- Research & Machine Learning Applications + UUV Motion Prediction & Hydrodynamics: Developed a machine learning framework to predict UUV motions with high accuracy (around 2% relative error) and gain insights into UUV hydrodynamics. + Stability Constant Factor Estimation for CRB Models: Developed a machine learning framework to predict a rigorous lower bound for the stability constant factor of a Certified Reduced-Basis Model (CRB). This framework guarantees all three key requirements of CRB models: rigorousness, rapidness, and sharpness/accuracy.- Technical Skills Highlighted + Advanced Machine Learning Techniques: Applied a combination of physics-informed machine learning, autoregressive neural networks, adaptive sampling, Bayesian optimization, multi-fidelity modeling, and mixture of density networks. + Matlab Scripting for RB Model Development: Parameterized governing equations (linear elasticity and Helmholtz) to generate data for the machine learning models and validate the results.- Research Outcomes + UUV Motion Prediction & Hydrodynamics: Achieved a highly accurate forecasting solution with minimal error (around 2%). + Stability Constant Factor Estimation for CRB Models: Established a rigorous, rapid, and sharp error bound for CRB solutions. This approach yielded a significant improvement in accuracy/sharpness (approximately 900%) compared to other published works.

- Research & Geometric Parameterization Applications in Reduced-Basis Method + Developed a novel geometric parameterization scheme for the certified reduced basis method analysis of a square unit cell, published findings in a peer-reviewed journal (https://doi.org/10.12941/jksiam.2021.25.196)- Technical Skills Highlighted + Python scripting for Finite Element Modeling (FEM): Utilized the FEniCS Python package to generate training data for the RB model and for the validation process + Python scripting for Certified Reduced-basis (CRB): Parameterized the heat equation to change the radius of the unit cell, Constructed the RB model based on the parameterized heat equation- Research Outcomes + RB solution with nearly the same solution with a speed of about 29 times faster on average, compared to FEM solution

- Research & Machine Learning Applications in Metal Forming + EDPOMP Project (VINIF funded): Developed a machine learning methodology to identify plastic flow in aluminum sheets during incremental sheet forming (ISF) processes. Published findings in a peer-reviewed journal (https://link.springer.com/article/10.1007/s00170-022-08698-z). + Contributed to ISF research: Presented research on predicting deformed shapes in ISF using a feedforward neural network at a prestigious conference (link included: https://link.springer.com/chapter/10.1007/978-981-19-2350-0_4).- Technical Skills Highlighted + Finite Element Modeling (FEM): Utilized ABAQUS software to generate training data for the machine learning model. + Machine Learning (ANN): Selected features, constructed, and analyzed the performance of Artificial Neural Network models for material parameter prediction in metal forming.

- 3D Modeling & Finite Element Analysis + Developed 3D models suitable for meshing, tailored for large-scale industrial applications. + Performed mesh generation and ensured high-quality grids for accurate simulations. + Utilized RB FEA method to solve complex engineering problems. + Analyzed simulation data to extract valuable insights.- Key Skills & Achievements + Automated workflows: Successfully scripted Python code to automate repetitive tasks, improving efficiency. + Proficient in 3D modeling: Possess the ability to create models specifically designed for finite element analysis. + Strong analytical skills: Capable of interpreting complex data generated from simulations.

- 3D Modeling & Vision Inspection Systems Design + Created and assembled 3D models for vision inspection systems. + Designed individual components for optimal system functionality. + Generated 2D manufacturing drawings to ensure accurate production.- Key Learnings + Mastered new design procedures for efficient development. + Gained in-depth knowledge of automation systems (e.g., pneumatics). + Adapted effectively to an industrial work environment.