Transient thermomechanical response of an electrolyte supported planar solid oxide electrolysis cell under dynamic loading conditions

Solid oxide electrolysis cells (SOECs) offer high efficiency, noble-metal-free construction, and broad power adaptability, making them promising for large-scale green hydrogen production integrated with renewable energy. However, the intermittency of renewable energy induces spatial and temporal gradients in temperature and electrochemical fields of the cell, leading to stress concentrations and potential mechanical failure. Understanding the transient thermomechanical response during dynamic loading of a SOEC is thus crucial for evaluating the electrochemical performance and predicting cell lifetime. While previous studies focused on developing steady-state models to investigate the thermal stress in the cell, we develop a transient multi-physics model to capture the coupled thermo–electro–chemo–mechanical behavior of an electrolyte-supported planar SOEC under dynamic operating conditions. Numerical simulations are performed with varying power control strategies, heating rates and water vapor molar fractions. Results reveal that the electrolyte layer consistently experiences the highest average maximum principal stress and failure risk. Stepped current density control induces a higher heating rate and thermal stress compared to stepped voltage control. Additionally, a slower water molar fraction decline reduces electrochemical reaction and heat absorption rates, leading to a slower temperature rise and reduced thermal stress. To enable rapid and accurate prediction of critical thermomechanical responses, a Random Forest Regression model is trained on simulation data using gas inlet heating rate as input. The model accurately predicts temperature and stress in the electrolyte layer and demonstrates strong generalization on unseen scenarios. The integration of high-fidelity physics-based modeling and machine learning provides a foundation for intelligent SOEC control and real-time optimization, enhancing system reliability and extending operational lifetime under renewable energy operation.