From Behavioral Assessment to Cognitive Attribution: Explainable AI-Enabled Reform in Electrical Machines Laboratory Instruction
DOI:
https://doi.org/10.55578/fepr.2608.012Keywords:
electrical machines laboratory, cognitive attribution, causal discovery, personalized feedback, teaching assessment reformAbstract
Laboratory courses in electrical machines have long been constrained by unidimensional process assessment, ambiguous attribution of learning difficulties, and the absence of personalized feedback. This study proposes an intelligent teaching evaluation and feedback framework grounded in explainable AI. The framework first constructs a multidimensional set of explicit features spanning cognitive foundations, affective attitudes, and operational behaviors. A differentiable causal discovery algorithm then extracts latent causal relationships from these explicit features that influence experiment completion. Finally, the TabNet attentive interpretable model builds a personalized prediction and attribution model for learning performance. This mechanism shifts laboratory evaluation from an outcome-oriented paradigm toward cognitive attribution, offering a computational pathway to address the diagnostic blind spot wherein traditional evaluation identifies surface problems but fails to trace their cognitive origins. The framework can inform the transition from experience-driven teaching evaluation to data-driven cognitive attribution in core electrical engineering laboratory courses.
References
[1] Cui, X. S., Wang, H., & Zhao, H. S. (2025). Visualization innovative teaching practice of “Electrical Machines” integrating virtual and real. Journal of Electrical and Electronic Education, *47*(2), 27–31.
[2] Ren, J. Z., Xu, S. Z., & Xin, X. (2022). Exploration of innovative reform in electrical machines experiment course teaching. Science and Technology Vision, (27), 125–127.
[3] Zhang, C. Y., Gao, J., & Zheng, A. H. (2022). Reform and exploration of information-based teaching of electrical machines course under new situation. China Modern Educational Equipment, (21), 22–26.
[4] Ji, X., Li, J. W., & Gao, H. Y. (2025). Exploration of project-progressive practical teaching pathway for “Electrical Machines” from the perspective of science-education integration. Research and Exploration in Laboratory, *44*(2), 183–186, 219.
[5] Kan, C. H., Ma, M. N., & Li, X. (2026). Exploration and practice of teaching methods for “Electrical Machine Engineering Training” course. Journal of Electrical and Electronic Education, *48*(1), 181–185.
[6] Li, X. P., Miao, Z. H., & Wang, B. B. (2024). Reform and practice of electromechanical system control experiment course under the background of “New Engineering”. Experiment Science and Technology, *22*(4), 47–53.
[7] Lu, Y., & Li, G. (2025). Enhancing Electric Machine Education: An integrated approach using 3D-printed models, multiple intelligences, and gamification. In Proceedings of the 2025 6th International Conference on Education, Knowledge and Information Management (pp. 1–5).
[8] Badreddine, F. M., El-Abd, M., & Hussain, G. A. (2026). Real-time co-simulation of electric machines using Unity and Simulink for laboratory applications. IEEE Access.
[9] Shao, Z., Wang, Y., & Zhong, Z. (2026). Classroom Education Enhancement: An open air-gap motor drive testbed with multiple operation modes. IEEE Power Electronics Magazine, *13*(1), 101–111.
[10] Duan, X. H., Cang, J. J., & Wang, B. Y. (2026). Practical exploration of teacher training in electrical machines based on virtual simulation of engineering cases. Advances in Education, *16*(6), 1162–1165.
[11] Liu, R. Z. (2026). Task-driven strategies for cultivating creative thinking in electrical machines teaching. Journal of Jilin Provincial Institute of Education, *42*(4), 109–113.
[12] Ruiz-Sarrio, J. E., Madariaga-Cifuentes, C., & Antonino-Daviu, J. A. (2025). FEA-Assisted Test Bench to enhance the comprehension of vibration monitoring in electrical machines—A practical experiential learning case study. Knowledge, *5*(3), 16.
[13] Lu, C. L., & Zhang, Y. X. (2026). Dynamic decision-support for engineering course evaluation and improvement: A case study of the electric machinery and drives course. Scientific Reports.
[14] Bhattacharya, R., Nagarajan, T., & Malinsky, D. (2021). Differentiable causal discovery under unmeasured confounding. In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) (pp. 2314–2322).
[15] Arık, S. Ö., & Pfister, T. (2021). TabNet: Attentive interpretable tabular learning. Proceedings of the AAAI Conference on Artificial Intelligence, *35*(8), 7115–7123.
[16] Li, J. X., & Liang, W. H. (2024). Effectiveness of virtual laboratory in engineering education: A meta-analysis. PLOS ONE, *19*(12), e0316269.
Downloads
Published
Data Availability Statement
Data availability is not applicable to this article as no new experimental data were created or analyzed in this methodological study.
Issue
Section
License
Copyright (c) 2026 Wenxue Xie, Jia Hu, Qingkan Zhang, Ziwei Wu, Tingyu Li, Shaojun Zhang, Xiyang Xue (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.