2026 ASEE Annual Conference & Exposition

The advantages of flipped teaching have long been recognized; however, its implementation often demands significant preparation time and access to appropriate technology. This paper examines strategies through which artificial intelligence (AI) can enhance the student learning experience in an introductory Engineering Thermodynamics course. By employing effective teaching pedagogies, leveraging diverse AI tools, and integrating interactive digital resources, instructors can provide a more engaging and supportive learning environment.

Inquiry-based questions, particularly for complex topics such as entropy, can support students’ pre-class preparation and foster active engagement during discussions. These questions also serve as valuable learning tools for students with limited prior knowledge. AI-generated visual materials—such as anchor charts or conceptual posters—can strengthen visual learning and aid concept retention. Student collaboration can be encouraged through shared video projects highlighting key thermodynamic principles. Additionally, AI-enabled tools for automated captioning and transcription enhance accessibility and improve comprehension of course content.

AI can also act as a critical examiner by providing alternative perspectives for validating hypothetical heat engines or refrigerators that appear to violate the Second Law of Thermodynamics. Animations can illustrate reversible and irreversible processes, while thermodynamic efficiencies can be dynamically visualized. Complex numerical problems—often neglected due to computational intensity—can be integrated meaningfully using AI-based tools. Examples include analyzing wind velocity effects on power generation, examining gas incompressibility at different temperatures, and evaluating higher-order ideal gas equations. AI-assisted, step-by-step derivations further reinforce conceptual understanding and analytical skills.

Simulations enable students to explore the influence of the polytropic index on thermodynamic processes, while AI-based visualizations clarify the optimization of Rankine cycle temperatures. Energy balance principles can be effectively conveyed using AI-generated concept maps for applications such as nozzles, turbines, compressors, and diffusers. AI tools can also gather and analyze data for thermodynamic properties—for instance, atmospheric pressure variations with elevation—and validate empirical relationships using equation generators such as Excel. Multiple plots can demonstrate the impact of glass thickness on heat loss for specified surface temperatures, providing immediate feedback on parameter sensitivity and system performance.

Moreover, AI can tutor students on saturation tables, psychrometric charts, and Mollier diagrams before lectures, allowing class time to focus on problem-solving and higher-level analysis. This approach enhances the flipped learning model and deepens student engagement with thermodynamic principles.

In this paper, illustrative examples are provided for each topic to demonstrate the effective integration of AI-based flipped classroom strategies in a 12/14-week Engineering Thermodynamics course.