS · 2013–2015
Haryana State Scholarship · Top 5%
Open to faculty, research, and collaboration opportunities.
I am interested in academic roles and collaborations at the intersection of additive manufacturing, machine learning, computational mechanics, aerospace structures, renewable energy, and sustainable materials.