2025 AIChE Annual Meeting

(383t) Advancing Hydrogen Generation: Data-Driven Modeling, Optimization, and Techno-Economic Evaluation of Electrolyzer and Fuel Cell Systems

Authors

Fernando Lima, West Virginia University
As industries accelerate their transition to net-zero, hydrogen has become a crucial component of decarbonized energy and manufacturing systems. My research integrates advanced electrochemical technologies with process systems engineering to develop systematic and scalable frameworks for modeling, optimization, operability analysis, and techno-economic evaluation of cutting-edge electrolyzer and fuel cell systems. These frameworks aim not only to enhance performance and reliability, but also to support the real-world deployment of sustainable hydrogen production solutions across chemical, energy, and clean technology sectors.

One key aspect of my work involves developing physics-based electrochemical models for proton-conducting and oxygen-conducting solid oxide electrolyzer cells (SOECs), using Python. These models are integrated into an operability analysis platform (Opyrability) to identify stable operating regions under uncertainty and guide safe, efficient operation. Additional models were created to simulate solid oxide fuel cell (SOFC) configurations, with a focus on reversibility and degradation behavior. These efforts are closely linked with techno-economic analysis (TEA) and life cycle assessment (LCA) to evaluate the economic viability and environmental impact of such novel technologies.

A second focus area involves applying machine learning and optimization algorithms to improve decision-making. I developed predictive AI models for methane reforming and optimized MATLAB-based genetic algorithms to maximize syngas yield. I also designed process flowsheets for ultra-fast high-temperature sintering (UHS) in manufacturing SOEC components, using AVEVA Process Simulation to optimize material use and thermal profiles.

Together, these frameworks form a multi-layered platform that combines first-principles modeling, AI-driven learning, and systems-level assessment. They support efficient process development and help scale up electrolyzer and fuel cell technologies for a green hydrogen economy.

Research Interests:

Electrochemical Systems, Process Simulation, Operability, Optimization, Process Systems Engineering, Hydrogen Production, Carbon Capture, AI–Machine Learning Modeling, Techno-Economic Analysis (TEA), Life Cycle Assessment (LCA), Software Development (using GitHub, etc.), Sustainability