Integration of ChatGPT 4o in Teaching Chemical Engineering Process Analysis
Huan Gu, Ph.D.
Department of Chemistry, Chemical and Biomedical Engineering
Tagliatela College of Engineering
University of New Haven
With the rapid advancement of conversational artificial intelligence (AI), it has become increasingly important to examine how such tools can be responsibly integrated into engineering education. In particular, students must learn not only the potential applications of these tools but also the limitations and risks of overreliance. This project investigated the use of ChatGPT-4o in a junior-level Chemical Engineering course, Process Analysis, with the goal of assessing its role in supporting student learning and problem-solving.
As part of the final project, students were required to conduct materials and energy balances as well as an economic analysis of a chemical process. ChatGPT-4o was introduced as a freely available resource that students could use within a limited timeframe. Findings indicated that the tool was effective for collecting reference information, including unit prices of reactants and products, solubility data, dew points, vapor pressures, and heat capacities. However, the tool demonstrated limited effectiveness in tasks requiring higher-order thinking, such as developing and labeling process flow diagrams, performing complete materials and energy balances, constructing detailed economic analysis tables (covering budget, income, and profit), and interpreting data to make informed engineering judgments.
The integration of ChatGPT-4o ultimately highlighted for students the importance of a solid foundation in engineering principles. While the tool could provide useful supplementary information, students recognized that critical evaluation, domain knowledge, and problem-solving skills were necessary to assess the accuracy of AI-generated output and to apply it productively. These findings suggest that conversational AI can be incorporated into chemical engineering education not as a substitute for fundamental learning, but as a scaffold that encourages students to engage more deeply with engineering concepts, exercise professional judgment, and develop responsible practices for future use of emerging technologies.
The full paper will be available to logged in and registered conference attendees once the conference starts on June 21, 2026, and to all visitors after the conference ends on June 24, 2026