Integrating Generative Artificial Intelligence into a Context-Based Electrochemistry Laboratory: Supporting Student Reasoning in Corrosion Kinetics
Abstract Tafel polarization analysis can be used to teach corrosion kinetics in upper-division physical chemistry and materials science laboratories, but implementing it through fixed procedures and automated fitting may limit students’ engagement with the underlying electrochemical principles. This work describes a context-based electrochemistry laboratory that integrates a large language model (LLM) as an analytical scaffold rather than a source of ready-made answers. The experiment was implemented with 60 third-year (fifth-semester) undergraduates in engineering-related majors. Students worked in groups of three, with each student attending one laboratory session consisting of three 45-min class periods. Within a materials-selection scenario for marine bridge components, students compared Q235 plain carbon steel and Q235NH weathering steel in 3.5 wt.% NaCl. Throughout the “AI + Lab Session,” DeepSeek was used to generate candidate SOPs, propose troubleshooting hypotheses, and clarify spreadsheet-based Tafel analysis, while students evaluated AI-generated operating parameters, performed Tafel polarization measurements, used AI-supported reasoning to troubleshoot instrumental problems, manually analyzed raw polarization data in spreadsheet software, and connected corrosion kinetics with a 30-year life-cycle cost analysis. Assessments based on oral examinations, instructor observations, and process-oriented individual laboratory reports indicated that most students completed the tasks successfully, with overall report scores mainly between 75 and 90 and an average score of 80.75 points. Troubleshooting scores showed the greatest variation, identifying diagnostic reasoning as the component requiring the most instructional support. This laboratory offers a transferable model for using generative AI to support student reasoning in corrosion kinetics, electrochemical data analysis, and materials-selection decision-making.
Authors
- Juan Jia
- Lu Xia (ORCID: https://orcid.org/0009-0005-9843-7618)
- Mingjie Dai
Institutions
- Wuhan University of Science and Technology (CN)
Publication Details
- Journal
- Journal of Chemical Education
- Published
- 2026-11-13
- DOI
- https://doi.org/10.1021/acs.jchemed.6c00476
- Primary Topic
- Various Chemistry Research Topics
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Hubei Provincial Department of Education
- Natural Science Foundation of Hubei Province
- Wuhan University of Science and Technology