PhD Candidate in Mechanical Engineering | Advanced Manufacturing for Aerospace | Metal-Based Additive Manufacturing | AI for Manufacturing

I am a PhD candidate in Mechanical Engineering at Embry-Riddle Aeronautical University, working at the intersection of aerospace-focused advanced manufacturing, physics-based modeling, sensor-driven monitoring, and machine learning. My research centers on metal-based additive manufacturing, aiming to develop intelligent, closed-loop manufacturing systems through the integration of real-time sensing, predictive modeling, and adaptive control. This work seeks to enhance process stability, microstructural control, and geometric fidelity in Directed Energy Deposition (DED) and related manufacturing platforms.

• Metal Additive Manufacturing
• Hybrid manufacturing and CNC-assisted additive manufacturing
• Thermal and geometric stability in additive manufacturing
• Sensor-based process monitoring
• Machine learning for process prediction and optimization
• Closed-loop control for intelligent manufacturing systems

Simulation & Modeling ANSYS Fluent, ANSYS Mechanical, Abaqus, CFD, FEM

Programming & Data Science Python, MATLAB, Machine Learning, Data Analysis

Manufacturing & Characterization Directed Energy Deposition, Binder Jetting, CNC machining, mechanical testing, DIC, SEM, EDX, EBSD

CAD & Geometry Processing Fusion 360, SolidWorks, Open3D, Trimesh, CloudCompare, mesh processing, signed distance field analysis

Developed an end-to-end pipeline for manufacturing validation by integrating ICP-based alignment and signed distance field methods to quantify geometric deviation between meshes, point clouds, and CAD references. The workflow generates deviation heatmaps, statistical reports, and tolerance verification metrics.

Designed and executed a hybrid DED-CNC workflow integrating laser-based deposition and CNC machining. Developed dwell-time control strategies to regulate thermal input, stabilize deposition behavior, and assess dimensional accuracy and surface integrity of metal matrix composite builds.

Designed and executed DED experiments using spatially variable process parameters as a next-step extension of functionally graded materials. Characterized microstructure evolution using SEM, EBSD, and PDAS analysis to connect thermal gradients with grain morphology, texture, and mechanical response.

Developed thermal models of melt pool behavior using moving heat source approximations and implemented in-situ pyrometry with control algorithms to regulate melt pool temperature. Applied machine learning and sensitivity analysis to quantify the effect of process parameters on thermal response and build geometry.

Built a data-driven modeling framework for Li-NMC battery leaching using curated experimental and literature-based datasets. Trained gradient boosting models to predict multi-element recovery and performed sensitivity and uncertainty analysis to guide process optimization.

Developed LSTM and GRU models for hourly electricity and heat demand prediction in residential systems. Optimized model architecture and hyperparameters to improve accuracy and robustness under temporal variability.

• Amir Yah, H. Patel, J. Robinett, S. Namilae, Y. Zhou. Binder jetting additive manufactured stainless steel battery cooling case: design, fabrication, and thermo-fluid analysis. Manufacturing Letters, 2026.

• A. Shakibi, Amir Yah, Y. Zhou. Predicting bead geometry in laser powder directed energy deposition: ensemble machine learning models for complex process parameters. The International Journal of Advanced Manufacturing Technology, 2026.

• Amir A. Yahyaeian, A. Shakibi, A. Mello, Y. Zhou. Directed Energy Deposition Additive Manufacturing of Stainless Steel with Spatially Variable Process Parameters. AIAA SciTech 2026.

• A. Morteza, Amir A. Yahyaeian, M. Mirzaeibonehkhater, S. Sadeghi, A. Moheimeni, S. Taheri. Deep Learning Hyperparameter Optimization: Application to Electricity and Heat Demand Prediction for Buildings. Energy & Buildings, 2023.

• ➡️ Full publication list: Google Scholar

• Public Policy Chair, AIAA Cape Canaveral Section
• Graduate teaching assistant in Mechanical Design Process, Artificial Intelligence, and Advanced Engineering Mathematics

Ph.D. Mechanical Engineering Embry-Riddle Aeronautical University, Daytona Beach, FL 2024–2027

M.Sc. Mechanical Engineering Purdue University, Indianapolis, IN 2022–2023

B.Sc. Mechanical Engineering Islamic Azad University, Tehran, Iran 2014–2020

• Email: [email protected]
• LinkedIn: Amir Yah
• Location: Daytona Beach, Florida, USA

I use GitHub to document research workflows, engineering tools, data-driven manufacturing projects, and public-facing outreach initiatives.