This paper presents a course-based research study investigating how generative artificial intelligence (AI) can be meaningfully integrated into a senior-level chemical engineering design course to foster students’ engineering judgment, reflective thinking, and professional self-efficacy. The study was conducted in the capstone senior design sequence, where students worked on authentic, open-ended design problems reflective of industrial practice. Two major design challenges were incorporated: (1) optimization of utility consumption through heat integration and heat exchanger network (HEN) design, and (2) simulation and design of a vinyl chloride monomer (VCM) production process using Aspen Plus.
Each student first employed a selected AI tool—such as ChatGPT, Gemini, Claude, or Copilot—to independently generate complete solutions, including process flow diagrams, pinch analyses, distillation column parameters, and energy trade-off evaluations. Teams then collaborated to perform manual calculations, verify results, and compare AI-generated and human-generated solutions to identify conceptual and thermodynamic inaccuracies. Both individual and team reflections were collected to analyze students’ reasoning processes and perceptions of AI’s role in design.
This study investigates how structured AI use shapes students’ engineering judgment and self-efficacy in process design. Preliminary results suggest that while AI tools improved creativity and early-stage problem framing, they frequently made unrealistic assumptions that required critical validation. The reflective analyses revealed that engaging with AI outputs deepened students’ metacognitive awareness, prompting them to apply disciplinary reasoning, verify data integrity, and confront ethical considerations surrounding reliance on AI. The findings contribute to emerging frameworks for AI-augmented engineering education, emphasizing reflection, judgment, and the human-AI partnership as central to developing adaptive expertise in future engineers.
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